diff options
101 files changed, 3087 insertions, 954 deletions
diff --git a/.gitignore b/.gitignore index 0422adf44..26dbde73d 100644 --- a/.gitignore +++ b/.gitignore @@ -1,5 +1,6 @@ *.pyc *.pyo +*.class *~ *.DS_Store wine-py2exe/ @@ -32,4 +33,4 @@ test/testdata .tox youtube-dl.zsh .idea -.idea/*
\ No newline at end of file +.idea/* @@ -160,3 +160,6 @@ Erwin de Haan Jens Wille Robin Houtevelts Patrick Griffis +Aidan Rowe +mutantmonkey +Ben Congdon diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md index d15267d7e..c996f03ab 100644 --- a/CONTRIBUTING.md +++ b/CONTRIBUTING.md @@ -1,6 +1,6 @@ -**Please include the full output of youtube-dl when run with `-v`**, i.e. add `-v` flag to your command line, copy the **whole** output and post it in the issue body wrapped in \`\`\` for better formatting. It should look similar to this: +**Please include the full output of youtube-dl when run with `-v`**, i.e. **add** `-v` flag to **your command line**, copy the **whole** output and post it in the issue body wrapped in \`\`\` for better formatting. It should look similar to this: ``` -$ youtube-dl -v http://www.youtube.com/watch?v=BaW_jenozKcj +$ youtube-dl -v <your command line> [debug] System config: [] [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] @@ -92,7 +92,9 @@ If you want to create a build of youtube-dl yourself, you'll need ### Adding support for a new site -If you want to add support for a new site, you can follow this quick list (assuming your service is called `yourextractor`): +If you want to add support for a new site, first of all **make sure** this site is **not dedicated to [copyright infringement](#can-you-add-support-for-this-anime-video-site-or-site-which-shows-current-movies-for-free)**. youtube-dl does **not support** such sites thus pull requests adding support for them **will be rejected**. + +After you have ensured this site is distributing it's content legally, you can follow this quick list (assuming your service is called `yourextractor`): 1. [Fork this repository](https://github.com/rg3/youtube-dl/fork) 2. Check out the source code with `git clone git@github.com:YOUR_GITHUB_USERNAME/youtube-dl.git` @@ -140,16 +142,17 @@ If you want to add support for a new site, you can follow this quick list (assum ``` 5. Add an import in [`youtube_dl/extractor/__init__.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/__init__.py). 6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test, then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc. -7. Have a look at [`youtube_dl/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should and may return](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L62-L200). Add tests and code for as many as you want. -8. If you can, check the code with [flake8](https://pypi.python.org/pypi/flake8). -9. When the tests pass, [add](http://git-scm.com/docs/git-add) the new files and [commit](http://git-scm.com/docs/git-commit) them and [push](http://git-scm.com/docs/git-push) the result, like this: +7. Have a look at [`youtube_dl/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should and may return](https://github.com/rg3/youtube-dl/blob/58525c94d547be1c8167d16c298bdd75506db328/youtube_dl/extractor/common.py#L68-L226). Add tests and code for as many as you want. +8. Keep in mind that the only mandatory fields in info dict for successful extraction process are `id`, `title` and either `url` or `formats`, i.e. these are the critical data the extraction does not make any sense without. This means that [any field](https://github.com/rg3/youtube-dl/blob/58525c94d547be1c8167d16c298bdd75506db328/youtube_dl/extractor/common.py#L138-L226) apart from aforementioned mandatory ones should be treated **as optional** and extraction should be **tolerate** to situations when sources for these fields can potentially be unavailable (even if they always available at the moment) and **future-proof** in order not to break the extraction of general purpose mandatory fields. For example, if you have some intermediate dict `meta` that is a source of metadata and it has a key `summary` that you want to extract and put into resulting info dict as `description`, you should be ready that this key may be missing from the `meta` dict, i.e. you should extract it as `meta.get('summary')` and not `meta['summary']`. Similarly, you should pass `fatal=False` when extracting data from a webpage with `_search_regex/_html_search_regex`. +9. Check the code with [flake8](https://pypi.python.org/pypi/flake8). +10. When the tests pass, [add](http://git-scm.com/docs/git-add) the new files and [commit](http://git-scm.com/docs/git-commit) them and [push](http://git-scm.com/docs/git-push) the result, like this: $ git add youtube_dl/extractor/__init__.py $ git add youtube_dl/extractor/yourextractor.py $ git commit -m '[yourextractor] Add new extractor' $ git push origin yourextractor -10. Finally, [create a pull request](https://help.github.com/articles/creating-a-pull-request). We'll then review and merge it. +11. Finally, [create a pull request](https://help.github.com/articles/creating-a-pull-request). We'll then review and merge it. In any case, thank you very much for your contributions! @@ -3,6 +3,7 @@ all: youtube-dl README.md CONTRIBUTING.md README.txt youtube-dl.1 youtube-dl.bas clean: rm -rf youtube-dl.1.temp.md youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dl.tar.gz youtube-dl.zsh youtube-dl.fish *.dump *.part *.info.json *.mp4 *.flv *.mp3 *.avi CONTRIBUTING.md.tmp youtube-dl youtube-dl.exe find . -name "*.pyc" -delete + find . -name "*.class" -delete PREFIX ?= /usr/local BINDIR ?= $(PREFIX)/bin @@ -44,7 +45,7 @@ test: ot: offlinetest offlinetest: codetest - nosetests --verbose test --exclude test_download.py --exclude test_age_restriction.py --exclude test_subtitles.py --exclude test_write_annotations.py --exclude test_youtube_lists.py + $(PYTHON) -m nose --verbose test --exclude test_download.py --exclude test_age_restriction.py --exclude test_subtitles.py --exclude test_write_annotations.py --exclude test_youtube_lists.py --exclude test_iqiyi_sdk_interpreter.py tar: youtube-dl.tar.gz @@ -80,6 +80,8 @@ which means you can modify it, redistribute it or use it however you like. on Windows) --flat-playlist Do not extract the videos of a playlist, only list them. + --mark-watched Mark videos watched (YouTube only) + --no-mark-watched Do not mark videos watched (YouTube only) --no-color Do not emit color codes in output ## Network Options: @@ -409,13 +411,18 @@ which means you can modify it, redistribute it or use it however you like. # CONFIGURATION -You can configure youtube-dl by placing any supported command line option to a configuration file. On Linux, the system wide configuration file is located at `/etc/youtube-dl.conf` and the user wide configuration file at `~/.config/youtube-dl/config`. On Windows, the user wide configuration file locations are `%APPDATA%\youtube-dl\config.txt` or `C:\Users\<user name>\youtube-dl.conf`. For example, with the following configuration file youtube-dl will always extract the audio, not copy the mtime and use a proxy: +You can configure youtube-dl by placing any supported command line option to a configuration file. On Linux, the system wide configuration file is located at `/etc/youtube-dl.conf` and the user wide configuration file at `~/.config/youtube-dl/config`. On Windows, the user wide configuration file locations are `%APPDATA%\youtube-dl\config.txt` or `C:\Users\<user name>\youtube-dl.conf`. + +For example, with the following configuration file youtube-dl will always extract the audio, not copy the mtime, use a proxy and save all videos under `Movies` directory in your home directory: ``` ---extract-audio +-x --no-mtime --proxy 127.0.0.1:3128 +-o ~/Movies/%(title)s.%(ext)s ``` +Note that options in configuration file are just the same options aka switches used in regular command line calls thus there **must be no whitespace** after `-` or `--`, e.g. `-o` or `--proxy` but not `- o` or `-- proxy`. + You can use `--ignore-config` if you want to disable the configuration file for a particular youtube-dl run. ### Authentication with `.netrc` file @@ -440,7 +447,11 @@ On Windows you may also need to setup the `%HOME%` environment variable manually # OUTPUT TEMPLATE -The `-o` option allows users to indicate a template for the output file names. The basic usage is not to set any template arguments when downloading a single file, like in `youtube-dl -o funny_video.flv "http://some/video"`. However, it may contain special sequences that will be replaced when downloading each video. The special sequences have the format `%(NAME)s`. To clarify, that is a percent symbol followed by a name in parentheses, followed by a lowercase S. Allowed names are: +The `-o` option allows users to indicate a template for the output file names. + +**tl;dr:** [navigate me to examples](#output-template-examples). + +The basic usage is not to set any template arguments when downloading a single file, like in `youtube-dl -o funny_video.flv "http://some/video"`. However, it may contain special sequences that will be replaced when downloading each video. The special sequences have the format `%(NAME)s`. To clarify, that is a percent symbol followed by a name in parentheses, followed by a lowercase S. Allowed names are: - `id`: Video identifier - `title`: Video title @@ -449,6 +460,7 @@ The `-o` option allows users to indicate a template for the output file names. T - `alt_title`: A secondary title of the video - `display_id`: An alternative identifier for the video - `uploader`: Full name of the video uploader + - `license`: License name the video is licensed under - `creator`: The main artist who created the video - `release_date`: The date (YYYYMMDD) when the video was released - `timestamp`: UNIX timestamp of the moment the video became available @@ -513,7 +525,9 @@ The current default template is `%(title)s-%(id)s.%(ext)s`. In some cases, you don't want special characters such as 中, spaces, or &, such as when transferring the downloaded filename to a Windows system or the filename through an 8bit-unsafe channel. In these cases, add the `--restrict-filenames` flag to get a shorter title: -Examples (note on Windows you may need to use double quotes instead of single): +#### Output template examples + +Note on Windows you may need to use double quotes instead of single. ```bash $ youtube-dl --get-filename -o '%(title)s.%(ext)s' BaW_jenozKc @@ -525,6 +539,9 @@ youtube-dl_test_video_.mp4 # A simple file name # Download YouTube playlist videos in separate directory indexed by video order in a playlist $ youtube-dl -o '%(playlist)s/%(playlist_index)s - %(title)s.%(ext)s' https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re +# Download all playlists of YouTube channel/user keeping each playlist in separate directory: +$ youtube-dl -o '%(uploader)s/%(playlist)s/%(playlist_index)s - %(title)s.%(ext)s' https://www.youtube.com/user/TheLinuxFoundation/playlists + # Download Udemy course keeping each chapter in separate directory under MyVideos directory in your home $ youtube-dl -u user -p password -o '~/MyVideos/%(playlist)s/%(chapter_number)s - %(chapter)s/%(title)s.%(ext)s' https://www.udemy.com/java-tutorial/ @@ -543,6 +560,8 @@ But sometimes you may want to download in a different format, for example when y The general syntax for format selection is `--format FORMAT` or shorter `-f FORMAT` where `FORMAT` is a *selector expression*, i.e. an expression that describes format or formats you would like to download. +**tl;dr:** [navigate me to examples](#format-selection-examples). + The simplest case is requesting a specific format, for example with `-f 22` you can download the format with format code equal to 22. You can get the list of available format codes for particular video using `--list-formats` or `-F`. Note that these format codes are extractor specific. You can also use a file extension (currently `3gp`, `aac`, `flv`, `m4a`, `mp3`, `mp4`, `ogg`, `wav`, `webm` are supported) to download best quality format of particular file extension served as a single file, e.g. `-f webm` will download best quality format with `webm` extension served as a single file. @@ -588,11 +607,14 @@ You can merge the video and audio of two formats into a single file using `-f <v Format selectors can also be grouped using parentheses, for example if you want to download the best mp4 and webm formats with a height lower than 480 you can use `-f '(mp4,webm)[height<480]'`. -Since the end of April 2015 and version 2015.04.26 youtube-dl uses `-f bestvideo+bestaudio/best` as default format selection (see #5447, #5456). If ffmpeg or avconv are installed this results in downloading `bestvideo` and `bestaudio` separately and muxing them together into a single file giving the best overall quality available. Otherwise it falls back to `best` and results in downloading the best available quality served as a single file. `best` is also needed for videos that don't come from YouTube because they don't provide the audio and video in two different files. If you want to only download some DASH formats (for example if you are not interested in getting videos with a resolution higher than 1080p), you can add `-f bestvideo[height<=?1080]+bestaudio/best` to your configuration file. Note that if you use youtube-dl to stream to `stdout` (and most likely to pipe it to your media player then), i.e. you explicitly specify output template as `-o -`, youtube-dl still uses `-f best` format selection in order to start content delivery immediately to your player and not to wait until `bestvideo` and `bestaudio` are downloaded and muxed. +Since the end of April 2015 and version 2015.04.26 youtube-dl uses `-f bestvideo+bestaudio/best` as default format selection (see [#5447](https://github.com/rg3/youtube-dl/issues/5447), [#5456](https://github.com/rg3/youtube-dl/issues/5456)). If ffmpeg or avconv are installed this results in downloading `bestvideo` and `bestaudio` separately and muxing them together into a single file giving the best overall quality available. Otherwise it falls back to `best` and results in downloading the best available quality served as a single file. `best` is also needed for videos that don't come from YouTube because they don't provide the audio and video in two different files. If you want to only download some DASH formats (for example if you are not interested in getting videos with a resolution higher than 1080p), you can add `-f bestvideo[height<=?1080]+bestaudio/best` to your configuration file. Note that if you use youtube-dl to stream to `stdout` (and most likely to pipe it to your media player then), i.e. you explicitly specify output template as `-o -`, youtube-dl still uses `-f best` format selection in order to start content delivery immediately to your player and not to wait until `bestvideo` and `bestaudio` are downloaded and muxed. If you want to preserve the old format selection behavior (prior to youtube-dl 2015.04.26), i.e. you want to download the best available quality media served as a single file, you should explicitly specify your choice with `-f best`. You may want to add it to the [configuration file](#configuration) in order not to type it every time you run youtube-dl. -Examples (note on Windows you may need to use double quotes instead of single): +#### Format selection examples + +Note on Windows you may need to use double quotes instead of single. + ```bash # Download best mp4 format available or any other best if no mp4 available $ youtube-dl -f 'bestvideo[ext=mp4]+bestaudio[ext=m4a]/best[ext=mp4]/best' @@ -733,7 +755,7 @@ means you're using an outdated version of Python. Please update to Python 2.6 or ### What is this binary file? Where has the code gone? -Since June 2012 (#342) youtube-dl is packed as an executable zipfile, simply unzip it (might need renaming to `youtube-dl.zip` first on some systems) or clone the git repository, as laid out above. If you modify the code, you can run it by executing the `__main__.py` file. To recompile the executable, run `make youtube-dl`. +Since June 2012 ([#342](https://github.com/rg3/youtube-dl/issues/342)) youtube-dl is packed as an executable zipfile, simply unzip it (might need renaming to `youtube-dl.zip` first on some systems) or clone the git repository, as laid out above. If you modify the code, you can run it by executing the `__main__.py` file. To recompile the executable, run `make youtube-dl`. ### The exe throws a *Runtime error from Visual C++* @@ -816,7 +838,9 @@ If you want to create a build of youtube-dl yourself, you'll need ### Adding support for a new site -If you want to add support for a new site, you can follow this quick list (assuming your service is called `yourextractor`): +If you want to add support for a new site, first of all **make sure** this site is **not dedicated to [copyright infringement](#can-you-add-support-for-this-anime-video-site-or-site-which-shows-current-movies-for-free)**. youtube-dl does **not support** such sites thus pull requests adding support for them **will be rejected**. + +After you have ensured this site is distributing it's content legally, you can follow this quick list (assuming your service is called `yourextractor`): 1. [Fork this repository](https://github.com/rg3/youtube-dl/fork) 2. Check out the source code with `git clone git@github.com:YOUR_GITHUB_USERNAME/youtube-dl.git` @@ -864,16 +888,17 @@ If you want to add support for a new site, you can follow this quick list (assum ``` 5. Add an import in [`youtube_dl/extractor/__init__.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/__init__.py). 6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test, then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc. -7. Have a look at [`youtube_dl/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should and may return](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L62-L200). Add tests and code for as many as you want. -8. If you can, check the code with [flake8](https://pypi.python.org/pypi/flake8). -9. When the tests pass, [add](http://git-scm.com/docs/git-add) the new files and [commit](http://git-scm.com/docs/git-commit) them and [push](http://git-scm.com/docs/git-push) the result, like this: +7. Have a look at [`youtube_dl/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should and may return](https://github.com/rg3/youtube-dl/blob/58525c94d547be1c8167d16c298bdd75506db328/youtube_dl/extractor/common.py#L68-L226). Add tests and code for as many as you want. +8. Keep in mind that the only mandatory fields in info dict for successful extraction process are `id`, `title` and either `url` or `formats`, i.e. these are the critical data the extraction does not make any sense without. This means that [any field](https://github.com/rg3/youtube-dl/blob/58525c94d547be1c8167d16c298bdd75506db328/youtube_dl/extractor/common.py#L138-L226) apart from aforementioned mandatory ones should be treated **as optional** and extraction should be **tolerate** to situations when sources for these fields can potentially be unavailable (even if they always available at the moment) and **future-proof** in order not to break the extraction of general purpose mandatory fields. For example, if you have some intermediate dict `meta` that is a source of metadata and it has a key `summary` that you want to extract and put into resulting info dict as `description`, you should be ready that this key may be missing from the `meta` dict, i.e. you should extract it as `meta.get('summary')` and not `meta['summary']`. Similarly, you should pass `fatal=False` when extracting data from a webpage with `_search_regex/_html_search_regex`. +9. Check the code with [flake8](https://pypi.python.org/pypi/flake8). +10. When the tests pass, [add](http://git-scm.com/docs/git-add) the new files and [commit](http://git-scm.com/docs/git-commit) them and [push](http://git-scm.com/docs/git-push) the result, like this: $ git add youtube_dl/extractor/__init__.py $ git add youtube_dl/extractor/yourextractor.py $ git commit -m '[yourextractor] Add new extractor' $ git push origin yourextractor -10. Finally, [create a pull request](https://help.github.com/articles/creating-a-pull-request). We'll then review and merge it. +11. Finally, [create a pull request](https://help.github.com/articles/creating-a-pull-request). We'll then review and merge it. In any case, thank you very much for your contributions! diff --git a/docs/supportedsites.md b/docs/supportedsites.md index b384a3165..0682e4af0 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -30,6 +30,7 @@ - **AlJazeera** - **Allocine** - **AlphaPorno** + - **AnimeOnDemand** - **anitube.se** - **AnySex** - **Aparat** @@ -49,6 +50,7 @@ - **arte.tv:ddc** - **arte.tv:embed** - **arte.tv:future** + - **arte.tv:magazine** - **AtresPlayer** - **ATTTechChannel** - **AudiMedia** @@ -75,6 +77,7 @@ - **BleacherReportCMS** - **blinkx** - **Bloomberg** + - **BokeCC** - **Bpb**: Bundeszentrale für politische Bildung - **BR**: Bayerischer Rundfunk Mediathek - **Break** @@ -191,6 +194,7 @@ - **faz.net** - **fc2** - **Fczenit** + - **features.aol.com** - **fernsehkritik.tv** - **Firstpost** - **FiveTV** @@ -290,6 +294,7 @@ - **kontrtube**: KontrTube.ru - Труба зовёт - **KrasView**: Красвью - **Ku6** + - **KUSI** - **kuwo:album**: 酷我音乐 - 专辑 - **kuwo:category**: 酷我音乐 - 分类 - **kuwo:chart**: 酷我音乐 - 排行榜 @@ -298,12 +303,11 @@ - **kuwo:song**: 酷我音乐 - **la7.tv** - **Laola1Tv** + - **Le**: 乐视网 - **Lecture2Go** - **Lemonde** - - **Letv**: 乐视网 + - **LePlaylist** - **LetvCloud**: 乐视云 - - **LetvPlaylist** - - **LetvTv** - **Libsyn** - **life:embed** - **lifenews**: LIFE | NEWS @@ -360,7 +364,7 @@ - **MySpace:album** - **MySpass** - **Myvi** - - **myvideo** + - **myvideo** (Currently broken) - **MyVidster** - **n-tv.de** - **NationalGeographic** @@ -410,6 +414,7 @@ - **NowTV** (Currently broken) - **NowTVList** - **nowvideo**: NowVideo + - **Noz** - **npo**: npo.nl and ntr.nl - **npo.nl:live** - **npo.nl:radio** @@ -417,6 +422,7 @@ - **Npr** - **NRK** - **NRKPlaylist** + - **NRKSkole**: NRK Skole - **NRKTV**: NRK TV and NRK Radio - **ntv.ru** - **Nuvid** @@ -460,6 +466,7 @@ - **PornHd** - **PornHub** - **PornHubPlaylist** + - **PornHubUserVideos** - **Pornotube** - **PornoVoisines** - **PornoXO** @@ -522,6 +529,7 @@ - **screen.yahoo:search**: Yahoo screen search - **Screencast** - **ScreencastOMatic** + - **ScreenJunkies** - **ScreenwaveMedia** - **SenateISVP** - **ServingSys** @@ -555,7 +563,6 @@ - **southpark.de** - **southpark.nl** - **southparkstudios.dk** - - **Space** - **SpankBang** - **Spankwire** - **Spiegel** @@ -615,6 +622,7 @@ - **TMZ** - **TMZArticle** - **TNAFlix** + - **TNAFlixNetworkEmbed** - **toggle** - **tou.tv** - **Toypics**: Toypics user profile @@ -655,6 +663,7 @@ - **twitch:video** - **twitch:vod** - **twitter** + - **twitter:amplify** - **twitter:card** - **Ubu** - **udemy** @@ -664,6 +673,7 @@ - **Urort**: NRK P3 Urørt - **ustream** - **ustream:channel** + - **Ustudio** - **Varzesh3** - **Vbox7** - **VeeHD** @@ -679,7 +689,7 @@ - **video.mit.edu** - **VideoDetective** - **videofy.me** - - **VideoMega** (Currently broken) + - **VideoMega** - **videomore** - **videomore:season** - **videomore:video** diff --git a/test/helper.py b/test/helper.py index bdd7acca4..f2d878212 100644 --- a/test/helper.py +++ b/test/helper.py @@ -11,8 +11,11 @@ import sys import youtube_dl.extractor from youtube_dl import YoutubeDL -from youtube_dl.utils import ( +from youtube_dl.compat import ( + compat_os_name, compat_str, +) +from youtube_dl.utils import ( preferredencoding, write_string, ) @@ -42,7 +45,7 @@ def report_warning(message): Print the message to stderr, it will be prefixed with 'WARNING:' If stderr is a tty file the 'WARNING:' will be colored ''' - if sys.stderr.isatty() and os.name != 'nt': + if sys.stderr.isatty() and compat_os_name != 'nt': _msg_header = '\033[0;33mWARNING:\033[0m' else: _msg_header = 'WARNING:' diff --git a/test/test_YoutubeDL.py b/test/test_YoutubeDL.py index 02caf5908..efbee3b71 100644 --- a/test/test_YoutubeDL.py +++ b/test/test_YoutubeDL.py @@ -234,7 +234,7 @@ class TestFormatSelection(unittest.TestCase): def test_youtube_format_selection(self): order = [ - '38', '37', '46', '22', '45', '35', '44', '18', '34', '43', '6', '5', '36', '17', '13', + '38', '37', '46', '22', '45', '35', '44', '18', '34', '43', '6', '5', '17', '36', '13', # Apple HTTP Live Streaming '96', '95', '94', '93', '92', '132', '151', # 3D @@ -502,6 +502,9 @@ class TestYoutubeDL(unittest.TestCase): assertRegexpMatches(self, ydl._format_note({ 'vbr': 10, }), '^\s*10k$') + assertRegexpMatches(self, ydl._format_note({ + 'fps': 30, + }), '^30fps$') def test_postprocessors(self): filename = 'post-processor-testfile.mp4' diff --git a/test/test_http.py b/test/test_http.py index f2e305b6f..fc59b1aed 100644 --- a/test/test_http.py +++ b/test/test_http.py @@ -52,7 +52,12 @@ class TestHTTP(unittest.TestCase): ('localhost', 0), HTTPTestRequestHandler) self.httpd.socket = ssl.wrap_socket( self.httpd.socket, certfile=certfn, server_side=True) - self.port = self.httpd.socket.getsockname()[1] + if os.name == 'java': + # In Jython SSLSocket is not a subclass of socket.socket + sock = self.httpd.socket.sock + else: + sock = self.httpd.socket + self.port = sock.getsockname()[1] self.server_thread = threading.Thread(target=self.httpd.serve_forever) self.server_thread.daemon = True self.server_thread.start() diff --git a/test/test_iqiyi_sdk_interpreter.py b/test/test_iqiyi_sdk_interpreter.py new file mode 100644 index 000000000..9d95cb606 --- /dev/null +++ b/test/test_iqiyi_sdk_interpreter.py @@ -0,0 +1,47 @@ +#!/usr/bin/env python + +from __future__ import unicode_literals + +# Allow direct execution +import os +import sys +import unittest +sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) + +from test.helper import FakeYDL +from youtube_dl.extractor import IqiyiIE + + +class IqiyiIEWithCredentials(IqiyiIE): + def _get_login_info(self): + return 'foo', 'bar' + + +class WarningLogger(object): + def __init__(self): + self.messages = [] + + def warning(self, msg): + self.messages.append(msg) + + def debug(self, msg): + pass + + def error(self, msg): + pass + + +class TestIqiyiSDKInterpreter(unittest.TestCase): + def test_iqiyi_sdk_interpreter(self): + ''' + Test the functionality of IqiyiSDKInterpreter by trying to log in + + If `sign` is incorrect, /validate call throws an HTTP 556 error + ''' + logger = WarningLogger() + ie = IqiyiIEWithCredentials(FakeYDL({'logger': logger})) + ie._login() + self.assertTrue('unable to log in:' in logger.messages[0]) + +if __name__ == '__main__': + unittest.main() diff --git a/test/test_utils.py b/test/test_utils.py index a1e416dd5..bc28ceb34 100644 --- a/test/test_utils.py +++ b/test/test_utils.py @@ -18,6 +18,7 @@ import xml.etree.ElementTree from youtube_dl.utils import ( age_restricted, args_to_str, + encode_base_n, clean_html, DateRange, detect_exe_version, @@ -35,10 +36,12 @@ from youtube_dl.utils import ( is_html, js_to_json, limit_length, + ohdave_rsa_encrypt, OnDemandPagedList, orderedSet, parse_duration, parse_filesize, + parse_count, parse_iso8601, read_batch_urls, sanitize_filename, @@ -59,6 +62,7 @@ from youtube_dl.utils import ( lowercase_escape, url_basename, urlencode_postdata, + update_url_query, version_tuple, xpath_with_ns, xpath_element, @@ -74,6 +78,8 @@ from youtube_dl.utils import ( ) from youtube_dl.compat import ( compat_etree_fromstring, + compat_urlparse, + compat_parse_qs, ) @@ -248,6 +254,7 @@ class TestUtil(unittest.TestCase): self.assertEqual( unified_strdate('2/2/2015 6:47:40 PM', day_first=False), '20150202') + self.assertEqual(unified_strdate('Feb 14th 2016 5:45PM'), '20160214') self.assertEqual(unified_strdate('25-09-2014'), '20140925') self.assertEqual(unified_strdate('UNKNOWN DATE FORMAT'), None) @@ -451,6 +458,40 @@ class TestUtil(unittest.TestCase): data = urlencode_postdata({'username': 'foo@bar.com', 'password': '1234'}) self.assertTrue(isinstance(data, bytes)) + def test_update_url_query(self): + def query_dict(url): + return compat_parse_qs(compat_urlparse.urlparse(url).query) + self.assertEqual(query_dict(update_url_query( + 'http://example.com/path', {'quality': ['HD'], 'format': ['mp4']})), + query_dict('http://example.com/path?quality=HD&format=mp4')) + self.assertEqual(query_dict(update_url_query( + 'http://example.com/path', {'system': ['LINUX', 'WINDOWS']})), + query_dict('http://example.com/path?system=LINUX&system=WINDOWS')) + self.assertEqual(query_dict(update_url_query( + 'http://example.com/path', {'fields': 'id,formats,subtitles'})), + query_dict('http://example.com/path?fields=id,formats,subtitles')) + self.assertEqual(query_dict(update_url_query( + 'http://example.com/path', {'fields': ('id,formats,subtitles', 'thumbnails')})), + query_dict('http://example.com/path?fields=id,formats,subtitles&fields=thumbnails')) + self.assertEqual(query_dict(update_url_query( + 'http://example.com/path?manifest=f4m', {'manifest': []})), + query_dict('http://example.com/path')) + self.assertEqual(query_dict(update_url_query( + 'http://example.com/path?system=LINUX&system=WINDOWS', {'system': 'LINUX'})), + query_dict('http://example.com/path?system=LINUX')) + self.assertEqual(query_dict(update_url_query( + 'http://example.com/path', {'fields': b'id,formats,subtitles'})), + query_dict('http://example.com/path?fields=id,formats,subtitles')) + self.assertEqual(query_dict(update_url_query( + 'http://example.com/path', {'width': 1080, 'height': 720})), + query_dict('http://example.com/path?width=1080&height=720')) + self.assertEqual(query_dict(update_url_query( + 'http://example.com/path', {'bitrate': 5020.43})), + query_dict('http://example.com/path?bitrate=5020.43')) + self.assertEqual(query_dict(update_url_query( + 'http://example.com/path', {'test': '第二行тест'})), + query_dict('http://example.com/path?test=%E7%AC%AC%E4%BA%8C%E8%A1%8C%D1%82%D0%B5%D1%81%D1%82')) + def test_dict_get(self): FALSE_VALUES = { 'none': None, @@ -613,6 +654,15 @@ class TestUtil(unittest.TestCase): self.assertEqual(parse_filesize('1.2Tb'), 1200000000000) self.assertEqual(parse_filesize('1,24 KB'), 1240) + def test_parse_count(self): + self.assertEqual(parse_count(None), None) + self.assertEqual(parse_count(''), None) + self.assertEqual(parse_count('0'), 0) + self.assertEqual(parse_count('1000'), 1000) + self.assertEqual(parse_count('1.000'), 1000) + self.assertEqual(parse_count('1.1k'), 1100) + self.assertEqual(parse_count('1.1kk'), 1100000) + def test_version_tuple(self): self.assertEqual(version_tuple('1'), (1,)) self.assertEqual(version_tuple('10.23.344'), (10, 23, 344)) @@ -792,6 +842,24 @@ The first line {'nocheckcertificate': False}, '--check-certificate', 'nocheckcertificate', 'false', 'true', '='), ['--check-certificate=true']) + def test_ohdave_rsa_encrypt(self): + N = 0xab86b6371b5318aaa1d3c9e612a9f1264f372323c8c0f19875b5fc3b3fd3afcc1e5bec527aa94bfa85bffc157e4245aebda05389a5357b75115ac94f074aefcd + e = 65537 + + self.assertEqual( + ohdave_rsa_encrypt(b'aa111222', e, N), + '726664bd9a23fd0c70f9f1b84aab5e3905ce1e45a584e9cbcf9bcc7510338fc1986d6c599ff990d923aa43c51c0d9013cd572e13bc58f4ae48f2ed8c0b0ba881') + + def test_encode_base_n(self): + self.assertEqual(encode_base_n(0, 30), '0') + self.assertEqual(encode_base_n(80, 30), '2k') + + custom_table = '9876543210ZYXWVUTSRQPONMLKJIHGFEDCBA' + self.assertEqual(encode_base_n(0, 30, custom_table), '9') + self.assertEqual(encode_base_n(80, 30, custom_table), '7P') + + self.assertRaises(ValueError, encode_base_n, 0, 70) + self.assertRaises(ValueError, encode_base_n, 0, 60, custom_table) if __name__ == '__main__': unittest.main() diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py index f4324039c..8c651cd52 100755 --- a/youtube_dl/YoutubeDL.py +++ b/youtube_dl/YoutubeDL.py @@ -24,9 +24,6 @@ import time import tokenize import traceback -if os.name == 'nt': - import ctypes - from .compat import ( compat_basestring, compat_cookiejar, @@ -34,6 +31,7 @@ from .compat import ( compat_get_terminal_size, compat_http_client, compat_kwargs, + compat_os_name, compat_str, compat_tokenize_tokenize, compat_urllib_error, @@ -87,6 +85,7 @@ from .extractor import get_info_extractor, gen_extractors from .downloader import get_suitable_downloader from .downloader.rtmp import rtmpdump_version from .postprocessor import ( + FFmpegFixupM3u8PP, FFmpegFixupM4aPP, FFmpegFixupStretchedPP, FFmpegMergerPP, @@ -95,6 +94,9 @@ from .postprocessor import ( ) from .version import __version__ +if compat_os_name == 'nt': + import ctypes + class YoutubeDL(object): """YoutubeDL class. @@ -450,7 +452,7 @@ class YoutubeDL(object): def to_console_title(self, message): if not self.params.get('consoletitle', False): return - if os.name == 'nt' and ctypes.windll.kernel32.GetConsoleWindow(): + if compat_os_name == 'nt' and ctypes.windll.kernel32.GetConsoleWindow(): # c_wchar_p() might not be necessary if `message` is # already of type unicode() ctypes.windll.kernel32.SetConsoleTitleW(ctypes.c_wchar_p(message)) @@ -521,7 +523,7 @@ class YoutubeDL(object): else: if self.params.get('no_warnings'): return - if not self.params.get('no_color') and self._err_file.isatty() and os.name != 'nt': + if not self.params.get('no_color') and self._err_file.isatty() and compat_os_name != 'nt': _msg_header = '\033[0;33mWARNING:\033[0m' else: _msg_header = 'WARNING:' @@ -533,7 +535,7 @@ class YoutubeDL(object): Do the same as trouble, but prefixes the message with 'ERROR:', colored in red if stderr is a tty file. ''' - if not self.params.get('no_color') and self._err_file.isatty() and os.name != 'nt': + if not self.params.get('no_color') and self._err_file.isatty() and compat_os_name != 'nt': _msg_header = '\033[0;31mERROR:\033[0m' else: _msg_header = 'ERROR:' @@ -566,7 +568,7 @@ class YoutubeDL(object): elif template_dict.get('height'): template_dict['resolution'] = '%sp' % template_dict['height'] elif template_dict.get('width'): - template_dict['resolution'] = '?x%d' % template_dict['width'] + template_dict['resolution'] = '%dx?' % template_dict['width'] sanitize = lambda k, v: sanitize_filename( compat_str(v), @@ -1232,6 +1234,10 @@ class YoutubeDL(object): if t.get('id') is None: t['id'] = '%d' % i + if self.params.get('list_thumbnails'): + self.list_thumbnails(info_dict) + return + if thumbnails and 'thumbnail' not in info_dict: info_dict['thumbnail'] = thumbnails[-1]['url'] @@ -1333,9 +1339,6 @@ class YoutubeDL(object): if self.params.get('listformats'): self.list_formats(info_dict) return - if self.params.get('list_thumbnails'): - self.list_thumbnails(info_dict) - return req_format = self.params.get('format') if req_format is None: @@ -1631,12 +1634,14 @@ class YoutubeDL(object): self.report_error('content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded)) return - if success: + if success and filename != '-': # Fixup content fixup_policy = self.params.get('fixup') if fixup_policy is None: fixup_policy = 'detect_or_warn' + INSTALL_FFMPEG_MESSAGE = 'Install ffmpeg or avconv to fix this automatically.' + stretched_ratio = info_dict.get('stretched_ratio') if stretched_ratio is not None and stretched_ratio != 1: if fixup_policy == 'warn': @@ -1649,15 +1654,18 @@ class YoutubeDL(object): info_dict['__postprocessors'].append(stretched_pp) else: self.report_warning( - '%s: Non-uniform pixel ratio (%s). Install ffmpeg or avconv to fix this automatically.' % ( - info_dict['id'], stretched_ratio)) + '%s: Non-uniform pixel ratio (%s). %s' + % (info_dict['id'], stretched_ratio, INSTALL_FFMPEG_MESSAGE)) else: assert fixup_policy in ('ignore', 'never') - if info_dict.get('requested_formats') is None and info_dict.get('container') == 'm4a_dash': + if (info_dict.get('requested_formats') is None and + info_dict.get('container') == 'm4a_dash'): if fixup_policy == 'warn': - self.report_warning('%s: writing DASH m4a. Only some players support this container.' % ( - info_dict['id'])) + self.report_warning( + '%s: writing DASH m4a. ' + 'Only some players support this container.' + % info_dict['id']) elif fixup_policy == 'detect_or_warn': fixup_pp = FFmpegFixupM4aPP(self) if fixup_pp.available: @@ -1665,8 +1673,27 @@ class YoutubeDL(object): info_dict['__postprocessors'].append(fixup_pp) else: self.report_warning( - '%s: writing DASH m4a. Only some players support this container. Install ffmpeg or avconv to fix this automatically.' % ( - info_dict['id'])) + '%s: writing DASH m4a. ' + 'Only some players support this container. %s' + % (info_dict['id'], INSTALL_FFMPEG_MESSAGE)) + else: + assert fixup_policy in ('ignore', 'never') + + if (info_dict.get('protocol') == 'm3u8_native' or + info_dict.get('protocol') == 'm3u8' and + self.params.get('hls_prefer_native')): + if fixup_policy == 'warn': + self.report_warning('%s: malformated aac bitstream.' % ( + info_dict['id'])) + elif fixup_policy == 'detect_or_warn': + fixup_pp = FFmpegFixupM3u8PP(self) + if fixup_pp.available: + info_dict.setdefault('__postprocessors', []) + info_dict['__postprocessors'].append(fixup_pp) + else: + self.report_warning( + '%s: malformated aac bitstream. %s' + % (info_dict['id'], INSTALL_FFMPEG_MESSAGE)) else: assert fixup_policy in ('ignore', 'never') @@ -1830,7 +1857,9 @@ class YoutubeDL(object): if fdict.get('vbr') is not None: res += '%4dk' % fdict['vbr'] if fdict.get('fps') is not None: - res += ', %sfps' % fdict['fps'] + if res: + res += ', ' + res += '%sfps' % fdict['fps'] if fdict.get('acodec') is not None: if res: res += ', ' @@ -1873,13 +1902,8 @@ class YoutubeDL(object): def list_thumbnails(self, info_dict): thumbnails = info_dict.get('thumbnails') if not thumbnails: - tn_url = info_dict.get('thumbnail') - if tn_url: - thumbnails = [{'id': '0', 'url': tn_url}] - else: - self.to_screen( - '[info] No thumbnails present for %s' % info_dict['id']) - return + self.to_screen('[info] No thumbnails present for %s' % info_dict['id']) + return self.to_screen( '[info] Thumbnails for %s:' % info_dict['id']) diff --git a/youtube_dl/__init__.py b/youtube_dl/__init__.py index f5f064241..79b389840 100644 --- a/youtube_dl/__init__.py +++ b/youtube_dl/__init__.py @@ -355,6 +355,7 @@ def _real_main(argv=None): 'youtube_include_dash_manifest': opts.youtube_include_dash_manifest, 'encoding': opts.encoding, 'extract_flat': opts.extract_flat, + 'mark_watched': opts.mark_watched, 'merge_output_format': opts.merge_output_format, 'postprocessors': postprocessors, 'fixup': opts.fixup, diff --git a/youtube_dl/compat.py b/youtube_dl/compat.py index b497da696..2771fb5fa 100644 --- a/youtube_dl/compat.py +++ b/youtube_dl/compat.py @@ -326,6 +326,9 @@ def compat_ord(c): return ord(c) +compat_os_name = os._name if os.name == 'java' else os.name + + if sys.version_info >= (3, 0): compat_getenv = os.getenv compat_expanduser = os.path.expanduser @@ -346,7 +349,7 @@ else: # The following are os.path.expanduser implementations from cpython 2.7.8 stdlib # for different platforms with correct environment variables decoding. - if os.name == 'posix': + if compat_os_name == 'posix': def compat_expanduser(path): """Expand ~ and ~user constructions. If user or $HOME is unknown, do nothing.""" @@ -370,7 +373,7 @@ else: userhome = pwent.pw_dir userhome = userhome.rstrip('/') return (userhome + path[i:]) or '/' - elif os.name == 'nt' or os.name == 'ce': + elif compat_os_name == 'nt' or compat_os_name == 'ce': def compat_expanduser(path): """Expand ~ and ~user constructs. @@ -556,6 +559,7 @@ __all__ = [ 'compat_itertools_count', 'compat_kwargs', 'compat_ord', + 'compat_os_name', 'compat_parse_qs', 'compat_print', 'compat_shlex_split', diff --git a/youtube_dl/downloader/common.py b/youtube_dl/downloader/common.py index 2d5154051..f39db58f6 100644 --- a/youtube_dl/downloader/common.py +++ b/youtube_dl/downloader/common.py @@ -5,6 +5,7 @@ import re import sys import time +from ..compat import compat_os_name from ..utils import ( encodeFilename, error_to_compat_str, @@ -219,7 +220,7 @@ class FileDownloader(object): if self.params.get('progress_with_newline', False): self.to_screen(fullmsg) else: - if os.name == 'nt': + if compat_os_name == 'nt': prev_len = getattr(self, '_report_progress_prev_line_length', 0) if prev_len > len(fullmsg): diff --git a/youtube_dl/downloader/fragment.py b/youtube_dl/downloader/fragment.py index 5bc99492b..a5bae9669 100644 --- a/youtube_dl/downloader/fragment.py +++ b/youtube_dl/downloader/fragment.py @@ -99,7 +99,8 @@ class FragmentFD(FileDownloader): state['eta'] = self.calc_eta( start, time_now, estimated_size, state['downloaded_bytes']) - state['speed'] = s.get('speed') + state['speed'] = s.get('speed') or ctx.get('speed') + ctx['speed'] = state['speed'] ctx['prev_frag_downloaded_bytes'] = frag_downloaded_bytes self._hook_progress(state) diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 1edbfbd28..c5b80f4aa 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -23,7 +23,10 @@ from .alphaporno import AlphaPornoIE from .animeondemand import AnimeOnDemandIE from .anitube import AnitubeIE from .anysex import AnySexIE -from .aol import AolIE +from .aol import ( + AolIE, + AolFeaturesIE, +) from .allocine import AllocineIE from .aparat import AparatIE from .appleconnect import AppleConnectIE @@ -51,6 +54,7 @@ from .arte import ( from .atresplayer import AtresPlayerIE from .atttechchannel import ATTTechChannelIE from .audimedia import AudiMediaIE +from .audioboom import AudioBoomIE from .audiomack import AudiomackIE, AudiomackAlbumIE from .azubu import AzubuIE, AzubuLiveIE from .baidu import BaiduVideoIE @@ -74,6 +78,7 @@ from .bleacherreport import ( ) from .blinkx import BlinkxIE from .bloomberg import BloombergIE +from .bokecc import BokeCCIE from .bpb import BpbIE from .br import BRIE from .breakcom import BreakIE @@ -184,6 +189,10 @@ from .dumpert import DumpertIE from .defense import DefenseGouvFrIE from .discovery import DiscoveryIE from .dropbox import DropboxIE +from .dw import ( + DWIE, + DWArticleIE, +) from .eagleplatform import EaglePlatformIE from .ebaumsworld import EbaumsWorldIE from .echomsk import EchoMskIE @@ -208,10 +217,7 @@ from .everyonesmixtape import EveryonesMixtapeIE from .exfm import ExfmIE from .expotv import ExpoTVIE from .extremetube import ExtremeTubeIE -from .facebook import ( - FacebookIE, - FacebookPostIE, -) +from .facebook import FacebookIE from .faz import FazIE from .fc2 import FC2IE from .fczenit import FczenitIE @@ -339,6 +345,7 @@ from .konserthusetplay import KonserthusetPlayIE from .kontrtube import KontrTubeIE from .krasview import KrasViewIE from .ku6 import Ku6IE +from .kusi import KUSIIE from .kuwo import ( KuwoIE, KuwoAlbumIE, @@ -351,10 +358,9 @@ from .la7 import LA7IE from .laola1tv import Laola1TvIE from .lecture2go import Lecture2GoIE from .lemonde import LemondeIE -from .letv import ( - LetvIE, - LetvTvIE, - LetvPlaylistIE, +from .leeco import ( + LeIE, + LePlaylistIE, LetvCloudIE, ) from .libsyn import LibsynIE @@ -383,6 +389,7 @@ from .lynda import ( from .m6 import M6IE from .macgamestore import MacGameStoreIE from .mailru import MailRuIE +from .makerschannel import MakersChannelIE from .makertv import MakerTVIE from .malemotion import MalemotionIE from .matchtv import MatchTVIE @@ -392,6 +399,7 @@ from .metacritic import MetacriticIE from .mgoon import MgoonIE from .minhateca import MinhatecaIE from .ministrygrid import MinistryGridIE +from .minoto import MinotoIE from .miomio import MioMioIE from .mit import TechTVMITIE, MITIE, OCWMITIE from .mitele import MiTeleIE @@ -505,6 +513,7 @@ from .npr import NprIE from .nrk import ( NRKIE, NRKPlaylistIE, + NRKSkoleIE, NRKTVIE, ) from .ntvde import NTVDeIE @@ -669,7 +678,6 @@ from .southpark import ( SouthParkEsIE, SouthParkNlIE ) -from .space import SpaceIE from .spankbang import SpankBangIE from .spankwire import SpankwireIE from .spiegel import SpiegelIE, SpiegelArticleIE @@ -737,6 +745,7 @@ from .tmz import ( TMZArticleIE, ) from .tnaflix import ( + TNAFlixNetworkEmbedIE, TNAFlixIE, EMPFlixIE, MovieFapIE, @@ -798,7 +807,11 @@ from .twitch import ( TwitchBookmarksIE, TwitchStreamIE, ) -from .twitter import TwitterCardIE, TwitterIE +from .twitter import ( + TwitterCardIE, + TwitterIE, + TwitterAmplifyIE, +) from .ubu import UbuIE from .udemy import ( UdemyIE, @@ -809,6 +822,7 @@ from .digiteka import DigitekaIE from .unistra import UnistraIE from .urort import UrortIE from .ustream import UstreamIE, UstreamChannelIE +from .ustudio import UstudioIE from .varzesh3 import Varzesh3IE from .vbox7 import Vbox7IE from .veehd import VeeHDIE @@ -822,7 +836,10 @@ from .vgtv import ( VGTVIE, ) from .vh1 import VH1IE -from .vice import ViceIE +from .vice import ( + ViceIE, + ViceShowIE, +) from .viddler import ViddlerIE from .videodetective import VideoDetectiveIE from .videofyme import VideofyMeIE @@ -849,6 +866,7 @@ from .vimeo import ( VimeoChannelIE, VimeoGroupsIE, VimeoLikesIE, + VimeoOndemandIE, VimeoReviewIE, VimeoUserIE, VimeoWatchLaterIE, diff --git a/youtube_dl/extractor/aol.py b/youtube_dl/extractor/aol.py index b51eafc45..b761b2cc4 100644 --- a/youtube_dl/extractor/aol.py +++ b/youtube_dl/extractor/aol.py @@ -1,24 +1,11 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor class AolIE(InfoExtractor): IE_NAME = 'on.aol.com' - _VALID_URL = r'''(?x) - (?: - aol-video:| - http://on\.aol\.com/ - (?: - video/.*-| - playlist/(?P<playlist_display_id>[^/?#]+?)-(?P<playlist_id>[0-9]+)[?#].*_videoid= - ) - ) - (?P<id>[0-9]+) - (?:$|\?) - ''' + _VALID_URL = r'(?:aol-video:|http://on\.aol\.com/video/.*-)(?P<id>[0-9]+)(?:$|\?)' _TESTS = [{ 'url': 'http://on.aol.com/video/u-s--official-warns-of-largest-ever-irs-phone-scam-518167793?icid=OnHomepageC2Wide_MustSee_Img', @@ -29,42 +16,31 @@ class AolIE(InfoExtractor): 'title': 'U.S. Official Warns Of \'Largest Ever\' IRS Phone Scam', }, 'add_ie': ['FiveMin'], - }, { - 'url': 'http://on.aol.com/playlist/brace-yourself---todays-weirdest-news-152147?icid=OnHomepageC4_Omg_Img#_videoid=518184316', - 'info_dict': { - 'id': '152147', - 'title': 'Brace Yourself - Today\'s Weirdest News', - }, - 'playlist_mincount': 10, }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - playlist_id = mobj.group('playlist_id') - if not playlist_id or self._downloader.params.get('noplaylist'): - return self.url_result('5min:%s' % video_id) + video_id = self._match_id(url) + return self.url_result('5min:%s' % video_id) - self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id)) - webpage = self._download_webpage(url, playlist_id) - title = self._html_search_regex( - r'<h1 class="video-title[^"]*">(.+?)</h1>', webpage, 'title') - playlist_html = self._search_regex( - r"(?s)<ul\s+class='video-related[^']*'>(.*?)</ul>", webpage, - 'playlist HTML') - entries = [{ - '_type': 'url', - 'url': 'aol-video:%s' % m.group('id'), - 'ie_key': 'Aol', - } for m in re.finditer( - r"<a\s+href='.*videoid=(?P<id>[0-9]+)'\s+class='video-thumb'>", - playlist_html)] +class AolFeaturesIE(InfoExtractor): + IE_NAME = 'features.aol.com' + _VALID_URL = r'http://features\.aol\.com/video/(?P<id>[^/?#]+)' - return { - '_type': 'playlist', - 'id': playlist_id, - 'display_id': mobj.group('playlist_display_id'), - 'title': title, - 'entries': entries, - } + _TESTS = [{ + 'url': 'http://features.aol.com/video/behind-secret-second-careers-late-night-talk-show-hosts', + 'md5': '7db483bb0c09c85e241f84a34238cc75', + 'info_dict': { + 'id': '519507715', + 'ext': 'mp4', + 'title': 'What To Watch - February 17, 2016', + }, + 'add_ie': ['FiveMin'], + }] + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + return self.url_result(self._search_regex( + r'<script type="text/javascript" src="(https?://[^/]*?5min\.com/Scripts/PlayerSeed\.js[^"]+)"', + webpage, '5min embed url'), 'FiveMin') diff --git a/youtube_dl/extractor/appletrailers.py b/youtube_dl/extractor/appletrailers.py index 62ed0c918..be40f85b4 100644 --- a/youtube_dl/extractor/appletrailers.py +++ b/youtube_dl/extractor/appletrailers.py @@ -12,7 +12,7 @@ from ..utils import ( class AppleTrailersIE(InfoExtractor): IE_NAME = 'appletrailers' - _VALID_URL = r'https?://(?:www\.)?trailers\.apple\.com/(?:trailers|ca)/(?P<company>[^/]+)/(?P<movie>[^/]+)' + _VALID_URL = r'https?://(?:www\.|movie)?trailers\.apple\.com/(?:trailers|ca)/(?P<company>[^/]+)/(?P<movie>[^/]+)' _TESTS = [{ 'url': 'http://trailers.apple.com/trailers/wb/manofsteel/', 'info_dict': { @@ -73,6 +73,9 @@ class AppleTrailersIE(InfoExtractor): }, { 'url': 'http://trailers.apple.com/ca/metropole/autrui/', 'only_matching': True, + }, { + 'url': 'http://movietrailers.apple.com/trailers/focus_features/kuboandthetwostrings/', + 'only_matching': True, }] _JSON_RE = r'iTunes.playURL\((.*?)\);' diff --git a/youtube_dl/extractor/arte.py b/youtube_dl/extractor/arte.py index 793da2ee1..3e119e21b 100644 --- a/youtube_dl/extractor/arte.py +++ b/youtube_dl/extractor/arte.py @@ -63,7 +63,7 @@ class ArteTvIE(InfoExtractor): class ArteTVPlus7IE(InfoExtractor): IE_NAME = 'arte.tv:+7' - _VALID_URL = r'https?://(?:www\.)?arte\.tv/guide/(?P<lang>fr|de|en|es)/(?:(?:sendungen|emissions)/)?(?P<id>[^/]+)/(?P<name>[^/?#&+])' + _VALID_URL = r'https?://(?:www\.)?arte\.tv/guide/(?P<lang>fr|de|en|es)/(?:(?:sendungen|emissions|embed)/)?(?P<id>[^/]+)/(?P<name>[^/?#&+])' @classmethod def _extract_url_info(cls, url): @@ -110,17 +110,29 @@ class ArteTVPlus7IE(InfoExtractor): # en and es URLs produce react-based pages with different layout (e.g. # http://www.arte.tv/guide/en/053330-002-A/carnival-italy?zone=world) if not iframe_url: - embed_html = self._parse_json( - self._search_regex( - r'program\s*:\s*({.+?["\']embed_html["\'].+?}),?\s*\n', - webpage, 'program'), - video_id)['embed_html'] - iframe_url = find_iframe_url(embed_html) - json_url = compat_parse_qs( - compat_urllib_parse_urlparse(iframe_url).query)['json_url'][0] - return self._extract_from_json_url(json_url, video_id, lang) - - def _extract_from_json_url(self, json_url, video_id, lang): + program = self._search_regex( + r'program\s*:\s*({.+?["\']embed_html["\'].+?}),?\s*\n', + webpage, 'program', default=None) + if program: + embed_html = self._parse_json(program, video_id) + if embed_html: + iframe_url = find_iframe_url(embed_html['embed_html']) + if iframe_url: + json_url = compat_parse_qs( + compat_urllib_parse_urlparse(iframe_url).query)['json_url'][0] + if json_url: + title = self._search_regex( + r'<h3[^>]+title=(["\'])(?P<title>.+?)\1', + webpage, 'title', default=None, group='title') + return self._extract_from_json_url(json_url, video_id, lang, title=title) + # Different kind of embed URL (e.g. + # http://www.arte.tv/magazine/trepalium/fr/episode-0406-replay-trepalium) + embed_url = self._search_regex( + r'<iframe[^>]+src=(["\'])(?P<url>.+?)\1', + webpage, 'embed url', group='url') + return self.url_result(embed_url) + + def _extract_from_json_url(self, json_url, video_id, lang, title=None): info = self._download_json(json_url, video_id) player_info = info['videoJsonPlayer'] @@ -128,7 +140,7 @@ class ArteTVPlus7IE(InfoExtractor): if not upload_date_str: upload_date_str = (player_info.get('VRA') or player_info.get('VDA') or '').split(' ')[0] - title = player_info['VTI'].strip() + title = (player_info.get('VTI') or title or player_info['VID']).strip() subtitle = player_info.get('VSU', '').strip() if subtitle: title += ' - %s' % subtitle @@ -230,6 +242,7 @@ class ArteTVFutureIE(ArteTVPlus7IE): 'id': '050940-028-A', 'ext': 'mp4', 'title': 'Les écrevisses aussi peuvent être anxieuses', + 'upload_date': '20140902', }, }, { 'url': 'http://future.arte.tv/fr/la-science-est-elle-responsable', @@ -294,12 +307,25 @@ class ArteTVMagazineIE(ArteTVPlus7IE): _VALID_URL = r'https?://(?:www\.)?arte\.tv/magazine/[^/]+/(?P<lang>fr|de|en|es)/(?P<id>[^/?#&]+)' _TESTS = [{ + # Embedded via <iframe src="http://www.arte.tv/arte_vp/index.php?json_url=..." 'url': 'http://www.arte.tv/magazine/trepalium/fr/entretien-avec-le-realisateur-vincent-lannoo-trepalium', - 'md5': '66a093339c1278bb3719157ef07107b2', + 'md5': '2a9369bcccf847d1c741e51416299f25', 'info_dict': { 'id': '065965-000-A', 'ext': 'mp4', 'title': 'Trepalium - Extrait Ep.01', + 'upload_date': '20160121', + }, + }, { + # Embedded via <iframe src="http://www.arte.tv/guide/fr/embed/054813-004-A/medium" + 'url': 'http://www.arte.tv/magazine/trepalium/fr/episode-0406-replay-trepalium', + 'md5': 'fedc64fc7a946110fe311634e79782ca', + 'info_dict': { + 'id': '054813-004_PLUS7-F', + 'ext': 'mp4', + 'title': 'Trepalium (4/6)', + 'description': 'md5:10057003c34d54e95350be4f9b05cb40', + 'upload_date': '20160218', }, }, { 'url': 'http://www.arte.tv/magazine/metropolis/de/frank-woeste-german-paris-metropolis', diff --git a/youtube_dl/extractor/audimedia.py b/youtube_dl/extractor/audimedia.py index 3b2effa15..aa6925623 100644 --- a/youtube_dl/extractor/audimedia.py +++ b/youtube_dl/extractor/audimedia.py @@ -10,9 +10,9 @@ from ..utils import ( class AudiMediaIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?audimedia\.tv/(?:en|de)/vid/(?P<id>[^/?#]+)' + _VALID_URL = r'https?://(?:www\.)?audi-mediacenter\.com/(?:en|de)/audimediatv/(?P<id>[^/?#]+)' _TEST = { - 'url': 'https://audimedia.tv/en/vid/60-seconds-of-audi-sport-104-2015-wec-bahrain-rookie-test', + 'url': 'https://www.audi-mediacenter.com/en/audimediatv/60-seconds-of-audi-sport-104-2015-wec-bahrain-rookie-test-1467', 'md5': '79a8b71c46d49042609795ab59779b66', 'info_dict': { 'id': '1565', @@ -32,7 +32,10 @@ class AudiMediaIE(InfoExtractor): display_id = self._match_id(url) webpage = self._download_webpage(url, display_id) - raw_payload = self._search_regex(r'<script[^>]+class="amtv-embed"[^>]+id="([^"]+)"', webpage, 'raw payload') + raw_payload = self._search_regex([ + r'class="amtv-embed"[^>]+id="([^"]+)"', + r'class=\\"amtv-embed\\"[^>]+id=\\"([^"]+)\\"', + ], webpage, 'raw payload') _, stage_mode, video_id, lang = raw_payload.split('-') # TODO: handle s and e stage_mode (live streams and ended live streams) @@ -59,13 +62,19 @@ class AudiMediaIE(InfoExtractor): video_version_url = video_version.get('download_url') or video_version.get('stream_url') if not video_version_url: continue - formats.append({ + f = { 'url': video_version_url, 'width': int_or_none(video_version.get('width')), 'height': int_or_none(video_version.get('height')), 'abr': int_or_none(video_version.get('audio_bitrate')), 'vbr': int_or_none(video_version.get('video_bitrate')), - }) + } + bitrate = self._search_regex(r'(\d+)k', video_version_url, 'bitrate', default=None) + if bitrate: + f.update({ + 'format_id': 'http-%s' % bitrate, + }) + formats.append(f) self._sort_formats(formats) return { diff --git a/youtube_dl/extractor/audioboom.py b/youtube_dl/extractor/audioboom.py new file mode 100644 index 000000000..2ec2d7092 --- /dev/null +++ b/youtube_dl/extractor/audioboom.py @@ -0,0 +1,66 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import float_or_none + + +class AudioBoomIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?audioboom\.com/boos/(?P<id>[0-9]+)' + _TEST = { + 'url': 'https://audioboom.com/boos/4279833-3-09-2016-czaban-hour-3?t=0', + 'md5': '63a8d73a055c6ed0f1e51921a10a5a76', + 'info_dict': { + 'id': '4279833', + 'ext': 'mp3', + 'title': '3/09/2016 Czaban Hour 3', + 'description': 'Guest: Nate Davis - NFL free agency, Guest: Stan Gans', + 'duration': 2245.72, + 'uploader': 'Steve Czaban', + 'uploader_url': 're:https?://(?:www\.)?audioboom\.com/channel/steveczabanyahoosportsradio', + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + clip = None + + clip_store = self._parse_json( + self._search_regex( + r'data-new-clip-store=(["\'])(?P<json>{.*?"clipId"\s*:\s*%s.*?})\1' % video_id, + webpage, 'clip store', default='{}', group='json'), + video_id, fatal=False) + if clip_store: + clips = clip_store.get('clips') + if clips and isinstance(clips, list) and isinstance(clips[0], dict): + clip = clips[0] + + def from_clip(field): + if clip: + clip.get(field) + + audio_url = from_clip('clipURLPriorToLoading') or self._og_search_property( + 'audio', webpage, 'audio url') + title = from_clip('title') or self._og_search_title(webpage) + description = from_clip('description') or self._og_search_description(webpage) + + duration = float_or_none(from_clip('duration') or self._html_search_meta( + 'weibo:audio:duration', webpage)) + + uploader = from_clip('author') or self._og_search_property( + 'audio:artist', webpage, 'uploader', fatal=False) + uploader_url = from_clip('author_url') or self._html_search_meta( + 'audioboo:channel', webpage, 'uploader url') + + return { + 'id': video_id, + 'url': audio_url, + 'title': title, + 'description': description, + 'duration': duration, + 'uploader': uploader, + 'uploader_url': uploader_url, + } diff --git a/youtube_dl/extractor/bbc.py b/youtube_dl/extractor/bbc.py index 9d0dfb961..e62b3860e 100644 --- a/youtube_dl/extractor/bbc.py +++ b/youtube_dl/extractor/bbc.py @@ -10,7 +10,6 @@ from ..utils import ( int_or_none, parse_duration, parse_iso8601, - remove_end, unescapeHTML, ) from ..compat import ( @@ -561,7 +560,7 @@ class BBCIE(BBCCoUkIE): 'url': 'http://www.bbc.co.uk/blogs/adamcurtis/entries/3662a707-0af9-3149-963f-47bea720b460', 'info_dict': { 'id': '3662a707-0af9-3149-963f-47bea720b460', - 'title': 'BBC Blogs - Adam Curtis - BUGGER', + 'title': 'BUGGER', }, 'playlist_count': 18, }, { @@ -670,10 +669,18 @@ class BBCIE(BBCCoUkIE): 'url': 'http://www.bbc.com/sport/0/football/34475836', 'info_dict': { 'id': '34475836', - 'title': 'What Liverpool can expect from Klopp', + 'title': 'Jurgen Klopp: Furious football from a witty and winning coach', }, 'playlist_count': 3, }, { + # school report article with single video + 'url': 'http://www.bbc.co.uk/schoolreport/35744779', + 'info_dict': { + 'id': '35744779', + 'title': 'School which breaks down barriers in Jerusalem', + }, + 'playlist_count': 1, + }, { # single video with playlist URL from weather section 'url': 'http://www.bbc.com/weather/features/33601775', 'only_matching': True, @@ -735,8 +742,17 @@ class BBCIE(BBCCoUkIE): json_ld_info = self._search_json_ld(webpage, playlist_id, default=None) timestamp = json_ld_info.get('timestamp') + playlist_title = json_ld_info.get('title') - playlist_description = json_ld_info.get('description') + if not playlist_title: + playlist_title = self._og_search_title( + webpage, default=None) or self._html_search_regex( + r'<title>(.+?)</title>', webpage, 'playlist title', default=None) + if playlist_title: + playlist_title = re.sub(r'(.+)\s*-\s*BBC.*?$', r'\1', playlist_title).strip() + + playlist_description = json_ld_info.get( + 'description') or self._og_search_description(webpage, default=None) if not timestamp: timestamp = parse_iso8601(self._search_regex( @@ -797,8 +813,6 @@ class BBCIE(BBCCoUkIE): playlist.get('progressiveDownloadUrl'), playlist_id, timestamp)) if entries: - playlist_title = playlist_title or remove_end(self._og_search_title(webpage), ' - BBC News') - playlist_description = playlist_description or self._og_search_description(webpage, default=None) return self.playlist_result(entries, playlist_id, playlist_title, playlist_description) # single video story (e.g. http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret) @@ -829,10 +843,6 @@ class BBCIE(BBCCoUkIE): 'subtitles': subtitles, } - playlist_title = self._html_search_regex( - r'<title>(.*?)(?:\s*-\s*BBC [^ ]+)?</title>', webpage, 'playlist title') - playlist_description = self._og_search_description(webpage, default=None) - def extract_all(pattern): return list(filter(None, map( lambda s: self._parse_json(s, playlist_id, fatal=False), diff --git a/youtube_dl/extractor/bleacherreport.py b/youtube_dl/extractor/bleacherreport.py index 38bda3af5..7a8e1f60b 100644 --- a/youtube_dl/extractor/bleacherreport.py +++ b/youtube_dl/extractor/bleacherreport.py @@ -28,10 +28,10 @@ class BleacherReportIE(InfoExtractor): 'add_ie': ['Ooyala'], }, { 'url': 'http://bleacherreport.com/articles/2586817-aussie-golfers-get-fright-of-their-lives-after-being-chased-by-angry-kangaroo', - 'md5': 'af5f90dc9c7ba1c19d0a3eac806bbf50', + 'md5': '6a5cd403418c7b01719248ca97fb0692', 'info_dict': { 'id': '2586817', - 'ext': 'mp4', + 'ext': 'webm', 'title': 'Aussie Golfers Get Fright of Their Lives After Being Chased by Angry Kangaroo', 'timestamp': 1446839961, 'uploader': 'Sean Fay', @@ -93,10 +93,14 @@ class BleacherReportCMSIE(AMPIE): 'md5': '8c2c12e3af7805152675446c905d159b', 'info_dict': { 'id': '8fd44c2f-3dc5-4821-9118-2c825a98c0e1', - 'ext': 'flv', + 'ext': 'mp4', 'title': 'Cena vs. Rollins Would Expose the Heavyweight Division', 'description': 'md5:984afb4ade2f9c0db35f3267ed88b36e', }, + 'params': { + # m3u8 download + 'skip_download': True, + }, }] def _real_extract(self, url): diff --git a/youtube_dl/extractor/bokecc.py b/youtube_dl/extractor/bokecc.py new file mode 100644 index 000000000..122a1cbb6 --- /dev/null +++ b/youtube_dl/extractor/bokecc.py @@ -0,0 +1,60 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..compat import compat_parse_qs +from ..utils import ExtractorError + + +class BokeCCBaseIE(InfoExtractor): + def _extract_bokecc_formats(self, webpage, video_id, format_id=None): + player_params_str = self._html_search_regex( + r'<(?:script|embed)[^>]+src="http://p\.bokecc\.com/player\?([^"]+)', + webpage, 'player params') + + player_params = compat_parse_qs(player_params_str) + + info_xml = self._download_xml( + 'http://p.bokecc.com/servlet/playinfo?uid=%s&vid=%s&m=1' % ( + player_params['siteid'][0], player_params['vid'][0]), video_id) + + formats = [{ + 'format_id': format_id, + 'url': quality.find('./copy').attrib['playurl'], + 'preference': int(quality.attrib['value']), + } for quality in info_xml.findall('./video/quality')] + + self._sort_formats(formats) + + return formats + + +class BokeCCIE(BokeCCBaseIE): + _IE_DESC = 'CC视频' + _VALID_URL = r'http://union\.bokecc\.com/playvideo\.bo\?(?P<query>.*)' + + _TESTS = [{ + 'url': 'http://union.bokecc.com/playvideo.bo?vid=E44D40C15E65EA30&uid=CD0C5D3C8614B28B', + 'info_dict': { + 'id': 'CD0C5D3C8614B28B_E44D40C15E65EA30', + 'ext': 'flv', + 'title': 'BokeCC Video', + }, + }] + + def _real_extract(self, url): + qs = compat_parse_qs(re.match(self._VALID_URL, url).group('query')) + if not qs.get('vid') or not qs.get('uid'): + raise ExtractorError('Invalid URL', expected=True) + + video_id = '%s_%s' % (qs['uid'][0], qs['vid'][0]) + + webpage = self._download_webpage(url, video_id) + + return { + 'id': video_id, + 'title': 'BokeCC Video', # no title provided in the webpage + 'formats': self._extract_bokecc_formats(webpage, video_id), + } diff --git a/youtube_dl/extractor/c56.py b/youtube_dl/extractor/c56.py index cb96c3876..cac8fdcba 100644 --- a/youtube_dl/extractor/c56.py +++ b/youtube_dl/extractor/c56.py @@ -4,12 +4,13 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..utils import js_to_json class C56IE(InfoExtractor): _VALID_URL = r'https?://(?:(?:www|player)\.)?56\.com/(?:.+?/)?(?:v_|(?:play_album.+-))(?P<textid>.+?)\.(?:html|swf)' IE_NAME = '56.com' - _TEST = { + _TESTS = [{ 'url': 'http://www.56.com/u39/v_OTM0NDA3MTY.html', 'md5': 'e59995ac63d0457783ea05f93f12a866', 'info_dict': { @@ -18,12 +19,29 @@ class C56IE(InfoExtractor): 'title': '网事知多少 第32期：车怒', 'duration': 283.813, }, - } + }, { + 'url': 'http://www.56.com/u47/v_MTM5NjQ5ODc2.html', + 'md5': '', + 'info_dict': { + 'id': '82247482', + 'title': '爱的诅咒之杜鹃花开', + }, + 'playlist_count': 7, + 'add_ie': ['Sohu'], + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url, flags=re.VERBOSE) text_id = mobj.group('textid') + webpage = self._download_webpage(url, text_id) + sohu_video_info_str = self._search_regex( + r'var\s+sohuVideoInfo\s*=\s*({[^}]+});', webpage, 'Sohu video info', default=None) + if sohu_video_info_str: + sohu_video_info = self._parse_json( + sohu_video_info_str, text_id, transform_source=js_to_json) + return self.url_result(sohu_video_info['url'], 'Sohu') + page = self._download_json( 'http://vxml.56.com/json/%s/' % text_id, text_id, 'Downloading video info') diff --git a/youtube_dl/extractor/cinemassacre.py b/youtube_dl/extractor/cinemassacre.py index 6d9cd8abd..042c4f2f1 100644 --- a/youtube_dl/extractor/cinemassacre.py +++ b/youtube_dl/extractor/cinemassacre.py @@ -21,6 +21,10 @@ class CinemassacreIE(InfoExtractor): 'title': '“Angry Video Game Nerd: The Movie” – Trailer', 'description': 'md5:fb87405fcb42a331742a0dce2708560b', }, + 'params': { + # m3u8 download + 'skip_download': True, + }, }, { 'url': 'http://cinemassacre.com/2013/10/02/the-mummys-hand-1940', @@ -31,14 +35,18 @@ class CinemassacreIE(InfoExtractor): 'upload_date': '20131002', 'title': 'The Mummy’s Hand (1940)', }, + 'params': { + # m3u8 download + 'skip_download': True, + }, }, { # Youtube embedded video 'url': 'http://cinemassacre.com/2006/12/07/chronologically-confused-about-bad-movie-and-video-game-sequel-titles/', - 'md5': 'df4cf8a1dcedaec79a73d96d83b99023', + 'md5': 'ec9838a5520ef5409b3e4e42fcb0a3b9', 'info_dict': { 'id': 'OEVzPCY2T-g', - 'ext': 'mp4', + 'ext': 'webm', 'title': 'AVGN: Chronologically Confused about Bad Movie and Video Game Sequel Titles', 'upload_date': '20061207', 'uploader': 'Cinemassacre', @@ -49,12 +57,12 @@ class CinemassacreIE(InfoExtractor): { # Youtube embedded video 'url': 'http://cinemassacre.com/2006/09/01/mckids/', - 'md5': '6eb30961fa795fedc750eac4881ad2e1', + 'md5': '7393c4e0f54602ad110c793eb7a6513a', 'info_dict': { 'id': 'FnxsNhuikpo', - 'ext': 'mp4', + 'ext': 'webm', 'upload_date': '20060901', - 'uploader': 'Cinemassacre Extras', + 'uploader': 'Cinemassacre Extra', 'description': 'md5:de9b751efa9e45fbaafd9c8a1123ed53', 'uploader_id': 'Cinemassacre', 'title': 'AVGN: McKids', @@ -69,7 +77,11 @@ class CinemassacreIE(InfoExtractor): 'description': 'Let’s Play Mario Kart 64 !! Mario Kart 64 is a classic go-kart racing game released for the Nintendo 64 (N64). Today James & Mike do 4 player Battle Mode with Kyle and Bootsy!', 'title': 'Mario Kart 64 (Nintendo 64) James & Mike Mondays', 'upload_date': '20150525', - } + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, } ] diff --git a/youtube_dl/extractor/cnet.py b/youtube_dl/extractor/cnet.py index 5c3908f72..3cf0bf95b 100644 --- a/youtube_dl/extractor/cnet.py +++ b/youtube_dl/extractor/cnet.py @@ -51,9 +51,7 @@ class CNETIE(ThePlatformIE): uploader = None uploader_id = None - mpx_account = data['config']['uvpConfig']['default']['mpx_account'] - - metadata = self.get_metadata('%s/%s' % (mpx_account, list(vdata['files'].values())[0]), video_id) + metadata = self.get_metadata('kYEXFC/%s' % list(vdata['files'].values())[0], video_id) description = vdata.get('description') or metadata.get('description') duration = int_or_none(vdata.get('duration')) or metadata.get('duration') @@ -62,7 +60,7 @@ class CNETIE(ThePlatformIE): for (fkey, vid) in vdata['files'].items(): if fkey == 'hls_phone' and 'hls_tablet' in vdata['files']: continue - release_url = 'http://link.theplatform.com/s/%s/%s?format=SMIL&mbr=true' % (mpx_account, vid) + release_url = 'http://link.theplatform.com/s/kYEXFC/%s?format=SMIL&mbr=true' % vid if fkey == 'hds': release_url += '&manifest=f4m' tp_formats, tp_subtitles = self._extract_theplatform_smil(release_url, video_id, 'Downloading %s SMIL data' % fkey) diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index f411ea763..ecd7da767 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -15,13 +15,14 @@ import math from ..compat import ( compat_cookiejar, compat_cookies, + compat_etree_fromstring, compat_getpass, compat_http_client, + compat_os_name, + compat_str, compat_urllib_error, compat_urllib_parse, compat_urlparse, - compat_str, - compat_etree_fromstring, ) from ..utils import ( NO_DEFAULT, @@ -46,6 +47,8 @@ from ..utils import ( xpath_with_ns, determine_protocol, parse_duration, + mimetype2ext, + update_url_query, ) @@ -103,7 +106,7 @@ class InfoExtractor(object): * protocol The protocol that will be used for the actual download, lower-case. "http", "https", "rtsp", "rtmp", "rtmpe", - "m3u8", or "m3u8_native". + "m3u8", "m3u8_native" or "http_dash_segments". * preference Order number of this format. If this field is present and not None, the formats get sorted by this field, regardless of all other values. @@ -156,12 +159,14 @@ class InfoExtractor(object): thumbnail: Full URL to a video thumbnail image. description: Full video description. uploader: Full name of the video uploader. + license: License name the video is licensed under. creator: The main artist who created the video. release_date: The date (YYYYMMDD) when the video was released. timestamp: UNIX timestamp of the moment the video became available. upload_date: Video upload date (YYYYMMDD). If not explicitly set, calculated from timestamp. uploader_id: Nickname or id of the video uploader. + uploader_url: Full URL to a personal webpage of the video uploader. location: Physical location where the video was filmed. subtitles: The available subtitles as a dictionary in the format {language: subformats}. "subformats" is a list sorted from @@ -341,7 +346,7 @@ class InfoExtractor(object): def IE_NAME(self): return compat_str(type(self).__name__[:-2]) - def _request_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True): + def _request_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, data=None, headers=None, query=None): """ Returns the response handle """ if note is None: self.report_download_webpage(video_id) @@ -350,6 +355,12 @@ class InfoExtractor(object): self.to_screen('%s' % (note,)) else: self.to_screen('%s: %s' % (video_id, note)) + # data, headers and query params will be ignored for `Request` objects + if isinstance(url_or_request, compat_str): + if query: + url_or_request = update_url_query(url_or_request, query) + if data or headers: + url_or_request = sanitized_Request(url_or_request, data, headers or {}) try: return self._downloader.urlopen(url_or_request) except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: @@ -365,13 +376,13 @@ class InfoExtractor(object): self._downloader.report_warning(errmsg) return False - def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None, fatal=True, encoding=None): + def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None, fatal=True, encoding=None, data=None, headers=None, query=None): """ Returns a tuple (page content as string, URL handle) """ # Strip hashes from the URL (#1038) if isinstance(url_or_request, (compat_str, str)): url_or_request = url_or_request.partition('#')[0] - urlh = self._request_webpage(url_or_request, video_id, note, errnote, fatal) + urlh = self._request_webpage(url_or_request, video_id, note, errnote, fatal, data=data, headers=headers, query=query) if urlh is False: assert not fatal return False @@ -424,7 +435,7 @@ class InfoExtractor(object): self.to_screen('Saving request to ' + filename) # Working around MAX_PATH limitation on Windows (see # http://msdn.microsoft.com/en-us/library/windows/desktop/aa365247(v=vs.85).aspx) - if os.name == 'nt': + if compat_os_name == 'nt': absfilepath = os.path.abspath(filename) if len(absfilepath) > 259: filename = '\\\\?\\' + absfilepath @@ -458,13 +469,13 @@ class InfoExtractor(object): return content - def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, tries=1, timeout=5, encoding=None): + def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, tries=1, timeout=5, encoding=None, data=None, headers=None, query=None): """ Returns the data of the page as a string """ success = False try_count = 0 while success is False: try: - res = self._download_webpage_handle(url_or_request, video_id, note, errnote, fatal, encoding=encoding) + res = self._download_webpage_handle(url_or_request, video_id, note, errnote, fatal, encoding=encoding, data=data, headers=headers, query=query) success = True except compat_http_client.IncompleteRead as e: try_count += 1 @@ -479,10 +490,10 @@ class InfoExtractor(object): def _download_xml(self, url_or_request, video_id, note='Downloading XML', errnote='Unable to download XML', - transform_source=None, fatal=True, encoding=None): + transform_source=None, fatal=True, encoding=None, data=None, headers=None, query=None): """Return the xml as an xml.etree.ElementTree.Element""" xml_string = self._download_webpage( - url_or_request, video_id, note, errnote, fatal=fatal, encoding=encoding) + url_or_request, video_id, note, errnote, fatal=fatal, encoding=encoding, data=data, headers=headers, query=query) if xml_string is False: return xml_string if transform_source: @@ -493,10 +504,10 @@ class InfoExtractor(object): note='Downloading JSON metadata', errnote='Unable to download JSON metadata', transform_source=None, - fatal=True, encoding=None): + fatal=True, encoding=None, data=None, headers=None, query=None): json_string = self._download_webpage( url_or_request, video_id, note, errnote, fatal=fatal, - encoding=encoding) + encoding=encoding, data=data, headers=headers, query=query) if (not fatal) and json_string is False: return None return self._parse_json( @@ -593,7 +604,7 @@ class InfoExtractor(object): if mobj: break - if not self._downloader.params.get('no_color') and os.name != 'nt' and sys.stderr.isatty(): + if not self._downloader.params.get('no_color') and compat_os_name != 'nt' and sys.stderr.isatty(): _name = '\033[0;34m%s\033[0m' % name else: _name = name @@ -899,6 +910,16 @@ class InfoExtractor(object): item='%s video format' % f.get('format_id') if f.get('format_id') else 'video'), formats) + @staticmethod + def _remove_duplicate_formats(formats): + format_urls = set() + unique_formats = [] + for f in formats: + if f['url'] not in format_urls: + format_urls.add(f['url']) + unique_formats.append(f) + formats[:] = unique_formats + def _is_valid_url(self, url, video_id, item='video'): url = self._proto_relative_url(url, scheme='http:') # For now assume non HTTP(S) URLs always valid @@ -952,6 +973,13 @@ class InfoExtractor(object): if manifest is False: return [] + return self._parse_f4m_formats( + manifest, manifest_url, video_id, preference=preference, f4m_id=f4m_id, + transform_source=transform_source, fatal=fatal) + + def _parse_f4m_formats(self, manifest, manifest_url, video_id, preference=None, f4m_id=None, + transform_source=lambda s: fix_xml_ampersands(s).strip(), + fatal=True): formats = [] manifest_version = '1.0' media_nodes = manifest.findall('{http://ns.adobe.com/f4m/1.0}media') @@ -977,7 +1005,8 @@ class InfoExtractor(object): # bitrate in f4m downloader if determine_ext(manifest_url) == 'f4m': formats.extend(self._extract_f4m_formats( - manifest_url, video_id, preference, f4m_id, fatal=fatal)) + manifest_url, video_id, preference=preference, f4m_id=f4m_id, + transform_source=transform_source, fatal=fatal)) continue tbr = int_or_none(media_el.attrib.get('bitrate')) formats.append({ @@ -1022,11 +1051,21 @@ class InfoExtractor(object): return [] m3u8_doc, urlh = res m3u8_url = urlh.geturl() - # A Media Playlist Tag MUST NOT appear in a Master Playlist - # https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.3 - # The EXT-X-TARGETDURATION tag is REQUIRED for every M3U8 Media Playlists - # https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.3.1 - if '#EXT-X-TARGETDURATION' in m3u8_doc: + + # We should try extracting formats only from master playlists [1], i.e. + # playlists that describe available qualities. On the other hand media + # playlists [2] should be returned as is since they contain just the media + # without qualities renditions. + # Fortunately, master playlist can be easily distinguished from media + # playlist based on particular tags availability. As of [1, 2] master + # playlist tags MUST NOT appear in a media playist and vice versa. + # As of [3] #EXT-X-TARGETDURATION tag is REQUIRED for every media playlist + # and MUST NOT appear in master playlist thus we can clearly detect media + # playlist with this criterion. + # 1. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.4 + # 2. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.3 + # 3. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.3.1 + if '#EXT-X-TARGETDURATION' in m3u8_doc: # media playlist, return as is return [{ 'url': m3u8_url, 'format_id': m3u8_id, @@ -1073,19 +1112,29 @@ class InfoExtractor(object): 'protocol': entry_protocol, 'preference': preference, } - codecs = last_info.get('CODECS') - if codecs: - # TODO: looks like video codec is not always necessarily goes first - va_codecs = codecs.split(',') - if va_codecs[0]: - f['vcodec'] = va_codecs[0] - if len(va_codecs) > 1 and va_codecs[1]: - f['acodec'] = va_codecs[1] resolution = last_info.get('RESOLUTION') if resolution: width_str, height_str = resolution.split('x') f['width'] = int(width_str) f['height'] = int(height_str) + codecs = last_info.get('CODECS') + if codecs: + vcodec, acodec = [None] * 2 + va_codecs = codecs.split(',') + if len(va_codecs) == 1: + # Audio only entries usually come with single codec and + # no resolution. For more robustness we also check it to + # be mp4 audio. + if not resolution and va_codecs[0].startswith('mp4a'): + vcodec, acodec = 'none', va_codecs[0] + else: + vcodec = va_codecs[0] + else: + vcodec, acodec = va_codecs[:2] + f.update({ + 'acodec': acodec, + 'vcodec': vcodec, + }) if last_media is not None: f['m3u8_media'] = last_media last_media = None @@ -1106,8 +1155,8 @@ class InfoExtractor(object): out.append('{%s}%s' % (namespace, c)) return '/'.join(out) - def _extract_smil_formats(self, smil_url, video_id, fatal=True, f4m_params=None): - smil = self._download_smil(smil_url, video_id, fatal=fatal) + def _extract_smil_formats(self, smil_url, video_id, fatal=True, f4m_params=None, transform_source=None): + smil = self._download_smil(smil_url, video_id, fatal=fatal, transform_source=transform_source) if smil is False: assert not fatal @@ -1124,10 +1173,10 @@ class InfoExtractor(object): return {} return self._parse_smil(smil, smil_url, video_id, f4m_params=f4m_params) - def _download_smil(self, smil_url, video_id, fatal=True): + def _download_smil(self, smil_url, video_id, fatal=True, transform_source=None): return self._download_xml( smil_url, video_id, 'Downloading SMIL file', - 'Unable to download SMIL file', fatal=fatal) + 'Unable to download SMIL file', fatal=fatal, transform_source=transform_source) def _parse_smil(self, smil, smil_url, video_id, f4m_params=None): namespace = self._parse_smil_namespace(smil) @@ -1277,16 +1326,7 @@ class InfoExtractor(object): if not src or src in urls: continue urls.append(src) - ext = textstream.get('ext') or determine_ext(src) - if not ext: - type_ = textstream.get('type') - SUBTITLES_TYPES = { - 'text/vtt': 'vtt', - 'text/srt': 'srt', - 'application/smptett+xml': 'tt', - } - if type_ in SUBTITLES_TYPES: - ext = SUBTITLES_TYPES[type_] + ext = textstream.get('ext') or determine_ext(src) or mimetype2ext(textstream.get('type')) lang = textstream.get('systemLanguage') or textstream.get('systemLanguageName') or textstream.get('lang') or subtitles_lang subtitles.setdefault(lang, []).append({ 'url': src, @@ -1422,8 +1462,9 @@ class InfoExtractor(object): continue representation_attrib = adaptation_set.attrib.copy() representation_attrib.update(representation.attrib) - mime_type = representation_attrib.get('mimeType') - content_type = mime_type.split('/')[0] if mime_type else representation_attrib.get('contentType') + # According to page 41 of ISO/IEC 29001-1:2014, @mimeType is mandatory + mime_type = representation_attrib['mimeType'] + content_type = mime_type.split('/')[0] if content_type == 'text': # TODO implement WebVTT downloading pass @@ -1446,6 +1487,7 @@ class InfoExtractor(object): f = { 'format_id': '%s-%s' % (mpd_id, representation_id) if mpd_id else representation_id, 'url': base_url, + 'ext': mimetype2ext(mime_type), 'width': int_or_none(representation_attrib.get('width')), 'height': int_or_none(representation_attrib.get('height')), 'tbr': int_or_none(representation_attrib.get('bandwidth'), 1000), @@ -1598,6 +1640,15 @@ class InfoExtractor(object): def _get_automatic_captions(self, *args, **kwargs): raise NotImplementedError('This method must be implemented by subclasses') + def mark_watched(self, *args, **kwargs): + if (self._downloader.params.get('mark_watched', False) and + (self._get_login_info()[0] is not None or + self._downloader.params.get('cookiefile') is not None)): + self._mark_watched(*args, **kwargs) + + def _mark_watched(self, *args, **kwargs): + raise NotImplementedError('This method must be implemented by subclasses') + class SearchInfoExtractor(InfoExtractor): """ diff --git a/youtube_dl/extractor/douyutv.py b/youtube_dl/extractor/douyutv.py index 373b3b4b4..bdc768c78 100644 --- a/youtube_dl/extractor/douyutv.py +++ b/youtube_dl/extractor/douyutv.py @@ -18,7 +18,7 @@ class DouyuTVIE(InfoExtractor): 'display_id': 'iseven', 'ext': 'flv', 'title': 're:^清晨醒脑！T-ara根本停不下来！ [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', - 'description': 'md5:c93d6692dde6fe33809a46edcbecca44', + 'description': 'md5:f34981259a03e980a3c6404190a3ed61', 'thumbnail': 're:^https?://.*\.jpg$', 'uploader': '7师傅', 'uploader_id': '431925', @@ -26,7 +26,7 @@ class DouyuTVIE(InfoExtractor): }, 'params': { 'skip_download': True, - } + }, }, { 'url': 'http://www.douyutv.com/85982', 'info_dict': { @@ -42,7 +42,24 @@ class DouyuTVIE(InfoExtractor): }, 'params': { 'skip_download': True, - } + }, + 'skip': 'Romm not found', + }, { + 'url': 'http://www.douyutv.com/17732', + 'info_dict': { + 'id': '17732', + 'display_id': '17732', + 'ext': 'flv', + 'title': 're:^清晨醒脑！T-ara根本停不下来！ [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', + 'description': 'md5:f34981259a03e980a3c6404190a3ed61', + 'thumbnail': 're:^https?://.*\.jpg$', + 'uploader': '7师傅', + 'uploader_id': '431925', + 'is_live': True, + }, + 'params': { + 'skip_download': True, + }, }] def _real_extract(self, url): diff --git a/youtube_dl/extractor/dplay.py b/youtube_dl/extractor/dplay.py index 6cda56a7f..a638c827c 100644 --- a/youtube_dl/extractor/dplay.py +++ b/youtube_dl/extractor/dplay.py @@ -1,6 +1,8 @@ -# encoding: utf-8 +# coding: utf-8 from __future__ import unicode_literals +import json +import re import time from .common import InfoExtractor @@ -8,44 +10,125 @@ from ..utils import int_or_none class DPlayIE(InfoExtractor): - _VALID_URL = r'http://www\.dplay\.se/[^/]+/(?P<id>[^/?#]+)' + _VALID_URL = r'http://(?P<domain>it\.dplay\.com|www\.dplay\.(?:dk|se|no))/[^/]+/(?P<id>[^/?#]+)' - _TEST = { + _TESTS = [{ + 'url': 'http://it.dplay.com/take-me-out/stagione-1-episodio-25/', + 'info_dict': { + 'id': '1255600', + 'display_id': 'stagione-1-episodio-25', + 'ext': 'mp4', + 'title': 'Episodio 25', + 'description': 'md5:cae5f40ad988811b197d2d27a53227eb', + 'duration': 2761, + 'timestamp': 1454701800, + 'upload_date': '20160205', + 'creator': 'RTIT', + 'series': 'Take me out', + 'season_number': 1, + 'episode_number': 25, + 'age_limit': 0, + }, + 'expected_warnings': ['Unable to download f4m manifest'], + }, { 'url': 'http://www.dplay.se/nugammalt-77-handelser-som-format-sverige/season-1-svensken-lar-sig-njuta-av-livet/', 'info_dict': { 'id': '3172', - 'ext': 'mp4', 'display_id': 'season-1-svensken-lar-sig-njuta-av-livet', + 'ext': 'flv', 'title': 'Svensken lär sig njuta av livet', + 'description': 'md5:d3819c9bccffd0fe458ca42451dd50d8', 'duration': 2650, + 'timestamp': 1365454320, + 'upload_date': '20130408', + 'creator': 'Kanal 5 (Home)', + 'series': 'Nugammalt - 77 händelser som format Sverige', + 'season_number': 1, + 'episode_number': 1, + 'age_limit': 0, }, - } + }, { + 'url': 'http://www.dplay.dk/mig-og-min-mor/season-6-episode-12/', + 'info_dict': { + 'id': '70816', + 'display_id': 'season-6-episode-12', + 'ext': 'flv', + 'title': 'Episode 12', + 'description': 'md5:9c86e51a93f8a4401fc9641ef9894c90', + 'duration': 2563, + 'timestamp': 1429696800, + 'upload_date': '20150422', + 'creator': 'Kanal 4', + 'series': 'Mig og min mor', + 'season_number': 6, + 'episode_number': 12, + 'age_limit': 0, + }, + }, { + 'url': 'http://www.dplay.no/pga-tour/season-1-hoydepunkter-18-21-februar/', + 'only_matching': True, + }] def _real_extract(self, url): - display_id = self._match_id(url) + mobj = re.match(self._VALID_URL, url) + display_id = mobj.group('id') + domain = mobj.group('domain') + webpage = self._download_webpage(url, display_id) + video_id = self._search_regex( - r'data-video-id="(\d+)"', webpage, 'video id') + r'data-video-id=["\'](\d+)', webpage, 'video id') info = self._download_json( - 'http://www.dplay.se/api/v2/ajax/videos?video_id=' + video_id, + 'http://%s/api/v2/ajax/videos?video_id=%s' % (domain, video_id), video_id)['data'][0] - self._set_cookie( - 'secure.dplay.se', 'dsc-geo', - '{"countryCode":"NL","expiry":%d}' % ((time.time() + 20 * 60) * 1000)) - # TODO: consider adding support for 'stream_type=hds', it seems to - # require setting some cookies - manifest_url = self._download_json( - 'https://secure.dplay.se/secure/api/v2/user/authorization/stream/%s?stream_type=hls' % video_id, - video_id, 'Getting manifest url for hls stream')['hls'] - formats = self._extract_m3u8_formats( - manifest_url, video_id, ext='mp4', entry_protocol='m3u8_native') + title = info['title'] + + PROTOCOLS = ('hls', 'hds') + formats = [] + + def extract_formats(protocol, manifest_url): + if protocol == 'hls': + formats.extend(self._extract_m3u8_formats( + manifest_url, video_id, ext='mp4', + entry_protocol='m3u8_native', m3u8_id=protocol, fatal=False)) + elif protocol == 'hds': + formats.extend(self._extract_f4m_formats( + manifest_url + '&hdcore=3.8.0&plugin=flowplayer-3.8.0.0', + video_id, f4m_id=protocol, fatal=False)) + + domain_tld = domain.split('.')[-1] + if domain_tld in ('se', 'dk'): + for protocol in PROTOCOLS: + self._set_cookie( + 'secure.dplay.%s' % domain_tld, 'dsc-geo', + json.dumps({ + 'countryCode': domain_tld.upper(), + 'expiry': (time.time() + 20 * 60) * 1000, + })) + stream = self._download_json( + 'https://secure.dplay.%s/secure/api/v2/user/authorization/stream/%s?stream_type=%s' + % (domain_tld, video_id, protocol), video_id, + 'Downloading %s stream JSON' % protocol, fatal=False) + if stream and stream.get(protocol): + extract_formats(protocol, stream[protocol]) + else: + for protocol in PROTOCOLS: + if info.get(protocol): + extract_formats(protocol, info[protocol]) return { 'id': video_id, 'display_id': display_id, - 'title': info['title'], - 'formats': formats, + 'title': title, + 'description': info.get('video_metadata_longDescription'), 'duration': int_or_none(info.get('video_metadata_length'), scale=1000), + 'timestamp': int_or_none(info.get('video_publish_date')), + 'creator': info.get('video_metadata_homeChannel'), + 'series': info.get('video_metadata_show'), + 'season_number': int_or_none(info.get('season')), + 'episode_number': int_or_none(info.get('episode')), + 'age_limit': int_or_none(info.get('minimum_age')), + 'formats': formats, } diff --git a/youtube_dl/extractor/dw.py b/youtube_dl/extractor/dw.py new file mode 100644 index 000000000..b6c985547 --- /dev/null +++ b/youtube_dl/extractor/dw.py @@ -0,0 +1,85 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import int_or_none +from ..compat import compat_urlparse + + +class DWIE(InfoExtractor): + IE_NAME = 'dw' + _VALID_URL = r'https?://(?:www\.)?dw\.com/(?:[^/]+/)+av-(?P<id>\d+)' + _TESTS = [{ + # video + 'url': 'http://www.dw.com/en/intelligent-light/av-19112290', + 'md5': '7372046e1815c5a534b43f3c3c36e6e9', + 'info_dict': { + 'id': '19112290', + 'ext': 'mp4', + 'title': 'Intelligent light', + 'description': 'md5:90e00d5881719f2a6a5827cb74985af1', + 'upload_date': '20160311', + } + }, { + # audio + 'url': 'http://www.dw.com/en/worldlink-my-business/av-19111941', + 'md5': '2814c9a1321c3a51f8a7aeb067a360dd', + 'info_dict': { + 'id': '19111941', + 'ext': 'mp3', + 'title': 'WorldLink: My business', + 'description': 'md5:bc9ca6e4e063361e21c920c53af12405', + 'upload_date': '20160311', + } + }] + + def _real_extract(self, url): + media_id = self._match_id(url) + webpage = self._download_webpage(url, media_id) + hidden_inputs = self._hidden_inputs(webpage) + title = hidden_inputs['media_title'] + + formats = [] + if hidden_inputs.get('player_type') == 'video' and hidden_inputs.get('stream_file') == '1': + formats = self._extract_smil_formats( + 'http://www.dw.com/smil/v-%s' % media_id, media_id, + transform_source=lambda s: s.replace( + 'rtmp://tv-od.dw.de/flash/', + 'http://tv-download.dw.de/dwtv_video/flv/')) + else: + formats = [{'url': hidden_inputs['file_name']}] + + return { + 'id': media_id, + 'title': title, + 'description': self._og_search_description(webpage), + 'thumbnail': hidden_inputs.get('preview_image'), + 'duration': int_or_none(hidden_inputs.get('file_duration')), + 'upload_date': hidden_inputs.get('display_date'), + 'formats': formats, + } + + +class DWArticleIE(InfoExtractor): + IE_NAME = 'dw:article' + _VALID_URL = r'https?://(?:www\.)?dw\.com/(?:[^/]+/)+a-(?P<id>\d+)' + _TEST = { + 'url': 'http://www.dw.com/en/no-hope-limited-options-for-refugees-in-idomeni/a-19111009', + 'md5': '8ca657f9d068bbef74d6fc38b97fc869', + 'info_dict': { + 'id': '19105868', + 'ext': 'mp4', + 'title': 'The harsh life of refugees in Idomeni', + 'description': 'md5:196015cc7e48ebf474db9399420043c7', + 'upload_date': '20160310', + } + } + + def _real_extract(self, url): + article_id = self._match_id(url) + webpage = self._download_webpage(url, article_id) + hidden_inputs = self._hidden_inputs(webpage) + media_id = hidden_inputs['media_id'] + media_path = self._search_regex(r'href="([^"]+av-%s)"\s+class="overlayLink"' % media_id, webpage, 'media url') + media_url = compat_urlparse.urljoin(url, media_path) + return self.url_result(media_url, 'DW', media_id) diff --git a/youtube_dl/extractor/elpais.py b/youtube_dl/extractor/elpais.py index 00a69e631..8c725a4e6 100644 --- a/youtube_dl/extractor/elpais.py +++ b/youtube_dl/extractor/elpais.py @@ -9,7 +9,7 @@ class ElPaisIE(InfoExtractor): _VALID_URL = r'https?://(?:[^.]+\.)?elpais\.com/.*/(?P<id>[^/#?]+)\.html(?:$|[?#])' IE_DESC = 'El País' - _TEST = { + _TESTS = [{ 'url': 'http://blogs.elpais.com/la-voz-de-inaki/2014/02/tiempo-nuevo-recetas-viejas.html', 'md5': '98406f301f19562170ec071b83433d55', 'info_dict': { @@ -19,30 +19,41 @@ class ElPaisIE(InfoExtractor): 'description': 'De lunes a viernes, a partir de las ocho de la mañana, Iñaki Gabilondo nos cuenta su visión de la actualidad nacional e internacional.', 'upload_date': '20140206', } - } + }, { + 'url': 'http://elcomidista.elpais.com/elcomidista/2016/02/24/articulo/1456340311_668921.html#?id_externo_nwl=newsletter_diaria20160303t', + 'md5': '3bd5b09509f3519d7d9e763179b013de', + 'info_dict': { + 'id': '1456340311_668921', + 'ext': 'mp4', + 'title': 'Cómo hacer el mejor café con cafetera italiana', + 'description': 'Que sí, que las cápsulas son cómodas. Pero si le pides algo más a la vida, quizá deberías aprender a usar bien la cafetera italiana. No tienes más que ver este vídeo y seguir sus siete normas básicas.', + 'upload_date': '20160303', + } + }] def _real_extract(self, url): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) prefix = self._html_search_regex( - r'var url_cache = "([^"]+)";', webpage, 'URL prefix') + r'var\s+url_cache\s*=\s*"([^"]+)";', webpage, 'URL prefix') video_suffix = self._search_regex( - r"URLMediaFile = url_cache \+ '([^']+)'", webpage, 'video URL') + r"(?:URLMediaFile|urlVideo_\d+)\s*=\s*url_cache\s*\+\s*'([^']+)'", webpage, 'video URL') video_url = prefix + video_suffix thumbnail_suffix = self._search_regex( - r"URLMediaStill = url_cache \+ '([^']+)'", webpage, 'thumbnail URL', - fatal=False) + r"(?:URLMediaStill|urlFotogramaFijo_\d+)\s*=\s*url_cache\s*\+\s*'([^']+)'", + webpage, 'thumbnail URL', fatal=False) thumbnail = ( None if thumbnail_suffix is None else prefix + thumbnail_suffix) title = self._html_search_regex( - '<h2 class="entry-header entry-title.*?>(.*?)</h2>', + (r"tituloVideo\s*=\s*'([^']+)'", webpage, 'title', + r'<h2 class="entry-header entry-title.*?>(.*?)</h2>'), webpage, 'title') - date_str = self._search_regex( + upload_date = unified_strdate(self._search_regex( r'<p class="date-header date-int updated"\s+title="([^"]+)">', - webpage, 'upload date', fatal=False) - upload_date = (None if date_str is None else unified_strdate(date_str)) + webpage, 'upload date', default=None) or self._html_search_meta( + 'datePublished', webpage, 'timestamp')) return { 'id': video_id, diff --git a/youtube_dl/extractor/engadget.py b/youtube_dl/extractor/engadget.py index e4180701d..e5e57d485 100644 --- a/youtube_dl/extractor/engadget.py +++ b/youtube_dl/extractor/engadget.py @@ -1,21 +1,13 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor -from ..utils import ( - url_basename, -) class EngadgetIE(InfoExtractor): - _VALID_URL = r'''(?x)https?://www.engadget.com/ - (?:video(?:/5min)?/(?P<id>\d+)| - [\d/]+/.*?) - ''' + _VALID_URL = r'https?://www.engadget.com/video/(?P<id>\d+)' _TEST = { - 'url': 'http://www.engadget.com/video/5min/518153925/', + 'url': 'http://www.engadget.com/video/518153925/', 'md5': 'c6820d4828a5064447a4d9fc73f312c9', 'info_dict': { 'id': '518153925', @@ -27,15 +19,4 @@ class EngadgetIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - - if video_id is not None: - return self.url_result('5min:%s' % video_id) - else: - title = url_basename(url) - webpage = self._download_webpage(url, title) - ids = re.findall(r'<iframe[^>]+?playList=(\d+)', webpage) - return { - '_type': 'playlist', - 'title': title, - 'entries': [self.url_result('5min:%s' % vid) for vid in ids] - } + return self.url_result('5min:%s' % video_id) diff --git a/youtube_dl/extractor/facebook.py b/youtube_dl/extractor/facebook.py index 0a9a5ca71..f5bbd39d2 100644 --- a/youtube_dl/extractor/facebook.py +++ b/youtube_dl/extractor/facebook.py @@ -34,9 +34,12 @@ class FacebookIE(InfoExtractor): video/video\.php| photo\.php| video\.php| - video/embed - )\?(?:.*?)(?:v|video_id)=| - [^/]+/videos/(?:[^/]+/)? + video/embed| + story\.php + )\?(?:.*?)(?:v|video_id|story_fbid)=| + [^/]+/videos/(?:[^/]+/)?| + [^/]+/posts/| + groups/[^/]+/permalink/ )| facebook: ) @@ -49,6 +52,8 @@ class FacebookIE(InfoExtractor): _CHROME_USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/48.0.2564.97 Safari/537.36' + _VIDEO_PAGE_TEMPLATE = 'https://www.facebook.com/video/video.php?v=%s' + _TESTS = [{ 'url': 'https://www.facebook.com/video.php?v=637842556329505&fref=nf', 'md5': '6a40d33c0eccbb1af76cf0485a052659', @@ -81,6 +86,33 @@ class FacebookIE(InfoExtractor): 'uploader': 'Demy de Zeeuw', }, }, { + 'url': 'https://www.facebook.com/maxlayn/posts/10153807558977570', + 'md5': '037b1fa7f3c2d02b7a0d7bc16031ecc6', + 'info_dict': { + 'id': '544765982287235', + 'ext': 'mp4', + 'title': '"What are you doing running in the snow?"', + 'uploader': 'FailArmy', + } + }, { + 'url': 'https://m.facebook.com/story.php?story_fbid=1035862816472149&id=116132035111903', + 'md5': '1deb90b6ac27f7efcf6d747c8a27f5e3', + 'info_dict': { + 'id': '1035862816472149', + 'ext': 'mp4', + 'title': 'What the Flock Is Going On In New Zealand Credit: ViralHog', + 'uploader': 'S. Saint', + }, + }, { + 'note': 'swf params escaped', + 'url': 'https://www.facebook.com/barackobama/posts/10153664894881749', + 'md5': '97ba073838964d12c70566e0085c2b91', + 'info_dict': { + 'id': '10153664894881749', + 'ext': 'mp4', + 'title': 'Facebook video #10153664894881749', + }, + }, { 'url': 'https://www.facebook.com/video.php?v=10204634152394104', 'only_matching': True, }, { @@ -92,6 +124,9 @@ class FacebookIE(InfoExtractor): }, { 'url': 'facebook:544765982287235', 'only_matching': True, + }, { + 'url': 'https://www.facebook.com/groups/164828000315060/permalink/764967300301124/', + 'only_matching': True, }] def _login(self): @@ -160,19 +195,19 @@ class FacebookIE(InfoExtractor): def _real_initialize(self): self._login() - def _real_extract(self, url): - video_id = self._match_id(url) - req = sanitized_Request('https://www.facebook.com/video/video.php?v=%s' % video_id) + def _extract_from_url(self, url, video_id, fatal_if_no_video=True): + req = sanitized_Request(url) req.add_header('User-Agent', self._CHROME_USER_AGENT) webpage = self._download_webpage(req, video_id) video_data = None - BEFORE = '{swf.addParam(param[0], param[1]);});\n' + BEFORE = '{swf.addParam(param[0], param[1]);});' AFTER = '.forEach(function(variable) {swf.addVariable(variable[0], variable[1]);});' - m = re.search(re.escape(BEFORE) + '(.*?)' + re.escape(AFTER), webpage) + m = re.search(re.escape(BEFORE) + '(?:\n|\\\\n)(.*?)' + re.escape(AFTER), webpage) if m: - data = dict(json.loads(m.group(1))) + swf_params = m.group(1).replace('\\\\', '\\').replace('\\"', '"') + data = dict(json.loads(swf_params)) params_raw = compat_urllib_parse_unquote(data['params']) video_data = json.loads(params_raw)['video_data'] @@ -185,13 +220,15 @@ class FacebookIE(InfoExtractor): if not video_data: server_js_data = self._parse_json(self._search_regex( - r'handleServerJS\(({.+})\);', webpage, 'server js data'), video_id) + r'handleServerJS\(({.+})\);', webpage, 'server js data', default='{}'), video_id) for item in server_js_data.get('instances', []): if item[1][0] == 'VideoConfig': video_data = video_data_list2dict(item[2][0]['videoData']) break if not video_data: + if not fatal_if_no_video: + return webpage, False m_msg = re.search(r'class="[^"]*uiInterstitialContent[^"]*"><div>(.*?)</div>', webpage) if m_msg is not None: raise ExtractorError( @@ -208,10 +245,13 @@ class FacebookIE(InfoExtractor): for src_type in ('src', 'src_no_ratelimit'): src = f[0].get('%s_%s' % (quality, src_type)) if src: + preference = -10 if format_id == 'progressive' else 0 + if quality == 'hd': + preference += 5 formats.append({ 'format_id': '%s_%s_%s' % (format_id, quality, src_type), 'url': src, - 'preference': -10 if format_id == 'progressive' else 0, + 'preference': preference, }) dash_manifest = f[0].get('dash_manifest') if dash_manifest: @@ -234,39 +274,36 @@ class FacebookIE(InfoExtractor): video_title = 'Facebook video #%s' % video_id uploader = clean_html(get_element_by_id('fbPhotoPageAuthorName', webpage)) - return { + info_dict = { 'id': video_id, 'title': video_title, 'formats': formats, 'uploader': uploader, } - -class FacebookPostIE(InfoExtractor): - IE_NAME = 'facebook:post' - _VALID_URL = r'https?://(?:\w+\.)?facebook\.com/[^/]+/posts/(?P<id>\d+)' - _TEST = { - 'url': 'https://www.facebook.com/maxlayn/posts/10153807558977570', - 'md5': '037b1fa7f3c2d02b7a0d7bc16031ecc6', - 'info_dict': { - 'id': '544765982287235', - 'ext': 'mp4', - 'title': '"What are you doing running in the snow?"', - 'uploader': 'FailArmy', - } - } + return webpage, info_dict def _real_extract(self, url): - post_id = self._match_id(url) + video_id = self._match_id(url) + + real_url = self._VIDEO_PAGE_TEMPLATE % video_id if url.startswith('facebook:') else url + webpage, info_dict = self._extract_from_url(real_url, video_id, fatal_if_no_video=False) - webpage = self._download_webpage(url, post_id) + if info_dict: + return info_dict - entries = [ - self.url_result('facebook:%s' % video_id, FacebookIE.ie_key()) - for video_id in self._parse_json( - self._search_regex( - r'(["\'])video_ids\1\s*:\s*(?P<ids>\[.+?\])', - webpage, 'video ids', group='ids'), - post_id)] + if '/posts/' in url: + entries = [ + self.url_result('facebook:%s' % vid, FacebookIE.ie_key()) + for vid in self._parse_json( + self._search_regex( + r'(["\'])video_ids\1\s*:\s*(?P<ids>\[.+?\])', + webpage, 'video ids', group='ids'), + video_id)] - return self.playlist_result(entries, post_id) + return self.playlist_result(entries, video_id) + else: + _, info_dict = self._extract_from_url( + self._VIDEO_PAGE_TEMPLATE % video_id, + video_id, fatal_if_no_video=True) + return info_dict diff --git a/youtube_dl/extractor/faz.py b/youtube_dl/extractor/faz.py index 6f9b003c2..fd535457d 100644 --- a/youtube_dl/extractor/faz.py +++ b/youtube_dl/extractor/faz.py @@ -52,7 +52,7 @@ class FazIE(InfoExtractor): formats = [] for pref, code in enumerate(['LOW', 'HIGH', 'HQ']): encoding = xpath_element(encodings, code) - if encoding: + if encoding is not None: encoding_url = xpath_text(encoding, 'FILENAME') if encoding_url: formats.append({ diff --git a/youtube_dl/extractor/fivemin.py b/youtube_dl/extractor/fivemin.py index 2955965d9..67d50a386 100644 --- a/youtube_dl/extractor/fivemin.py +++ b/youtube_dl/extractor/fivemin.py @@ -1,5 +1,7 @@ from __future__ import unicode_literals +import re + from .common import InfoExtractor from ..compat import ( compat_urllib_parse, @@ -16,12 +18,7 @@ from ..utils import ( class FiveMinIE(InfoExtractor): IE_NAME = '5min' - _VALID_URL = r'''(?x) - (?:https?://[^/]*?5min\.com/Scripts/PlayerSeed\.js\?(?:.*?&)?playList=| - https?://(?:(?:massively|www)\.)?joystiq\.com/video/| - 5min:) - (?P<id>\d+) - ''' + _VALID_URL = r'(?:5min:(?P<id>\d+)(?::(?P<sid>\d+))?|https?://[^/]*?5min\.com/Scripts/PlayerSeed\.js\?(?P<query>.*))' _TESTS = [ { @@ -45,6 +42,7 @@ class FiveMinIE(InfoExtractor): 'title': 'How to Make a Next-Level Fruit Salad', 'duration': 184, }, + 'skip': 'no longer available', }, ] _ERRORS = { @@ -91,20 +89,33 @@ class FiveMinIE(InfoExtractor): } def _real_extract(self, url): - video_id = self._match_id(url) + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + sid = mobj.group('sid') + + if mobj.group('query'): + qs = compat_parse_qs(mobj.group('query')) + if not qs.get('playList'): + raise ExtractorError('Invalid URL', expected=True) + video_id = qs['playList'][0] + if qs.get('sid'): + sid = qs['sid'][0] + embed_url = 'https://embed.5min.com/playerseed/?playList=%s' % video_id - embed_page = self._download_webpage(embed_url, video_id, - 'Downloading embed page') - sid = self._search_regex(r'sid=(\d+)', embed_page, 'sid') - query = compat_urllib_parse.urlencode({ - 'func': 'GetResults', - 'playlist': video_id, - 'sid': sid, - 'isPlayerSeed': 'true', - 'url': embed_url, - }) + if not sid: + embed_page = self._download_webpage(embed_url, video_id, + 'Downloading embed page') + sid = self._search_regex(r'sid=(\d+)', embed_page, 'sid') + response = self._download_json( - 'https://syn.5min.com/handlers/SenseHandler.ashx?' + query, + 'https://syn.5min.com/handlers/SenseHandler.ashx?' + + compat_urllib_parse.urlencode({ + 'func': 'GetResults', + 'playlist': video_id, + 'sid': sid, + 'isPlayerSeed': 'true', + 'url': embed_url, + }), video_id) if not response['success']: raise ExtractorError( @@ -118,9 +129,7 @@ class FiveMinIE(InfoExtractor): parsed_video_url = compat_urllib_parse_urlparse(compat_parse_qs( compat_urllib_parse_urlparse(info['EmbededURL']).query)['videoUrl'][0]) for rendition in info['Renditions']: - if rendition['RenditionType'] == 'm3u8': - formats.extend(self._extract_m3u8_formats(rendition['Url'], video_id, m3u8_id='hls')) - elif rendition['RenditionType'] == 'aac': + if rendition['RenditionType'] == 'aac' or rendition['RenditionType'] == 'm3u8': continue else: rendition_url = compat_urlparse.urlunparse(parsed_video_url._replace(path=replace_extension(parsed_video_url.path.replace('//', '/%s/' % rendition['ID']), rendition['RenditionType']))) diff --git a/youtube_dl/extractor/foxnews.py b/youtube_dl/extractor/foxnews.py index 318ac013d..1dc50318c 100644 --- a/youtube_dl/extractor/foxnews.py +++ b/youtube_dl/extractor/foxnews.py @@ -36,6 +36,10 @@ class FoxNewsIE(AMPIE): # 'upload_date': '20141204', 'thumbnail': 're:^https?://.*\.jpg$', }, + 'params': { + # m3u8 download + 'skip_download': True, + }, }, { 'url': 'http://video.foxnews.com/v/video-embed.html?video_id=3937480&d=video.foxnews.com', diff --git a/youtube_dl/extractor/freespeech.py b/youtube_dl/extractor/freespeech.py index c210177f7..1477708bb 100644 --- a/youtube_dl/extractor/freespeech.py +++ b/youtube_dl/extractor/freespeech.py @@ -14,7 +14,7 @@ class FreespeechIE(InfoExtractor): 'url': 'https://www.freespeech.org/video/obama-romney-campaign-colorado-ahead-debate-0', 'info_dict': { 'id': 'poKsVCZ64uU', - 'ext': 'mp4', + 'ext': 'webm', 'title': 'Obama, Romney Campaign in Colorado Ahead of Debate', 'description': 'Obama, Romney Campaign in Colorado Ahead of Debate', 'uploader': 'freespeechtv', diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 45adbb7a3..8121f04a5 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -47,6 +47,7 @@ from .senateisvp import SenateISVPIE from .svt import SVTIE from .pornhub import PornHubIE from .xhamster import XHamsterEmbedIE +from .tnaflix import TNAFlixNetworkEmbedIE from .vimeo import VimeoIE from .dailymotion import DailymotionCloudIE from .onionstudios import OnionStudiosIE @@ -1241,28 +1242,34 @@ class GenericIE(InfoExtractor): full_response = self._request_webpage(request, video_id) head_response = full_response + info_dict = { + 'id': video_id, + 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]), + } + # Check for direct link to a video content_type = head_response.headers.get('Content-Type', '') m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>.+)$', content_type) if m: upload_date = unified_strdate( head_response.headers.get('Last-Modified')) - formats = [] - if m.group('format_id').endswith('mpegurl'): + format_id = m.group('format_id') + if format_id.endswith('mpegurl'): formats = self._extract_m3u8_formats(url, video_id, 'mp4') + elif format_id == 'f4m': + formats = self._extract_f4m_formats(url, video_id) else: formats = [{ 'format_id': m.group('format_id'), 'url': url, 'vcodec': 'none' if m.group('type') == 'audio' else None }] - return { - 'id': video_id, - 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]), + info_dict.update({ 'direct': True, 'formats': formats, 'upload_date': upload_date, - } + }) + return info_dict if not self._downloader.params.get('test', False) and not is_intentional: force = self._downloader.params.get('force_generic_extractor', False) @@ -1290,13 +1297,12 @@ class GenericIE(InfoExtractor): 'URL could be a direct video link, returning it as such.') upload_date = unified_strdate( head_response.headers.get('Last-Modified')) - return { - 'id': video_id, - 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]), + info_dict.update({ 'direct': True, 'url': url, 'upload_date': upload_date, - } + }) + return info_dict webpage = self._webpage_read_content( full_response, url, video_id, prefix=first_bytes) @@ -1313,12 +1319,12 @@ class GenericIE(InfoExtractor): elif doc.tag == '{http://xspf.org/ns/0/}playlist': return self.playlist_result(self._parse_xspf(doc, video_id), video_id) elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag): - return { - 'id': video_id, - 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]), - 'formats': self._parse_mpd_formats( - doc, video_id, mpd_base_url=url.rpartition('/')[0]), - } + info_dict['formats'] = self._parse_mpd_formats( + doc, video_id, mpd_base_url=url.rpartition('/')[0]) + return info_dict + elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag): + info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id) + return info_dict except compat_xml_parse_error: pass @@ -1573,6 +1579,11 @@ class GenericIE(InfoExtractor): if mobj is not None: return self.url_result(mobj.group('url'), 'VK') + # Look for embedded Odnoklassniki player + mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage) + if mobj is not None: + return self.url_result(mobj.group('url'), 'Odnoklassniki') + # Look for embedded ivi player mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage) if mobj is not None: @@ -1628,6 +1639,11 @@ class GenericIE(InfoExtractor): if xhamster_urls: return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed') + # Look for embedded TNAFlixNetwork player + tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage) + if tnaflix_urls: + return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key()) + # Look for embedded Tvigle player mobj = re.search( r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage) @@ -1974,6 +1990,8 @@ class GenericIE(InfoExtractor): entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4') elif ext == 'mpd': entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id) + elif ext == 'f4m': + entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id) else: entry_info_dict['url'] = video_url diff --git a/youtube_dl/extractor/googledrive.py b/youtube_dl/extractor/googledrive.py index f354c9c7a..766fc26d0 100644 --- a/youtube_dl/extractor/googledrive.py +++ b/youtube_dl/extractor/googledrive.py @@ -10,8 +10,8 @@ from ..utils import ( class GoogleDriveIE(InfoExtractor): - _VALID_URL = r'https?://(?:(?:docs|drive)\.google\.com/(?:uc\?.*?id=|file/d/)|video\.google\.com/get_player\?.*?docid=)(?P<id>[a-zA-Z0-9_-]{28})' - _TEST = { + _VALID_URL = r'https?://(?:(?:docs|drive)\.google\.com/(?:uc\?.*?id=|file/d/)|video\.google\.com/get_player\?.*?docid=)(?P<id>[a-zA-Z0-9_-]{28,})' + _TESTS = [{ 'url': 'https://drive.google.com/file/d/0ByeS4oOUV-49Zzh4R1J6R09zazQ/edit?pli=1', 'md5': '881f7700aec4f538571fa1e0eed4a7b6', 'info_dict': { @@ -20,7 +20,11 @@ class GoogleDriveIE(InfoExtractor): 'title': 'Big Buck Bunny.mp4', 'duration': 46, } - } + }, { + # video id is longer than 28 characters + 'url': 'https://drive.google.com/file/d/1ENcQ_jeCuj7y19s66_Ou9dRP4GKGsodiDQ/edit', + 'only_matching': True, + }] _FORMATS_EXT = { '5': 'flv', '6': 'flv', @@ -43,7 +47,7 @@ class GoogleDriveIE(InfoExtractor): @staticmethod def _extract_url(webpage): mobj = re.search( - r'<iframe[^>]+src="https?://(?:video\.google\.com/get_player\?.*?docid=|(?:docs|drive)\.google\.com/file/d/)(?P<id>[a-zA-Z0-9_-]{28})', + r'<iframe[^>]+src="https?://(?:video\.google\.com/get_player\?.*?docid=|(?:docs|drive)\.google\.com/file/d/)(?P<id>[a-zA-Z0-9_-]{28,})', webpage) if mobj: return 'https://drive.google.com/file/d/%s' % mobj.group('id') @@ -82,7 +86,7 @@ class GoogleDriveIE(InfoExtractor): return { 'id': video_id, 'title': title, - 'thumbnail': self._og_search_thumbnail(webpage), + 'thumbnail': self._og_search_thumbnail(webpage, default=None), 'duration': duration, 'formats': formats, } diff --git a/youtube_dl/extractor/imdb.py b/youtube_dl/extractor/imdb.py index 02e1e428e..b61b2dc4e 100644 --- a/youtube_dl/extractor/imdb.py +++ b/youtube_dl/extractor/imdb.py @@ -42,7 +42,7 @@ class ImdbIE(InfoExtractor): for f_url, f_name in extra_formats] format_pages.append(player_page) - quality = qualities(['SD', '480p', '720p']) + quality = qualities(('SD', '480p', '720p', '1080p')) formats = [] for format_page in format_pages: json_data = self._search_regex( diff --git a/youtube_dl/extractor/indavideo.py b/youtube_dl/extractor/indavideo.py index 12fb5e8e1..9622f198a 100644 --- a/youtube_dl/extractor/indavideo.py +++ b/youtube_dl/extractor/indavideo.py @@ -73,7 +73,7 @@ class IndavideoEmbedIE(InfoExtractor): 'url': self._proto_relative_url(thumbnail) } for thumbnail in video.get('thumbnails', [])] - tags = [tag['title'] for tag in video.get('tags', [])] + tags = [tag['title'] for tag in video.get('tags') or []] return { 'id': video.get('id') or video_id, diff --git a/youtube_dl/extractor/infoq.py b/youtube_dl/extractor/infoq.py index 016af2084..cca0b8a93 100644 --- a/youtube_dl/extractor/infoq.py +++ b/youtube_dl/extractor/infoq.py @@ -4,15 +4,12 @@ from __future__ import unicode_literals import base64 -from .common import InfoExtractor -from ..compat import ( - compat_urllib_parse_unquote, - compat_parse_qs, -) +from ..compat import compat_urllib_parse_unquote from ..utils import determine_ext +from .bokecc import BokeCCBaseIE -class InfoQIE(InfoExtractor): +class InfoQIE(BokeCCBaseIE): _VALID_URL = r'https?://(?:www\.)?infoq\.com/(?:[^/]+/)+(?P<id>[^/]+)' _TESTS = [{ @@ -38,26 +35,6 @@ class InfoQIE(InfoExtractor): }, }] - def _extract_bokecc_videos(self, webpage, video_id): - # TODO: bokecc.com is a Chinese video cloud platform - # It should have an independent extractor but I don't have other - # examples using bokecc - player_params_str = self._html_search_regex( - r'<script[^>]+src="http://p\.bokecc\.com/player\?([^"]+)', - webpage, 'player params', default=None) - - player_params = compat_parse_qs(player_params_str) - - info_xml = self._download_xml( - 'http://p.bokecc.com/servlet/playinfo?uid=%s&vid=%s&m=1' % ( - player_params['siteid'][0], player_params['vid'][0]), video_id) - - return [{ - 'format_id': 'bokecc', - 'url': quality.find('./copy').attrib['playurl'], - 'preference': int(quality.attrib['value']), - } for quality in info_xml.findall('./video/quality')] - def _extract_rtmp_videos(self, webpage): # The server URL is hardcoded video_url = 'rtmpe://video.infoq.com/cfx/st/' @@ -101,7 +78,7 @@ class InfoQIE(InfoExtractor): if '/cn/' in url: # for China videos, HTTP video URL exists but always fails with 403 - formats = self._extract_bokecc_videos(webpage, video_id) + formats = self._extract_bokecc_formats(webpage, video_id) else: formats = self._extract_rtmp_videos(webpage) + self._extract_http_videos(webpage) diff --git a/youtube_dl/extractor/iqiyi.py b/youtube_dl/extractor/iqiyi.py index 9046705a5..e7c0cb3f6 100644 --- a/youtube_dl/extractor/iqiyi.py +++ b/youtube_dl/extractor/iqiyi.py @@ -2,32 +2,173 @@ from __future__ import unicode_literals import hashlib +import itertools import math import os import random +import re import time import uuid from .common import InfoExtractor from ..compat import ( compat_parse_qs, + compat_str, compat_urllib_parse, compat_urllib_parse_urlparse, ) from ..utils import ( + decode_packed_codes, ExtractorError, + ohdave_rsa_encrypt, + remove_start, sanitized_Request, urlencode_postdata, url_basename, ) +def md5_text(text): + return hashlib.md5(text.encode('utf-8')).hexdigest() + + +class IqiyiSDK(object): + def __init__(self, target, ip, timestamp): + self.target = target + self.ip = ip + self.timestamp = timestamp + + @staticmethod + def split_sum(data): + return compat_str(sum(map(lambda p: int(p, 16), list(data)))) + + @staticmethod + def digit_sum(num): + if isinstance(num, int): + num = compat_str(num) + return compat_str(sum(map(int, num))) + + def even_odd(self): + even = self.digit_sum(compat_str(self.timestamp)[::2]) + odd = self.digit_sum(compat_str(self.timestamp)[1::2]) + return even, odd + + def preprocess(self, chunksize): + self.target = md5_text(self.target) + chunks = [] + for i in range(32 // chunksize): + chunks.append(self.target[chunksize * i:chunksize * (i + 1)]) + if 32 % chunksize: + chunks.append(self.target[32 - 32 % chunksize:]) + return chunks, list(map(int, self.ip.split('.'))) + + def mod(self, modulus): + chunks, ip = self.preprocess(32) + self.target = chunks[0] + ''.join(map(lambda p: compat_str(p % modulus), ip)) + + def split(self, chunksize): + modulus_map = { + 4: 256, + 5: 10, + 8: 100, + } + + chunks, ip = self.preprocess(chunksize) + ret = '' + for i in range(len(chunks)): + ip_part = compat_str(ip[i] % modulus_map[chunksize]) if i < 4 else '' + if chunksize == 8: + ret += ip_part + chunks[i] + else: + ret += chunks[i] + ip_part + self.target = ret + + def handle_input16(self): + self.target = md5_text(self.target) + self.target = self.split_sum(self.target[:16]) + self.target + self.split_sum(self.target[16:]) + + def handle_input8(self): + self.target = md5_text(self.target) + ret = '' + for i in range(4): + part = self.target[8 * i:8 * (i + 1)] + ret += self.split_sum(part) + part + self.target = ret + + def handleSum(self): + self.target = md5_text(self.target) + self.target = self.split_sum(self.target) + self.target + + def date(self, scheme): + self.target = md5_text(self.target) + d = time.localtime(self.timestamp) + strings = { + 'y': compat_str(d.tm_year), + 'm': '%02d' % d.tm_mon, + 'd': '%02d' % d.tm_mday, + } + self.target += ''.join(map(lambda c: strings[c], list(scheme))) + + def split_time_even_odd(self): + even, odd = self.even_odd() + self.target = odd + md5_text(self.target) + even + + def split_time_odd_even(self): + even, odd = self.even_odd() + self.target = even + md5_text(self.target) + odd + + def split_ip_time_sum(self): + chunks, ip = self.preprocess(32) + self.target = compat_str(sum(ip)) + chunks[0] + self.digit_sum(self.timestamp) + + def split_time_ip_sum(self): + chunks, ip = self.preprocess(32) + self.target = self.digit_sum(self.timestamp) + chunks[0] + compat_str(sum(ip)) + + +class IqiyiSDKInterpreter(object): + def __init__(self, sdk_code): + self.sdk_code = sdk_code + + def run(self, target, ip, timestamp): + self.sdk_code = decode_packed_codes(self.sdk_code) + + functions = re.findall(r'input=([a-zA-Z0-9]+)\(input', self.sdk_code) + + sdk = IqiyiSDK(target, ip, timestamp) + + other_functions = { + 'handleSum': sdk.handleSum, + 'handleInput8': sdk.handle_input8, + 'handleInput16': sdk.handle_input16, + 'splitTimeEvenOdd': sdk.split_time_even_odd, + 'splitTimeOddEven': sdk.split_time_odd_even, + 'splitIpTimeSum': sdk.split_ip_time_sum, + 'splitTimeIpSum': sdk.split_time_ip_sum, + } + for function in functions: + if re.match(r'mod\d+', function): + sdk.mod(int(function[3:])) + elif re.match(r'date[ymd]{3}', function): + sdk.date(function[4:]) + elif re.match(r'split\d+', function): + sdk.split(int(function[5:])) + elif function in other_functions: + other_functions[function]() + else: + raise ExtractorError('Unknown funcion %s' % function) + + return sdk.target + + class IqiyiIE(InfoExtractor): IE_NAME = 'iqiyi' IE_DESC = '爱奇艺' _VALID_URL = r'http://(?:[^.]+\.)?iqiyi\.com/.+\.html' + _NETRC_MACHINE = 'iqiyi' + _TESTS = [{ 'url': 'http://www.iqiyi.com/v_19rrojlavg.html', 'md5': '2cb594dc2781e6c941a110d8f358118b', @@ -125,6 +266,13 @@ class IqiyiIE(InfoExtractor): }, }], 'expected_warnings': ['Needs a VIP account for full video'], + }, { + 'url': 'http://www.iqiyi.com/a_19rrhb8ce1.html', + 'info_dict': { + 'id': '202918101', + 'title': '灌篮高手 国语版', + }, + 'playlist_count': 101, }] _FORMATS_MAP = [ @@ -136,9 +284,63 @@ class IqiyiIE(InfoExtractor): ('10', 'h1'), ] + def _real_initialize(self): + self._login() + @staticmethod - def md5_text(text): - return hashlib.md5(text.encode('utf-8')).hexdigest() + def _rsa_fun(data): + # public key extracted from http://static.iqiyi.com/js/qiyiV2/20160129180840/jobs/i18n/i18nIndex.js + N = 0xab86b6371b5318aaa1d3c9e612a9f1264f372323c8c0f19875b5fc3b3fd3afcc1e5bec527aa94bfa85bffc157e4245aebda05389a5357b75115ac94f074aefcd + e = 65537 + + return ohdave_rsa_encrypt(data, e, N) + + def _login(self): + (username, password) = self._get_login_info() + + # No authentication to be performed + if not username: + return True + + data = self._download_json( + 'http://kylin.iqiyi.com/get_token', None, + note='Get token for logging', errnote='Unable to get token for logging') + sdk = data['sdk'] + timestamp = int(time.time()) + target = '/apis/reglogin/login.action?lang=zh_TW&area_code=null&email=%s&passwd=%s&agenttype=1&from=undefined&keeplogin=0&piccode=&fromurl=&_pos=1' % ( + username, self._rsa_fun(password.encode('utf-8'))) + + interp = IqiyiSDKInterpreter(sdk) + sign = interp.run(target, data['ip'], timestamp) + + validation_params = { + 'target': target, + 'server': 'BEA3AA1908656AABCCFF76582C4C6660', + 'token': data['token'], + 'bird_src': 'f8d91d57af224da7893dd397d52d811a', + 'sign': sign, + 'bird_t': timestamp, + } + validation_result = self._download_json( + 'http://kylin.iqiyi.com/validate?' + compat_urllib_parse.urlencode(validation_params), None, + note='Validate credentials', errnote='Unable to validate credentials') + + MSG_MAP = { + 'P00107': 'please login via the web interface and enter the CAPTCHA code', + 'P00117': 'bad username or password', + } + + code = validation_result['code'] + if code != 'A00000': + msg = MSG_MAP.get(code) + if not msg: + msg = 'error %s' % code + if validation_result.get('msg'): + msg += ': ' + validation_result['msg'] + self._downloader.report_warning('unable to log in: ' + msg) + return False + + return True def _authenticate_vip_video(self, api_video_url, video_id, tvid, _uuid, do_report_warning): auth_params = { @@ -199,7 +401,7 @@ class IqiyiIE(InfoExtractor): note='Download path key of segment %d for format %s' % (segment_index + 1, format_id) )['t'] t = str(int(math.floor(int(tm) / (600.0)))) - return self.md5_text(t + mg + x) + return md5_text(t + mg + x) video_urls_dict = {} need_vip_warning_report = True @@ -278,16 +480,16 @@ class IqiyiIE(InfoExtractor): tail = tm + tvid param = { 'key': 'fvip', - 'src': self.md5_text('youtube-dl'), + 'src': md5_text('youtube-dl'), 'tvId': tvid, 'vid': video_id, 'vinfo': 1, 'tm': tm, - 'enc': self.md5_text(enc_key + tail), + 'enc': md5_text(enc_key + tail), 'qyid': _uuid, 'tn': random.random(), 'um': 0, - 'authkey': self.md5_text(self.md5_text('') + tail), + 'authkey': md5_text(md5_text('') + tail), 'k_tag': 1, } @@ -296,24 +498,62 @@ class IqiyiIE(InfoExtractor): raw_data = self._download_json(api_url, video_id) return raw_data - def get_enc_key(self, swf_url, video_id): + def get_enc_key(self, video_id): # TODO: automatic key extraction # last update at 2016-01-22 for Zombie::bite - enc_key = '6ab6d0280511493ba85594779759d4ed' + enc_key = '8ed797d224d043e7ac23d95b70227d32' return enc_key + def _extract_playlist(self, webpage): + PAGE_SIZE = 50 + + links = re.findall( + r'<a[^>]+class="site-piclist_pic_link"[^>]+href="(http://www\.iqiyi\.com/.+\.html)"', + webpage) + if not links: + return + + album_id = self._search_regex( + r'albumId\s*:\s*(\d+),', webpage, 'album ID') + album_title = self._search_regex( + r'data-share-title="([^"]+)"', webpage, 'album title', fatal=False) + + entries = list(map(self.url_result, links)) + + # Start from 2 because links in the first page are already on webpage + for page_num in itertools.count(2): + pagelist_page = self._download_webpage( + 'http://cache.video.qiyi.com/jp/avlist/%s/%d/%d/' % (album_id, page_num, PAGE_SIZE), + album_id, + note='Download playlist page %d' % page_num, + errnote='Failed to download playlist page %d' % page_num) + pagelist = self._parse_json( + remove_start(pagelist_page, 'var tvInfoJs='), album_id) + vlist = pagelist['data']['vlist'] + for item in vlist: + entries.append(self.url_result(item['vurl'])) + if len(vlist) < PAGE_SIZE: + break + + return self.playlist_result(entries, album_id, album_title) + def _real_extract(self, url): webpage = self._download_webpage( url, 'temp_id', note='download video page') + + # There's no simple way to determine whether an URL is a playlist or not + # So detect it + playlist_result = self._extract_playlist(webpage) + if playlist_result: + return playlist_result + tvid = self._search_regex( r'data-player-tvid\s*=\s*[\'"](\d+)', webpage, 'tvid') video_id = self._search_regex( r'data-player-videoid\s*=\s*[\'"]([a-f\d]+)', webpage, 'video_id') - swf_url = self._search_regex( - r'(http://[^\'"]+MainPlayer[^.]+\.swf)', webpage, 'swf player URL') _uuid = uuid.uuid4().hex - enc_key = self.get_enc_key(swf_url, video_id) + enc_key = self.get_enc_key(video_id) raw_data = self.get_raw_data(tvid, video_id, enc_key, _uuid) diff --git a/youtube_dl/extractor/jeuxvideo.py b/youtube_dl/extractor/jeuxvideo.py index eef7daa29..137db873c 100644 --- a/youtube_dl/extractor/jeuxvideo.py +++ b/youtube_dl/extractor/jeuxvideo.py @@ -30,7 +30,7 @@ class JeuxVideoIE(InfoExtractor): webpage = self._download_webpage(url, title) title = self._html_search_meta('name', webpage) or self._og_search_title(webpage) config_url = self._html_search_regex( - r'data-src="(/contenu/medias/video.php.*?)"', + r'data-src(?:set-video)?="(/contenu/medias/video.php.*?)"', webpage, 'config URL') config_url = 'http://www.jeuxvideo.com' + config_url diff --git a/youtube_dl/extractor/jwplatform.py b/youtube_dl/extractor/jwplatform.py index 8e90d5986..6770685d7 100644 --- a/youtube_dl/extractor/jwplatform.py +++ b/youtube_dl/extractor/jwplatform.py @@ -7,33 +7,9 @@ from .common import InfoExtractor from ..utils import int_or_none -class JWPlatformIE(InfoExtractor): - _VALID_URL = r'(?:https?://content\.jwplatform\.com/(?:feeds|players|jw6)/|jwplatform:)(?P<id>[a-zA-Z0-9]{8})' - _TEST = { - 'url': 'http://content.jwplatform.com/players/nPripu9l-ALJ3XQCI.js', - 'md5': 'fa8899fa601eb7c83a64e9d568bdf325', - 'info_dict': { - 'id': 'nPripu9l', - 'ext': 'mov', - 'title': 'Big Buck Bunny Trailer', - 'description': 'Big Buck Bunny is a short animated film by the Blender Institute. It is made using free and open source software.', - 'upload_date': '20081127', - 'timestamp': 1227796140, - } - } - - @staticmethod - def _extract_url(webpage): - mobj = re.search( - r'<script[^>]+?src=["\'](?P<url>(?:https?:)?//content.jwplatform.com/players/[a-zA-Z0-9]{8})', - webpage) - if mobj: - return mobj.group('url') - - def _real_extract(self, url): - video_id = self._match_id(url) - json_data = self._download_json('http://content.jwplatform.com/feeds/%s.json' % video_id, video_id) - video_data = json_data['playlist'][0] +class JWPlatformBaseIE(InfoExtractor): + def _parse_jwplayer_data(self, jwplayer_data, video_id, require_title=True): + video_data = jwplayer_data['playlist'][0] subtitles = {} for track in video_data['tracks']: if track['kind'] == 'captions': @@ -43,7 +19,7 @@ class JWPlatformIE(InfoExtractor): for source in video_data['sources']: source_url = self._proto_relative_url(source['file']) source_type = source.get('type') or '' - if source_type == 'application/vnd.apple.mpegurl': + if source_type in ('application/vnd.apple.mpegurl', 'hls'): formats.extend(self._extract_m3u8_formats( source_url, video_id, 'mp4', 'm3u8_native', fatal=False)) elif source_type.startswith('audio'): @@ -61,10 +37,39 @@ class JWPlatformIE(InfoExtractor): return { 'id': video_id, - 'title': video_data['title'], + 'title': video_data['title'] if require_title else video_data.get('title'), 'description': video_data.get('description'), 'thumbnail': self._proto_relative_url(video_data.get('image')), 'timestamp': int_or_none(video_data.get('pubdate')), 'subtitles': subtitles, 'formats': formats, } + + +class JWPlatformIE(JWPlatformBaseIE): + _VALID_URL = r'(?:https?://content\.jwplatform\.com/(?:feeds|players|jw6)/|jwplatform:)(?P<id>[a-zA-Z0-9]{8})' + _TEST = { + 'url': 'http://content.jwplatform.com/players/nPripu9l-ALJ3XQCI.js', + 'md5': 'fa8899fa601eb7c83a64e9d568bdf325', + 'info_dict': { + 'id': 'nPripu9l', + 'ext': 'mov', + 'title': 'Big Buck Bunny Trailer', + 'description': 'Big Buck Bunny is a short animated film by the Blender Institute. It is made using free and open source software.', + 'upload_date': '20081127', + 'timestamp': 1227796140, + } + } + + @staticmethod + def _extract_url(webpage): + mobj = re.search( + r'<script[^>]+?src=["\'](?P<url>(?:https?:)?//content.jwplatform.com/players/[a-zA-Z0-9]{8})', + webpage) + if mobj: + return mobj.group('url') + + def _real_extract(self, url): + video_id = self._match_id(url) + json_data = self._download_json('http://content.jwplatform.com/feeds/%s.json' % video_id, video_id) + return self._parse_jwplayer_data(json_data, video_id) diff --git a/youtube_dl/extractor/kaltura.py b/youtube_dl/extractor/kaltura.py index ccbc39c66..44d7c84a1 100644 --- a/youtube_dl/extractor/kaltura.py +++ b/youtube_dl/extractor/kaltura.py @@ -8,6 +8,7 @@ from .common import InfoExtractor from ..compat import ( compat_urllib_parse, compat_urlparse, + compat_parse_qs, ) from ..utils import ( clean_html, @@ -20,21 +21,17 @@ from ..utils import ( class KalturaIE(InfoExtractor): _VALID_URL = r'''(?x) (?: - kaltura:(?P<partner_id_s>\d+):(?P<id_s>[0-9a-z_]+)| + kaltura:(?P<partner_id>\d+):(?P<id>[0-9a-z_]+)| https?:// (:?(?:www|cdnapi(?:sec)?)\.)?kaltura\.com/ (?: (?: # flash player - index\.php/kwidget/ - (?:[^/]+/)*?wid/_(?P<partner_id>\d+)/ - (?:[^/]+/)*?entry_id/(?P<id>[0-9a-z_]+)| + index\.php/kwidget| # html5 player - html5/html5lib/ - (?:[^/]+/)*?entry_id/(?P<id_html5>[0-9a-z_]+) - .*\?.*\bwid=_(?P<partner_id_html5>\d+) + html5/html5lib/[^/]+/mwEmbedFrame\.php ) - ) + )(?:/(?P<path>[^?]+))?(?:\?(?P<query>.*))? ) ''' _API_BASE = 'http://cdnapi.kaltura.com/api_v3/index.php?' @@ -127,10 +124,41 @@ class KalturaIE(InfoExtractor): url, smuggled_data = unsmuggle_url(url, {}) mobj = re.match(self._VALID_URL, url) - partner_id = mobj.group('partner_id_s') or mobj.group('partner_id') or mobj.group('partner_id_html5') - entry_id = mobj.group('id_s') or mobj.group('id') or mobj.group('id_html5') - - info, flavor_assets = self._get_video_info(entry_id, partner_id) + partner_id, entry_id = mobj.group('partner_id', 'id') + ks = None + if partner_id and entry_id: + info, flavor_assets = self._get_video_info(entry_id, partner_id) + else: + path, query = mobj.group('path', 'query') + if not path and not query: + raise ExtractorError('Invalid URL', expected=True) + params = {} + if query: + params = compat_parse_qs(query) + if path: + splitted_path = path.split('/') + params.update(dict((zip(splitted_path[::2], [[v] for v in splitted_path[1::2]])))) + if 'wid' in params: + partner_id = params['wid'][0][1:] + elif 'p' in params: + partner_id = params['p'][0] + else: + raise ExtractorError('Invalid URL', expected=True) + if 'entry_id' in params: + entry_id = params['entry_id'][0] + info, flavor_assets = self._get_video_info(entry_id, partner_id) + elif 'uiconf_id' in params and 'flashvars[referenceId]' in params: + reference_id = params['flashvars[referenceId]'][0] + webpage = self._download_webpage(url, reference_id) + entry_data = self._parse_json(self._search_regex( + r'window\.kalturaIframePackageData\s*=\s*({.*});', + webpage, 'kalturaIframePackageData'), + reference_id)['entryResult'] + info, flavor_assets = entry_data['meta'], entry_data['contextData']['flavorAssets'] + entry_id = info['id'] + else: + raise ExtractorError('Invalid URL', expected=True) + ks = params.get('flashvars[ks]', [None])[0] source_url = smuggled_data.get('source_url') if source_url: @@ -140,14 +168,19 @@ class KalturaIE(InfoExtractor): else: referrer = None + def sign_url(unsigned_url): + if ks: + unsigned_url += '/ks/%s' % ks + if referrer: + unsigned_url += '?referrer=%s' % referrer + return unsigned_url + formats = [] for f in flavor_assets: # Continue if asset is not ready if f['status'] != 2: continue - video_url = '%s/flavorId/%s' % (info['dataUrl'], f['id']) - if referrer: - video_url += '?referrer=%s' % referrer + video_url = sign_url('%s/flavorId/%s' % (info['dataUrl'], f['id'])) formats.append({ 'format_id': '%(fileExt)s-%(bitrate)s' % f, 'ext': f.get('fileExt'), @@ -160,9 +193,7 @@ class KalturaIE(InfoExtractor): 'width': int_or_none(f.get('width')), 'url': video_url, }) - m3u8_url = info['dataUrl'].replace('format/url', 'format/applehttp') - if referrer: - m3u8_url += '?referrer=%s' % referrer + m3u8_url = sign_url(info['dataUrl'].replace('format/url', 'format/applehttp')) formats.extend(self._extract_m3u8_formats( m3u8_url, entry_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)) diff --git a/youtube_dl/extractor/khanacademy.py b/youtube_dl/extractor/khanacademy.py index 08a671fa8..61739efa7 100644 --- a/youtube_dl/extractor/khanacademy.py +++ b/youtube_dl/extractor/khanacademy.py @@ -14,10 +14,10 @@ class KhanAcademyIE(InfoExtractor): _TESTS = [{ 'url': 'http://www.khanacademy.org/video/one-time-pad', - 'md5': '7021db7f2d47d4fff89b13177cb1e8f4', + 'md5': '7b391cce85e758fb94f763ddc1bbb979', 'info_dict': { 'id': 'one-time-pad', - 'ext': 'mp4', + 'ext': 'webm', 'title': 'The one-time pad', 'description': 'The perfect cipher', 'duration': 176, diff --git a/youtube_dl/extractor/kusi.py b/youtube_dl/extractor/kusi.py new file mode 100644 index 000000000..931f34c9b --- /dev/null +++ b/youtube_dl/extractor/kusi.py @@ -0,0 +1,99 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import random +import re + +from .common import InfoExtractor +from ..compat import compat_urllib_parse_unquote_plus +from ..utils import ( + int_or_none, + float_or_none, + timeconvert, + update_url_query, + xpath_text, +) + + +class KUSIIE(InfoExtractor): + _VALID_URL = r'http://(?:www\.)?kusi\.com/(?P<path>story/.+|video\?clipId=(?P<clipId>\d+))' + _TESTS = [{ + 'url': 'http://www.kusi.com/story/31183873/turko-files-case-closed-put-on-hold', + 'md5': 'f926e7684294cf8cb7bdf8858e1b3988', + 'info_dict': { + 'id': '12203019', + 'ext': 'mp4', + 'title': 'Turko Files: Case Closed! & Put On Hold!', + 'duration': 231.0, + 'upload_date': '20160210', + 'timestamp': 1455087571, + 'thumbnail': 're:^https?://.*\.jpg$' + }, + }, { + 'url': 'http://kusi.com/video?clipId=12203019', + 'info_dict': { + 'id': '12203019', + 'ext': 'mp4', + 'title': 'Turko Files: Case Closed! & Put On Hold!', + 'duration': 231.0, + 'upload_date': '20160210', + 'timestamp': 1455087571, + 'thumbnail': 're:^https?://.*\.jpg$' + }, + 'params': { + 'skip_download': True, # Same as previous one + }, + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + clip_id = mobj.group('clipId') + video_id = clip_id or mobj.group('path') + + webpage = self._download_webpage(url, video_id) + + if clip_id is None: + video_id = clip_id = self._html_search_regex( + r'"clipId"\s*,\s*"(\d+)"', webpage, 'clip id') + + affiliate_id = self._search_regex( + r'affiliateId\s*:\s*\'([^\']+)\'', webpage, 'affiliate id') + + # See __Packages/worldnow/model/GalleryModel.as of WNGallery.swf + xml_url = update_url_query('http://www.kusi.com/build.asp', { + 'buildtype': 'buildfeaturexmlrequest', + 'featureType': 'Clip', + 'featureid': clip_id, + 'affiliateno': affiliate_id, + 'clientgroupid': '1', + 'rnd': int(round(random.random() * 1000000)), + }) + + doc = self._download_xml(xml_url, video_id) + + video_title = xpath_text(doc, 'HEADLINE', fatal=True) + duration = float_or_none(xpath_text(doc, 'DURATION'), scale=1000) + description = xpath_text(doc, 'ABSTRACT') + thumbnail = xpath_text(doc, './THUMBNAILIMAGE/FILENAME') + createtion_time = timeconvert(xpath_text(doc, 'rfc822creationdate')) + + quality_options = doc.find('{http://search.yahoo.com/mrss/}group').findall('{http://search.yahoo.com/mrss/}content') + formats = [] + for quality in quality_options: + formats.append({ + 'url': compat_urllib_parse_unquote_plus(quality.attrib['url']), + 'height': int_or_none(quality.attrib.get('height')), + 'width': int_or_none(quality.attrib.get('width')), + 'vbr': float_or_none(quality.attrib.get('bitratebits'), scale=1000), + }) + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': video_title, + 'description': description, + 'duration': duration, + 'formats': formats, + 'thumbnail': thumbnail, + 'timestamp': createtion_time, + } diff --git a/youtube_dl/extractor/kuwo.py b/youtube_dl/extractor/kuwo.py index f641edef8..700e44b63 100644 --- a/youtube_dl/extractor/kuwo.py +++ b/youtube_dl/extractor/kuwo.py @@ -68,6 +68,7 @@ class KuwoIE(KuwoBaseIE): 'id': '6446136', 'ext': 'mp3', 'title': '心', + 'description': 'md5:b2ab6295d014005bfc607525bfc1e38a', 'creator': 'IU', 'upload_date': '20150518', }, diff --git a/youtube_dl/extractor/letv.py b/youtube_dl/extractor/leeco.py index 9665ece89..df47e88ba 100644 --- a/youtube_dl/extractor/letv.py +++ b/youtube_dl/extractor/leeco.py @@ -1,36 +1,39 @@ # coding: utf-8 from __future__ import unicode_literals +import base64 import datetime +import hashlib import re import time -import base64 -import hashlib from .common import InfoExtractor from ..compat import ( - compat_urllib_parse, compat_ord, compat_str, + compat_urllib_parse, ) from ..utils import ( determine_ext, + encode_data_uri, ExtractorError, + int_or_none, + orderedSet, parse_iso8601, sanitized_Request, - int_or_none, str_or_none, - encode_data_uri, url_basename, ) -class LetvIE(InfoExtractor): +class LeIE(InfoExtractor): IE_DESC = '乐视网' - _VALID_URL = r'http://www\.letv\.com/ptv/vplay/(?P<id>\d+).html' + _VALID_URL = r'http://www\.le\.com/ptv/vplay/(?P<id>\d+)\.html' + + _URL_TEMPLATE = 'http://www.le.com/ptv/vplay/%s.html' _TESTS = [{ - 'url': 'http://www.letv.com/ptv/vplay/22005890.html', + 'url': 'http://www.le.com/ptv/vplay/22005890.html', 'md5': 'edadcfe5406976f42f9f266057ee5e40', 'info_dict': { 'id': '22005890', @@ -42,7 +45,7 @@ class LetvIE(InfoExtractor): 'hls_prefer_native': True, }, }, { - 'url': 'http://www.letv.com/ptv/vplay/1415246.html', + 'url': 'http://www.le.com/ptv/vplay/1415246.html', 'info_dict': { 'id': '1415246', 'ext': 'mp4', @@ -54,7 +57,7 @@ class LetvIE(InfoExtractor): }, }, { 'note': 'This video is available only in Mainland China, thus a proxy is needed', - 'url': 'http://www.letv.com/ptv/vplay/1118082.html', + 'url': 'http://www.le.com/ptv/vplay/1118082.html', 'md5': '2424c74948a62e5f31988438979c5ad1', 'info_dict': { 'id': '1118082', @@ -94,17 +97,16 @@ class LetvIE(InfoExtractor): return encrypted_data encrypted_data = encrypted_data[5:] - _loc4_ = bytearray() - while encrypted_data: - b = compat_ord(encrypted_data[0]) - _loc4_.extend([b // 16, b & 0x0f]) - encrypted_data = encrypted_data[1:] + _loc4_ = bytearray(2 * len(encrypted_data)) + for idx, val in enumerate(encrypted_data): + b = compat_ord(val) + _loc4_[2 * idx] = b // 16 + _loc4_[2 * idx + 1] = b % 16 idx = len(_loc4_) - 11 _loc4_ = _loc4_[idx:] + _loc4_[:idx] - _loc7_ = bytearray() - while _loc4_: - _loc7_.append(_loc4_[0] * 16 + _loc4_[1]) - _loc4_ = _loc4_[2:] + _loc7_ = bytearray(len(encrypted_data)) + for i in range(len(encrypted_data)): + _loc7_[i] = _loc4_[2 * i] * 16 + _loc4_[2 * i + 1] return bytes(_loc7_) @@ -117,10 +119,10 @@ class LetvIE(InfoExtractor): 'splatid': 101, 'format': 1, 'tkey': self.calc_time_key(int(time.time())), - 'domain': 'www.letv.com' + 'domain': 'www.le.com' } play_json_req = sanitized_Request( - 'http://api.letv.com/mms/out/video/playJson?' + compat_urllib_parse.urlencode(params) + 'http://api.le.com/mms/out/video/playJson?' + compat_urllib_parse.urlencode(params) ) cn_verification_proxy = self._downloader.params.get('cn_verification_proxy') if cn_verification_proxy: @@ -193,26 +195,51 @@ class LetvIE(InfoExtractor): } -class LetvTvIE(InfoExtractor): - _VALID_URL = r'http://www.letv.com/tv/(?P<id>\d+).html' +class LePlaylistIE(InfoExtractor): + _VALID_URL = r'http://[a-z]+\.le\.com/[a-z]+/(?P<id>[a-z0-9_]+)' + _TESTS = [{ - 'url': 'http://www.letv.com/tv/46177.html', + 'url': 'http://www.le.com/tv/46177.html', 'info_dict': { 'id': '46177', 'title': '美人天下', 'description': 'md5:395666ff41b44080396e59570dbac01c' }, 'playlist_count': 35 + }, { + 'url': 'http://tv.le.com/izt/wuzetian/index.html', + 'info_dict': { + 'id': 'wuzetian', + 'title': '武媚娘传奇', + 'description': 'md5:e12499475ab3d50219e5bba00b3cb248' + }, + # This playlist contains some extra videos other than the drama itself + 'playlist_mincount': 96 + }, { + 'url': 'http://tv.le.com/pzt/lswjzzjc/index.shtml', + # This series is moved to http://www.le.com/tv/10005297.html + 'only_matching': True, + }, { + 'url': 'http://www.le.com/comic/92063.html', + 'only_matching': True, + }, { + 'url': 'http://list.le.com/listn/c1009_sc532002_d2_p1_o1.html', + 'only_matching': True, }] + @classmethod + def suitable(cls, url): + return False if LeIE.suitable(url) else super(LePlaylistIE, cls).suitable(url) + def _real_extract(self, url): playlist_id = self._match_id(url) page = self._download_webpage(url, playlist_id) - media_urls = list(set(re.findall( - r'http://www.letv.com/ptv/vplay/\d+.html', page))) - entries = [self.url_result(media_url, ie='Letv') - for media_url in media_urls] + # Currently old domain names are still used in playlists + media_ids = orderedSet(re.findall( + r'<a[^>]+href="http://www\.letv\.com/ptv/vplay/(\d+)\.html', page)) + entries = [self.url_result(LeIE._URL_TEMPLATE % media_id, ie='Le') + for media_id in media_ids] title = self._html_search_meta('keywords', page, fatal=False).split('，')[0] @@ -222,31 +249,9 @@ class LetvTvIE(InfoExtractor): playlist_description=description) -class LetvPlaylistIE(LetvTvIE): - _VALID_URL = r'http://tv.letv.com/[a-z]+/(?P<id>[a-z]+)/index.s?html' - _TESTS = [{ - 'url': 'http://tv.letv.com/izt/wuzetian/index.html', - 'info_dict': { - 'id': 'wuzetian', - 'title': '武媚娘传奇', - 'description': 'md5:e12499475ab3d50219e5bba00b3cb248' - }, - # This playlist contains some extra videos other than the drama itself - 'playlist_mincount': 96 - }, { - 'url': 'http://tv.letv.com/pzt/lswjzzjc/index.shtml', - 'info_dict': { - 'id': 'lswjzzjc', - # The title should be "劲舞青春", but I can't find a simple way to - # determine the playlist title - 'title': '乐视午间自制剧场', - 'description': 'md5:b1eef244f45589a7b5b1af9ff25a4489' - }, - 'playlist_mincount': 7 - }] - - class LetvCloudIE(InfoExtractor): + # Most of *.letv.com is changed to *.le.com on 2016/01/02 + # but yuntv.letv.com is kept, so also keep the extractor name IE_DESC = '乐视云' _VALID_URL = r'https?://yuntv\.letv\.com/bcloud.html\?.+' @@ -327,7 +332,7 @@ class LetvCloudIE(InfoExtractor): formats.append({ 'url': url, 'ext': determine_ext(decoded_url), - 'format_id': int_or_none(play_url.get('vtype')), + 'format_id': str_or_none(play_url.get('vtype')), 'format_note': str_or_none(play_url.get('definition')), 'width': int_or_none(play_url.get('vwidth')), 'height': int_or_none(play_url.get('vheight')), diff --git a/youtube_dl/extractor/lifenews.py b/youtube_dl/extractor/lifenews.py index f8cbca7b3..a8fd639cc 100644 --- a/youtube_dl/extractor/lifenews.py +++ b/youtube_dl/extractor/lifenews.py @@ -20,18 +20,18 @@ class LifeNewsIE(InfoExtractor): _VALID_URL = r'http://lifenews\.ru/(?:mobile/)?(?P<section>news|video)/(?P<id>\d+)' _TESTS = [{ - 'url': 'http://lifenews.ru/news/126342', - 'md5': 'e1b50a5c5fb98a6a544250f2e0db570a', + # single video embedded via video/source + 'url': 'http://lifenews.ru/news/98736', + 'md5': '77c95eaefaca216e32a76a343ad89d23', 'info_dict': { - 'id': '126342', + 'id': '98736', 'ext': 'mp4', - 'title': 'МВД разыскивает мужчин, оставивших в IKEA сумку с автоматом', - 'description': 'Камеры наблюдения гипермаркета зафиксировали троих мужчин, спрятавших оружейный арсенал в камере хранения.', - 'thumbnail': 're:http://.*\.jpg', - 'upload_date': '20140130', + 'title': 'Мужчина нашел дома архив оборонного завода', + 'description': 'md5:3b06b1b39b5e2bea548e403d99b8bf26', + 'upload_date': '20120805', } }, { - # video in <iframe> + # single video embedded via iframe 'url': 'http://lifenews.ru/news/152125', 'md5': '77d19a6f0886cd76bdbf44b4d971a273', 'info_dict': { @@ -42,15 +42,33 @@ class LifeNewsIE(InfoExtractor): 'upload_date': '20150402', } }, { + # two videos embedded via iframe 'url': 'http://lifenews.ru/news/153461', - 'md5': '9b6ef8bc0ffa25aebc8bdb40d89ab795', 'info_dict': { 'id': '153461', - 'ext': 'mp4', 'title': 'В Москве спасли потерявшегося медвежонка, который спрятался на дереве', 'description': 'Маленький хищник не смог найти дорогу домой и обрел временное убежище на тополе недалеко от жилого массива, пока его не нашла соседская собака.', 'upload_date': '20150505', - } + }, + 'playlist': [{ + 'md5': '9b6ef8bc0ffa25aebc8bdb40d89ab795', + 'info_dict': { + 'id': '153461-video1', + 'ext': 'mp4', + 'title': 'В Москве спасли потерявшегося медвежонка, который спрятался на дереве (Видео 1)', + 'description': 'Маленький хищник не смог найти дорогу домой и обрел временное убежище на тополе недалеко от жилого массива, пока его не нашла соседская собака.', + 'upload_date': '20150505', + }, + }, { + 'md5': 'ebb3bf3b1ce40e878d0d628e93eb0322', + 'info_dict': { + 'id': '153461-video2', + 'ext': 'mp4', + 'title': 'В Москве спасли потерявшегося медвежонка, который спрятался на дереве (Видео 2)', + 'description': 'Маленький хищник не смог найти дорогу домой и обрел временное убежище на тополе недалеко от жилого массива, пока его не нашла соседская собака.', + 'upload_date': '20150505', + }, + }], }, { 'url': 'http://lifenews.ru/video/13035', 'only_matching': True, @@ -65,10 +83,14 @@ class LifeNewsIE(InfoExtractor): 'http://lifenews.ru/%s/%s' % (section, video_id), video_id, 'Downloading page') - videos = re.findall(r'<video.*?poster="(?P<poster>[^"]+)".*?src="(?P<video>[^"]+)".*?></video>', webpage) - iframe_link = self._html_search_regex( - '<iframe[^>]+src=["\']([^"\']+)["\']', webpage, 'iframe link', default=None) - if not videos and not iframe_link: + video_urls = re.findall( + r'<video[^>]+><source[^>]+src=["\'](.+?)["\']', webpage) + + iframe_links = re.findall( + r'<iframe[^>]+src=["\']((?:https?:)?//embed\.life\.ru/embed/.+?)["\']', + webpage) + + if not video_urls and not iframe_links: raise ExtractorError('No media links available for %s' % video_id) title = remove_end( @@ -95,31 +117,44 @@ class LifeNewsIE(InfoExtractor): 'upload_date': upload_date, } - def make_entry(video_id, media, video_number=None): + def make_entry(video_id, video_url, index=None): cur_info = dict(common_info) cur_info.update({ - 'id': video_id, - 'url': media[1], - 'thumbnail': media[0], - 'title': title if video_number is None else '%s-video%s' % (title, video_number), + 'id': video_id if not index else '%s-video%s' % (video_id, index), + 'url': video_url, + 'title': title if not index else '%s (Видео %s)' % (title, index), }) return cur_info - if iframe_link: - iframe_link = self._proto_relative_url(iframe_link, 'http:') - cur_info = dict(common_info) - cur_info.update({ - '_type': 'url_transparent', - 'id': video_id, - 'title': title, - 'url': iframe_link, - }) + def make_video_entry(video_id, video_url, index=None): + video_url = compat_urlparse.urljoin(url, video_url) + return make_entry(video_id, video_url, index) + + def make_iframe_entry(video_id, video_url, index=None): + video_url = self._proto_relative_url(video_url, 'http:') + cur_info = make_entry(video_id, video_url, index) + cur_info['_type'] = 'url_transparent' return cur_info - if len(videos) == 1: - return make_entry(video_id, videos[0]) - else: - return [make_entry(video_id, media, video_number + 1) for video_number, media in enumerate(videos)] + if len(video_urls) == 1 and not iframe_links: + return make_video_entry(video_id, video_urls[0]) + + if len(iframe_links) == 1 and not video_urls: + return make_iframe_entry(video_id, iframe_links[0]) + + entries = [] + + if video_urls: + for num, video_url in enumerate(video_urls, 1): + entries.append(make_video_entry(video_id, video_url, num)) + + if iframe_links: + for num, iframe_link in enumerate(iframe_links, len(video_urls) + 1): + entries.append(make_iframe_entry(video_id, iframe_link, num)) + + playlist = common_info.copy() + playlist.update(self.playlist_result(entries, video_id, title, description)) + return playlist class LifeEmbedIE(InfoExtractor): diff --git a/youtube_dl/extractor/livestream.py b/youtube_dl/extractor/livestream.py index 38fb3d9e4..eada7c299 100644 --- a/youtube_dl/extractor/livestream.py +++ b/youtube_dl/extractor/livestream.py @@ -14,6 +14,7 @@ from ..utils import ( xpath_with_ns, xpath_text, orderedSet, + update_url_query, int_or_none, float_or_none, parse_iso8601, @@ -64,7 +65,7 @@ class LivestreamIE(InfoExtractor): def _parse_smil_formats(self, smil, smil_url, video_id, namespace=None, f4m_params=None, transform_rtmp_url=None): base_ele = find_xpath_attr( smil, self._xpath_ns('.//meta', namespace), 'name', 'httpBase') - base = base_ele.get('content') if base_ele else 'http://livestreamvod-f.akamaihd.net/' + base = base_ele.get('content') if base_ele is not None else 'http://livestreamvod-f.akamaihd.net/' formats = [] video_nodes = smil.findall(self._xpath_ns('.//video', namespace)) @@ -72,7 +73,10 @@ class LivestreamIE(InfoExtractor): for vn in video_nodes: tbr = int_or_none(vn.attrib.get('system-bitrate'), 1000) furl = ( - '%s%s?v=3.0.3&fp=WIN%%2014,0,0,145' % (base, vn.attrib['src'])) + update_url_query(compat_urlparse.urljoin(base, vn.attrib['src']), { + 'v': '3.0.3', + 'fp': 'WIN% 14,0,0,145', + })) if 'clipBegin' in vn.attrib: furl += '&ssek=' + vn.attrib['clipBegin'] formats.append({ diff --git a/youtube_dl/extractor/makerschannel.py b/youtube_dl/extractor/makerschannel.py new file mode 100644 index 000000000..f5d00e61d --- /dev/null +++ b/youtube_dl/extractor/makerschannel.py @@ -0,0 +1,40 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + + +class MakersChannelIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?makerschannel\.com/.*(?P<id_type>video|production)_id=(?P<id>[0-9]+)' + _TEST = { + 'url': 'http://makerschannel.com/en/zoomin/community-highlights?video_id=849', + 'md5': '624a512c6969236b5967bf9286345ad1', + 'info_dict': { + 'id': '849', + 'ext': 'mp4', + 'title': 'Landing a bus on a plane is an epic win', + 'uploader': 'ZoomIn', + 'description': 'md5:cd9cca2ea7b69b78be81d07020c97139', + } + } + + def _real_extract(self, url): + id_type, url_id = re.match(self._VALID_URL, url).groups() + webpage = self._download_webpage(url, url_id) + video_data = self._html_search_regex(r'<div([^>]+data-%s-id="%s"[^>]+)>' % (id_type, url_id), webpage, 'video data') + + def extract_data_val(attr, fatal=False): + return self._html_search_regex(r'data-%s\s*=\s*"([^"]+)"' % attr, video_data, attr, fatal=fatal) + minoto_id = self._search_regex(r'/id/([a-zA-Z0-9]+)', extract_data_val('video-src', True), 'minoto id') + + return { + '_type': 'url_transparent', + 'url': 'minoto:%s' % minoto_id, + 'id': extract_data_val('video-id', True), + 'title': extract_data_val('title', True), + 'description': extract_data_val('description'), + 'thumbnail': extract_data_val('image'), + 'uploader': extract_data_val('channel'), + } diff --git a/youtube_dl/extractor/mdr.py b/youtube_dl/extractor/mdr.py index 425fc9e2a..2338e7f96 100644 --- a/youtube_dl/extractor/mdr.py +++ b/youtube_dl/extractor/mdr.py @@ -14,7 +14,7 @@ from ..utils import ( class MDRIE(InfoExtractor): IE_DESC = 'MDR.DE and KiKA' - _VALID_URL = r'https?://(?:www\.)?(?:mdr|kika)\.de/(?:.*)/[a-z]+(?P<id>\d+)(?:_.+?)?\.html' + _VALID_URL = r'https?://(?:www\.)?(?:mdr|kika)\.de/(?:.*)/[a-z]+-?(?P<id>\d+)(?:_.+?)?\.html' _TESTS = [{ # MDR regularly deletes its videos @@ -60,6 +60,9 @@ class MDRIE(InfoExtractor): }, { 'url': 'http://www.kika.de/sendungen/einzelsendungen/weihnachtsprogramm/einzelsendung2534.html', 'only_matching': True, + }, { + 'url': 'http://www.mdr.de/mediathek/mdr-videos/a/video-1334.html', + 'only_matching': True, }] def _real_extract(self, url): @@ -68,8 +71,8 @@ class MDRIE(InfoExtractor): webpage = self._download_webpage(url, video_id) data_url = self._search_regex( - r'dataURL\s*:\s*(["\'])(?P<url>/.+/(?:video|audio)[0-9]+-avCustom\.xml)\1', - webpage, 'data url', group='url') + r'(?:dataURL|playerXml(?:["\'])?)\s*:\s*(["\'])(?P<url>\\?/.+/(?:video|audio)-?[0-9]+-avCustom\.xml)\1', + webpage, 'data url', default=None, group='url').replace('\/', '/') doc = self._download_xml( compat_urlparse.urljoin(url, data_url), video_id) diff --git a/youtube_dl/extractor/minoto.py b/youtube_dl/extractor/minoto.py new file mode 100644 index 000000000..959a10589 --- /dev/null +++ b/youtube_dl/extractor/minoto.py @@ -0,0 +1,56 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import int_or_none + + +class MinotoIE(InfoExtractor): + _VALID_URL = r'(?:minoto:|https?://(?:play|iframe|embed)\.minoto-video\.com/(?P<player_id>[0-9]+)/)(?P<id>[a-zA-Z0-9]+)' + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + player_id = mobj.group('player_id') or '1' + video_id = mobj.group('id') + video_data = self._download_json('http://play.minoto-video.com/%s/%s.js' % (player_id, video_id), video_id) + video_metadata = video_data['video-metadata'] + formats = [] + for fmt in video_data['video-files']: + fmt_url = fmt.get('url') + if not fmt_url: + continue + container = fmt.get('container') + if container == 'hls': + formats.extend(fmt_url, video_id, 'mp4', m3u8_id='hls', fatal=False) + else: + fmt_profile = fmt.get('profile') or {} + f = { + 'format_id': fmt_profile.get('name-short'), + 'format_note': fmt_profile.get('name'), + 'url': fmt_url, + 'container': container, + 'tbr': int_or_none(fmt.get('bitrate')), + 'filesize': int_or_none(fmt.get('filesize')), + 'width': int_or_none(fmt.get('width')), + 'height': int_or_none(fmt.get('height')), + } + codecs = fmt.get('codecs') + if codecs: + codecs = codecs.split(',') + if len(codecs) == 2: + f.update({ + 'vcodec': codecs[0], + 'acodec': codecs[1], + }) + formats.append(f) + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': video_metadata['title'], + 'description': video_metadata.get('description'), + 'thumbnail': video_metadata.get('video-poster', {}).get('url'), + 'formats': formats, + } diff --git a/youtube_dl/extractor/mit.py b/youtube_dl/extractor/mit.py index 29ca45778..819c1b90b 100644 --- a/youtube_dl/extractor/mit.py +++ b/youtube_dl/extractor/mit.py @@ -99,7 +99,7 @@ class OCWMITIE(InfoExtractor): 'url': 'http://ocw.mit.edu/courses/electrical-engineering-and-computer-science/6-041-probabilistic-systems-analysis-and-applied-probability-fall-2010/video-lectures/lecture-7-multiple-variables-expectations-independence/', 'info_dict': { 'id': 'EObHWIEKGjA', - 'ext': 'mp4', + 'ext': 'webm', 'title': 'Lecture 7: Multiple Discrete Random Variables: Expectations, Conditioning, Independence', 'description': 'In this lecture, the professor discussed multiple random variables, expectations, and binomial distribution.', 'upload_date': '20121109', diff --git a/youtube_dl/extractor/mixcloud.py b/youtube_dl/extractor/mixcloud.py index c2b7ed9ab..101497118 100644 --- a/youtube_dl/extractor/mixcloud.py +++ b/youtube_dl/extractor/mixcloud.py @@ -7,6 +7,7 @@ from ..compat import compat_urllib_parse_unquote from ..utils import ( ExtractorError, HEADRequest, + parse_count, str_to_int, ) @@ -85,8 +86,8 @@ class MixcloudIE(InfoExtractor): uploader_id = self._search_regex( r'\s+"profile": "([^"]+)",', webpage, 'uploader id', fatal=False) description = self._og_search_description(webpage) - like_count = str_to_int(self._search_regex( - r'\bbutton-favorite\b[^>]+m-ajax-toggle-count="([^"]+)"', + like_count = parse_count(self._search_regex( + r'\bbutton-favorite[^>]+>.*?<span[^>]+class=["\']toggle-number[^>]+>\s*([^<]+)', webpage, 'like count', fatal=False)) view_count = str_to_int(self._search_regex( [r'<meta itemprop="interactionCount" content="UserPlays:([0-9]+)"', diff --git a/youtube_dl/extractor/motherless.py b/youtube_dl/extractor/motherless.py index 97d5da626..0b4787c1d 100644 --- a/youtube_dl/extractor/motherless.py +++ b/youtube_dl/extractor/motherless.py @@ -5,6 +5,7 @@ import re from .common import InfoExtractor from ..utils import ( + ExtractorError, str_to_int, unified_strdate, ) @@ -12,55 +13,62 @@ from ..utils import ( class MotherlessIE(InfoExtractor): _VALID_URL = r'http://(?:www\.)?motherless\.com/(?:g/[a-z0-9_]+/)?(?P<id>[A-Z0-9]+)' - _TESTS = [ - { - 'url': 'http://motherless.com/AC3FFE1', - 'md5': '310f62e325a9fafe64f68c0bccb6e75f', - 'info_dict': { - 'id': 'AC3FFE1', - 'ext': 'mp4', - 'title': 'Fucked in the ass while playing PS3', - 'categories': ['Gaming', 'anal', 'reluctant', 'rough', 'Wife'], - 'upload_date': '20100913', - 'uploader_id': 'famouslyfuckedup', - 'thumbnail': 're:http://.*\.jpg', - 'age_limit': 18, - } - }, - { - 'url': 'http://motherless.com/532291B', - 'md5': 'bc59a6b47d1f958e61fbd38a4d31b131', - 'info_dict': { - 'id': '532291B', - 'ext': 'mp4', - 'title': 'Amazing girl playing the omegle game, PERFECT!', - 'categories': ['Amateur', 'webcam', 'omegle', 'pink', 'young', 'masturbate', 'teen', 'game', 'hairy'], - 'upload_date': '20140622', - 'uploader_id': 'Sulivana7x', - 'thumbnail': 're:http://.*\.jpg', - 'age_limit': 18, - } + _TESTS = [{ + 'url': 'http://motherless.com/AC3FFE1', + 'md5': '310f62e325a9fafe64f68c0bccb6e75f', + 'info_dict': { + 'id': 'AC3FFE1', + 'ext': 'mp4', + 'title': 'Fucked in the ass while playing PS3', + 'categories': ['Gaming', 'anal', 'reluctant', 'rough', 'Wife'], + 'upload_date': '20100913', + 'uploader_id': 'famouslyfuckedup', + 'thumbnail': 're:http://.*\.jpg', + 'age_limit': 18, + } + }, { + 'url': 'http://motherless.com/532291B', + 'md5': 'bc59a6b47d1f958e61fbd38a4d31b131', + 'info_dict': { + 'id': '532291B', + 'ext': 'mp4', + 'title': 'Amazing girl playing the omegle game, PERFECT!', + 'categories': ['Amateur', 'webcam', 'omegle', 'pink', 'young', 'masturbate', 'teen', + 'game', 'hairy'], + 'upload_date': '20140622', + 'uploader_id': 'Sulivana7x', + 'thumbnail': 're:http://.*\.jpg', + 'age_limit': 18, }, - { - 'url': 'http://motherless.com/g/cosplay/633979F', - 'md5': '0b2a43f447a49c3e649c93ad1fafa4a0', - 'info_dict': { - 'id': '633979F', - 'ext': 'mp4', - 'title': 'Turtlette', - 'categories': ['superheroine heroine superher'], - 'upload_date': '20140827', - 'uploader_id': 'shade0230', - 'thumbnail': 're:http://.*\.jpg', - 'age_limit': 18, - } + 'skip': '404', + }, { + 'url': 'http://motherless.com/g/cosplay/633979F', + 'md5': '0b2a43f447a49c3e649c93ad1fafa4a0', + 'info_dict': { + 'id': '633979F', + 'ext': 'mp4', + 'title': 'Turtlette', + 'categories': ['superheroine heroine superher'], + 'upload_date': '20140827', + 'uploader_id': 'shade0230', + 'thumbnail': 're:http://.*\.jpg', + 'age_limit': 18, } - ] + }, { + # no keywords + 'url': 'http://motherless.com/8B4BBC1', + 'only_matching': True, + }] def _real_extract(self, url): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) + if any(p in webpage for p in ( + '<title>404 - MOTHERLESS.COM<', + ">The page you're looking for cannot be found.<")): + raise ExtractorError('Video %s does not exist' % video_id, expected=True) + title = self._html_search_regex( r'id="view-upload-title">\s+([^<]+)<', webpage, 'title') video_url = self._html_search_regex( @@ -86,7 +94,7 @@ class MotherlessIE(InfoExtractor): r'"thumb-member-username">\s+<a href="/m/([^"]+)"', webpage, 'uploader_id') - categories = self._html_search_meta('keywords', webpage) + categories = self._html_search_meta('keywords', webpage, default=None) if categories: categories = [cat.strip() for cat in categories.split(',')] diff --git a/youtube_dl/extractor/mtv.py b/youtube_dl/extractor/mtv.py index e8bb527b8..ed068365d 100644 --- a/youtube_dl/extractor/mtv.py +++ b/youtube_dl/extractor/mtv.py @@ -11,6 +11,7 @@ from ..utils import ( ExtractorError, find_xpath_attr, fix_xml_ampersands, + float_or_none, HEADRequest, sanitized_Request, unescapeHTML, @@ -110,7 +111,8 @@ class MTVServicesInfoExtractor(InfoExtractor): uri = itemdoc.find('guid').text video_id = self._id_from_uri(uri) self.report_extraction(video_id) - mediagen_url = itemdoc.find('%s/%s' % (_media_xml_tag('group'), _media_xml_tag('content'))).attrib['url'] + content_el = itemdoc.find('%s/%s' % (_media_xml_tag('group'), _media_xml_tag('content'))) + mediagen_url = content_el.attrib['url'] # Remove the templates, like &device={device} mediagen_url = re.sub(r'&[^=]*?={.*?}(?=(&|$))', '', mediagen_url) if 'acceptMethods' not in mediagen_url: @@ -165,6 +167,7 @@ class MTVServicesInfoExtractor(InfoExtractor): 'id': video_id, 'thumbnail': self._get_thumbnail_url(uri, itemdoc), 'description': description, + 'duration': float_or_none(content_el.attrib.get('duration')), } def _get_feed_query(self, uri): diff --git a/youtube_dl/extractor/nba.py b/youtube_dl/extractor/nba.py index a071378b6..3e2b3e599 100644 --- a/youtube_dl/extractor/nba.py +++ b/youtube_dl/extractor/nba.py @@ -1,18 +1,26 @@ from __future__ import unicode_literals +import functools +import os.path import re from .common import InfoExtractor +from ..compat import ( + compat_urllib_parse, + compat_urlparse, +) from ..utils import ( - parse_duration, int_or_none, + OnDemandPagedList, + parse_duration, + remove_start, xpath_text, xpath_attr, ) class NBAIE(InfoExtractor): - _VALID_URL = r'https?://(?:watch\.|www\.)?nba\.com/(?P<path>(?:[^/]+/)?video/(?P<id>[^?]*?))/?(?:/index\.html)?(?:\?.*)?$' + _VALID_URL = r'https?://(?:watch\.|www\.)?nba\.com/(?P<path>(?:[^/]+/)+(?P<id>[^?]*?))/?(?:/index\.html)?(?:\?.*)?$' _TESTS = [{ 'url': 'http://www.nba.com/video/games/nets/2012/12/04/0021200253-okc-bkn-recap.nba/index.html', 'md5': '9e7729d3010a9c71506fd1248f74e4f4', @@ -44,14 +52,101 @@ class NBAIE(InfoExtractor): 'timestamp': 1432134543, 'upload_date': '20150520', } + }, { + 'url': 'http://www.nba.com/clippers/news/doc-rivers-were-not-trading-blake', + 'info_dict': { + 'id': '1455672027478-Doc_Feb16_720', + 'ext': 'mp4', + 'title': 'Practice: Doc Rivers - 2/16/16', + 'description': 'Head Coach Doc Rivers addresses the media following practice.', + 'upload_date': '20160217', + 'timestamp': 1455672000, + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + }, { + 'url': 'http://www.nba.com/timberwolves/wiggins-shootaround#', + 'info_dict': { + 'id': 'timberwolves', + 'title': 'Shootaround Access - Dec. 12 | Andrew Wiggins', + }, + 'playlist_count': 30, + 'params': { + # Download the whole playlist takes too long time + 'playlist_items': '1-30', + }, + }, { + 'url': 'http://www.nba.com/timberwolves/wiggins-shootaround#', + 'info_dict': { + 'id': 'Wigginsmp4', + 'ext': 'mp4', + 'title': 'Shootaround Access - Dec. 12 | Andrew Wiggins', + 'description': 'Wolves rookie Andrew Wiggins addresses the media after Friday\'s shootaround.', + 'upload_date': '20141212', + 'timestamp': 1418418600, + }, + 'params': { + 'noplaylist': True, + # m3u8 download + 'skip_download': True, + }, }] + _PAGE_SIZE = 30 + + def _fetch_page(self, team, video_id, page): + search_url = 'http://searchapp2.nba.com/nba-search/query.jsp?' + compat_urllib_parse.urlencode({ + 'type': 'teamvideo', + 'start': page * self._PAGE_SIZE + 1, + 'npp': (page + 1) * self._PAGE_SIZE + 1, + 'sort': 'recent', + 'output': 'json', + 'site': team, + }) + results = self._download_json( + search_url, video_id, note='Download page %d of playlist data' % page)['results'][0] + for item in results: + yield self.url_result(compat_urlparse.urljoin('http://www.nba.com/', item['url'])) + + def _extract_playlist(self, orig_path, video_id, webpage): + team = orig_path.split('/')[0] + + if self._downloader.params.get('noplaylist'): + self.to_screen('Downloading just video because of --no-playlist') + video_path = self._search_regex( + r'nbaVideoCore\.firstVideo\s*=\s*\'([^\']+)\';', webpage, 'video path') + video_url = 'http://www.nba.com/%s/video/%s' % (team, video_path) + return self.url_result(video_url) + + self.to_screen('Downloading playlist - add --no-playlist to just download video') + playlist_title = self._og_search_title(webpage, fatal=False) + entries = OnDemandPagedList( + functools.partial(self._fetch_page, team, video_id), + self._PAGE_SIZE, use_cache=True) + + return self.playlist_result(entries, team, playlist_title) + def _real_extract(self, url): path, video_id = re.match(self._VALID_URL, url).groups() + orig_path = path if path.startswith('nba/'): path = path[3:] + + if 'video/' not in path: + webpage = self._download_webpage(url, video_id) + path = remove_start(self._search_regex(r'data-videoid="([^"]+)"', webpage, 'video id'), '/') + + if path == '{{id}}': + return self._extract_playlist(orig_path, video_id, webpage) + + # See prepareContentId() of pkgCvp.js + if path.startswith('video/teams'): + path = 'video/channels/proxy/' + path[6:] + video_info = self._download_xml('http://www.nba.com/%s.xml' % path, video_id) - video_id = xpath_text(video_info, 'slug') + video_id = os.path.splitext(xpath_text(video_info, 'slug'))[0] title = xpath_text(video_info, 'headline') description = xpath_text(video_info, 'description') duration = parse_duration(xpath_text(video_info, 'length')) diff --git a/youtube_dl/extractor/nrk.py b/youtube_dl/extractor/nrk.py index a126f5054..3b21fbd4d 100644 --- a/youtube_dl/extractor/nrk.py +++ b/youtube_dl/extractor/nrk.py @@ -4,7 +4,10 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import compat_urlparse +from ..compat import ( + compat_urlparse, + compat_urllib_parse_unquote, +) from ..utils import ( determine_ext, ExtractorError, @@ -87,7 +90,7 @@ class NRKIE(InfoExtractor): class NRKPlaylistIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?nrk\.no/(?!video)(?:[^/]+/)+(?P<id>[^/]+)' + _VALID_URL = r'https?://(?:www\.)?nrk\.no/(?!video|skole)(?:[^/]+/)+(?P<id>[^/]+)' _TESTS = [{ 'url': 'http://www.nrk.no/troms/gjenopplev-den-historiske-solformorkelsen-1.12270763', @@ -126,6 +129,37 @@ class NRKPlaylistIE(InfoExtractor): entries, playlist_id, playlist_title, playlist_description) +class NRKSkoleIE(InfoExtractor): + IE_DESC = 'NRK Skole' + _VALID_URL = r'https?://(?:www\.)?nrk\.no/skole/klippdetalj?.*\btopic=(?P<id>[^/?#&]+)' + + _TESTS = [{ + 'url': 'http://nrk.no/skole/klippdetalj?topic=nrk:klipp/616532', + 'md5': '04cd85877cc1913bce73c5d28a47e00f', + 'info_dict': { + 'id': '6021', + 'ext': 'flv', + 'title': 'Genetikk og eneggede tvillinger', + 'description': 'md5:3aca25dcf38ec30f0363428d2b265f8d', + 'duration': 399, + }, + }, { + 'url': 'http://www.nrk.no/skole/klippdetalj?topic=nrk%3Aklipp%2F616532#embed', + 'only_matching': True, + }, { + 'url': 'http://www.nrk.no/skole/klippdetalj?topic=urn:x-mediadb:21379', + 'only_matching': True, + }] + + def _real_extract(self, url): + video_id = compat_urllib_parse_unquote(self._match_id(url)) + + webpage = self._download_webpage(url, video_id) + + nrk_id = self._search_regex(r'data-nrk-id=["\'](\d+)', webpage, 'nrk id') + return self.url_result('nrk:%s' % nrk_id) + + class NRKTVIE(InfoExtractor): IE_DESC = 'NRK TV and NRK Radio' _VALID_URL = r'(?P<baseurl>https?://(?:tv|radio)\.nrk(?:super)?\.no/)(?:serie/[^/]+|program)/(?P<id>[a-zA-Z]{4}\d{8})(?:/\d{2}-\d{2}-\d{4})?(?:#del=(?P<part_id>\d+))?' diff --git a/youtube_dl/extractor/pbs.py b/youtube_dl/extractor/pbs.py index cca012953..f43e3a146 100644 --- a/youtube_dl/extractor/pbs.py +++ b/youtube_dl/extractor/pbs.py @@ -338,6 +338,21 @@ class PBSIE(InfoExtractor): }, }, { + # Serves hd only via wigget/partnerplayer page + 'url': 'http://www.pbs.org/video/2365641075/', + 'info_dict': { + 'id': '2365641075', + 'ext': 'mp4', + 'title': 'FRONTLINE - Netanyahu at War', + 'duration': 6852, + 'thumbnail': 're:^https?://.*\.jpg$', + 'formats': 'mincount:8', + }, + 'params': { + 'skip_download': True, # requires ffmpeg + }, + }, + { 'url': 'http://player.pbs.org/widget/partnerplayer/2365297708/?start=0&end=0&chapterbar=false&endscreen=false&topbar=true', 'only_matching': True, }, @@ -437,34 +452,54 @@ class PBSIE(InfoExtractor): for vid_id in video_id] return self.playlist_result(entries, display_id) + info = None + redirects = [] + redirect_urls = set() + + def extract_redirect_urls(info): + for encoding_name in ('recommended_encoding', 'alternate_encoding'): + redirect = info.get(encoding_name) + if not redirect: + continue + redirect_url = redirect.get('url') + if redirect_url and redirect_url not in redirect_urls: + redirects.append(redirect) + redirect_urls.add(redirect_url) + try: - info = self._download_json( + video_info = self._download_json( 'http://player.pbs.org/videoInfo/%s?format=json&type=partner' % video_id, display_id, 'Downloading video info JSON') + extract_redirect_urls(video_info) + info = video_info except ExtractorError as e: + # videoInfo API may not work for some videos if not isinstance(e.cause, compat_HTTPError) or e.cause.code != 404: raise - # videoInfo API may not work for some videos, fallback to portalplayer API + + # Player pages may also serve different qualities + for page in ('widget/partnerplayer', 'portalplayer'): player = self._download_webpage( - 'http://player.pbs.org/portalplayer/%s' % video_id, display_id) - info = self._parse_json( - self._search_regex( - r'(?s)PBS\.videoData\s*=\s*({.+?});\n', - player, 'video data', default='{}'), - display_id, transform_source=js_to_json, fatal=False) + 'http://player.pbs.org/%s/%s' % (page, video_id), + display_id, 'Downloading %s page' % page, fatal=False) + if player: + video_info = self._parse_json( + self._search_regex( + r'(?s)PBS\.videoData\s*=\s*({.+?});\n', + player, '%s video data' % page, default='{}'), + display_id, transform_source=js_to_json, fatal=False) + if video_info: + extract_redirect_urls(video_info) + if not info: + info = video_info formats = [] - for encoding_name in ('recommended_encoding', 'alternate_encoding'): - redirect = info.get(encoding_name) - if not redirect: - continue - redirect_url = redirect.get('url') - if not redirect_url: - continue + for num, redirect in enumerate(redirects): + redirect_id = redirect.get('eeid') redirect_info = self._download_json( - redirect_url + '?format=json', display_id, - 'Downloading %s video url info' % encoding_name) + '%s?format=json' % redirect['url'], display_id, + 'Downloading %s video url info' % (redirect_id or num)) if redirect_info['status'] == 'error': raise ExtractorError( @@ -483,8 +518,9 @@ class PBSIE(InfoExtractor): else: formats.append({ 'url': format_url, - 'format_id': redirect.get('eeid'), + 'format_id': redirect_id, }) + self._remove_duplicate_formats(formats) self._sort_formats(formats) rating_str = info.get('rating') diff --git a/youtube_dl/extractor/pyvideo.py b/youtube_dl/extractor/pyvideo.py index 6d5732d45..30a5f2de4 100644 --- a/youtube_dl/extractor/pyvideo.py +++ b/youtube_dl/extractor/pyvideo.py @@ -12,14 +12,14 @@ class PyvideoIE(InfoExtractor): _TESTS = [ { 'url': 'http://pyvideo.org/video/1737/become-a-logging-expert-in-30-minutes', - 'md5': 'de317418c8bc76b1fd8633e4f32acbc6', + 'md5': '520915673e53a5c5d487c36e0c4d85b5', 'info_dict': { 'id': '24_4WWkSmNo', - 'ext': 'mp4', + 'ext': 'webm', 'title': 'Become a logging expert in 30 minutes', 'description': 'md5:9665350d466c67fb5b1598de379021f7', 'upload_date': '20130320', - 'uploader': 'NextDayVideo', + 'uploader': 'Next Day Video', 'uploader_id': 'NextDayVideo', }, 'add_ie': ['Youtube'], diff --git a/youtube_dl/extractor/revision3.py b/youtube_dl/extractor/revision3.py index b1b8800b9..99979ebe1 100644 --- a/youtube_dl/extractor/revision3.py +++ b/youtube_dl/extractor/revision3.py @@ -19,7 +19,7 @@ class Revision3IE(InfoExtractor): 'url': 'http://www.revision3.com/technobuffalo/5-google-predictions-for-2016', 'md5': 'd94a72d85d0a829766de4deb8daaf7df', 'info_dict': { - 'id': '73034', + 'id': '71089', 'display_id': 'technobuffalo/5-google-predictions-for-2016', 'ext': 'webm', 'title': '5 Google Predictions for 2016', @@ -31,6 +31,7 @@ class Revision3IE(InfoExtractor): 'uploader_id': 'technobuffalo', } }, { + # Show 'url': 'http://testtube.com/brainstuff', 'info_dict': { 'id': '251', @@ -41,7 +42,7 @@ class Revision3IE(InfoExtractor): }, { 'url': 'https://testtube.com/dnews/5-weird-ways-plants-can-eat-animals?utm_source=FB&utm_medium=DNews&utm_campaign=DNewsSocial', 'info_dict': { - 'id': '60163', + 'id': '58227', 'display_id': 'dnews/5-weird-ways-plants-can-eat-animals', 'duration': 275, 'ext': 'webm', @@ -52,18 +53,72 @@ class Revision3IE(InfoExtractor): 'uploader': 'DNews', 'uploader_id': 'dnews', }, + }, { + 'url': 'http://testtube.com/tt-editors-picks/the-israel-palestine-conflict-explained-in-ten-min', + 'info_dict': { + 'id': '71618', + 'ext': 'mp4', + 'display_id': 'tt-editors-picks/the-israel-palestine-conflict-explained-in-ten-min', + 'title': 'The Israel-Palestine Conflict Explained in Ten Minutes', + 'description': 'If you\'d like to learn about the struggle between Israelis and Palestinians, this video is a great place to start', + 'uploader': 'Editors\' Picks', + 'uploader_id': 'tt-editors-picks', + 'timestamp': 1453309200, + 'upload_date': '20160120', + }, + 'add_ie': ['Youtube'], + }, { + # Tag + 'url': 'http://testtube.com/tech-news', + 'info_dict': { + 'id': '21018', + 'title': 'tech news', + }, + 'playlist_mincount': 9, }] _PAGE_DATA_TEMPLATE = 'http://www.%s/apiProxy/ddn/%s?domain=%s' _API_KEY = 'ba9c741bce1b9d8e3defcc22193f3651b8867e62' def _real_extract(self, url): domain, display_id = re.match(self._VALID_URL, url).groups() + site = domain.split('.')[0] page_info = self._download_json( self._PAGE_DATA_TEMPLATE % (domain, display_id, domain), display_id) - if page_info['data']['type'] == 'episode': - episode_data = page_info['data'] - video_id = compat_str(episode_data['video']['data']['id']) + page_data = page_info['data'] + page_type = page_data['type'] + if page_type in ('episode', 'embed'): + show_data = page_data['show']['data'] + page_id = compat_str(page_data['id']) + video_id = compat_str(page_data['video']['data']['id']) + + preference = qualities(['mini', 'small', 'medium', 'large']) + thumbnails = [{ + 'url': image_url, + 'id': image_id, + 'preference': preference(image_id) + } for image_id, image_url in page_data.get('images', {}).items()] + + info = { + 'id': page_id, + 'display_id': display_id, + 'title': unescapeHTML(page_data['name']), + 'description': unescapeHTML(page_data.get('summary')), + 'timestamp': parse_iso8601(page_data.get('publishTime'), ' '), + 'author': page_data.get('author'), + 'uploader': show_data.get('name'), + 'uploader_id': show_data.get('slug'), + 'thumbnails': thumbnails, + 'extractor_key': site, + } + + if page_type == 'embed': + info.update({ + '_type': 'url_transparent', + 'url': page_data['video']['data']['embed'], + }) + return info + video_data = self._download_json( 'http://revision3.com/api/getPlaylist.json?api_key=%s&codecs=h264,vp8,theora&video_id=%s' % (self._API_KEY, video_id), video_id)['items'][0] @@ -84,36 +139,30 @@ class Revision3IE(InfoExtractor): }) self._sort_formats(formats) - preference = qualities(['mini', 'small', 'medium', 'large']) - thumbnails = [{ - 'url': image_url, - 'id': image_id, - 'preference': preference(image_id) - } for image_id, image_url in video_data.get('images', {}).items()] - - return { - 'id': video_id, - 'display_id': display_id, + info.update({ 'title': unescapeHTML(video_data['title']), 'description': unescapeHTML(video_data.get('summary')), - 'timestamp': parse_iso8601(episode_data.get('publishTime'), ' '), - 'author': episode_data.get('author'), 'uploader': video_data.get('show', {}).get('name'), 'uploader_id': video_data.get('show', {}).get('slug'), 'duration': int_or_none(video_data.get('duration')), - 'thumbnails': thumbnails, 'formats': formats, - } + }) + return info else: - show_data = page_info['show']['data'] + list_data = page_info[page_type]['data'] episodes_data = page_info['episodes']['data'] num_episodes = page_info['meta']['totalEpisodes'] processed_episodes = 0 entries = [] page_num = 1 while True: - entries.extend([self.url_result( - 'http://%s/%s/%s' % (domain, display_id, episode['slug'])) for episode in episodes_data]) + entries.extend([{ + '_type': 'url', + 'url': 'http://%s%s' % (domain, episode['path']), + 'id': compat_str(episode['id']), + 'ie_key': 'Revision3', + 'extractor_key': site, + } for episode in episodes_data]) processed_episodes += len(episodes_data) if processed_episodes == num_episodes: break @@ -123,5 +172,5 @@ class Revision3IE(InfoExtractor): display_id)['episodes']['data'] return self.playlist_result( - entries, compat_str(show_data['id']), - show_data.get('name'), show_data.get('summary')) + entries, compat_str(list_data['id']), + list_data.get('name'), list_data.get('summary')) diff --git a/youtube_dl/extractor/rtve.py b/youtube_dl/extractor/rtve.py index 603d7bd00..8a8c5d2a0 100644 --- a/youtube_dl/extractor/rtve.py +++ b/youtube_dl/extractor/rtve.py @@ -10,6 +10,7 @@ from ..utils import ( ExtractorError, float_or_none, remove_end, + remove_start, sanitized_Request, std_headers, struct_unpack, @@ -178,14 +179,14 @@ class RTVEInfantilIE(InfoExtractor): class RTVELiveIE(InfoExtractor): IE_NAME = 'rtve.es:live' IE_DESC = 'RTVE.es live streams' - _VALID_URL = r'http://www\.rtve\.es/(?:deportes/directo|noticias|television)/(?P<id>[a-zA-Z0-9-]+)' + _VALID_URL = r'http://www\.rtve\.es/directo/(?P<id>[a-zA-Z0-9-]+)' _TESTS = [{ - 'url': 'http://www.rtve.es/noticias/directo-la-1/', + 'url': 'http://www.rtve.es/directo/la-1/', 'info_dict': { - 'id': 'directo-la-1', - 'ext': 'flv', - 'title': 're:^La 1 de TVE [0-9]{4}-[0-9]{2}-[0-9]{2}Z[0-9]{6}$', + 'id': 'la-1', + 'ext': 'mp4', + 'title': 're:^La 1 [0-9]{4}-[0-9]{2}-[0-9]{2}Z[0-9]{6}$', }, 'params': { 'skip_download': 'live stream', @@ -198,23 +199,20 @@ class RTVELiveIE(InfoExtractor): video_id = mobj.group('id') webpage = self._download_webpage(url, video_id) - player_url = self._search_regex( - r'<param name="movie" value="([^"]+)"/>', webpage, 'player URL') - title = remove_end(self._og_search_title(webpage), ' en directo') + title = remove_end(self._og_search_title(webpage), ' en directo en RTVE.es') + title = remove_start(title, 'Estoy viendo ') title += ' ' + time.strftime('%Y-%m-%dZ%H%M%S', start_time) vidplayer_id = self._search_regex( - r' id="vidplayer([0-9]+)"', webpage, 'internal video ID') - png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/default/videos/%s.png' % vidplayer_id + r'playerId=player([0-9]+)', webpage, 'internal video ID') + png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/amonet/videos/%s.png' % vidplayer_id png = self._download_webpage(png_url, video_id, 'Downloading url information') - video_url = _decrypt_url(png) + m3u8_url = _decrypt_url(png) + formats = self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4') return { 'id': video_id, - 'ext': 'flv', 'title': title, - 'url': video_url, - 'app': 'rtve-live-live?ovpfv=2.1.2', - 'player_url': player_url, - 'rtmp_live': True, + 'formats': formats, + 'is_live': True, } diff --git a/youtube_dl/extractor/safari.py b/youtube_dl/extractor/safari.py index 7de7b7273..256396bb8 100644 --- a/youtube_dl/extractor/safari.py +++ b/youtube_dl/extractor/safari.py @@ -4,14 +4,13 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from .brightcove import BrightcoveLegacyIE from ..utils import ( ExtractorError, sanitized_Request, - smuggle_url, std_headers, urlencode_postdata, + update_url_query, ) @@ -20,28 +19,30 @@ class SafariBaseIE(InfoExtractor): _SUCCESSFUL_LOGIN_REGEX = r'<a href="/accounts/logout/"[^>]*>Sign Out</a>' _NETRC_MACHINE = 'safari' - _API_BASE = 'https://www.safaribooksonline.com/api/v1/book' + _API_BASE = 'https://www.safaribooksonline.com/api/v1' _API_FORMAT = 'json' LOGGED_IN = False def _real_initialize(self): - # We only need to log in once for courses or individual videos - if not self.LOGGED_IN: - self._login() - SafariBaseIE.LOGGED_IN = True + self._login() def _login(self): + # We only need to log in once for courses or individual videos + if self.LOGGED_IN: + return + (username, password) = self._get_login_info() if username is None: - self.raise_login_required('safaribooksonline.com account is required') + return - headers = std_headers + headers = std_headers.copy() if 'Referer' not in headers: headers['Referer'] = self._LOGIN_URL + login_page_request = sanitized_Request(self._LOGIN_URL, headers=headers) login_page = self._download_webpage( - self._LOGIN_URL, None, + login_page_request, None, 'Downloading login form') csrf = self._html_search_regex( @@ -66,6 +67,8 @@ class SafariBaseIE(InfoExtractor): 'Login failed; make sure your credentials are correct and try again.', expected=True) + SafariBaseIE.LOGGED_IN = True + self.to_screen('Login successful') @@ -85,13 +88,15 @@ class SafariIE(SafariBaseIE): _TESTS = [{ 'url': 'https://www.safaribooksonline.com/library/view/hadoop-fundamentals-livelessons/9780133392838/part00.html', - 'md5': '5b0c4cc1b3c1ba15dda7344085aa5592', + 'md5': 'dcc5a425e79f2564148652616af1f2a3', 'info_dict': { - 'id': '2842601850001', + 'id': '0_qbqx90ic', 'ext': 'mp4', - 'title': 'Introduction', + 'title': 'Introduction to Hadoop Fundamentals LiveLessons', + 'timestamp': 1437758058, + 'upload_date': '20150724', + 'uploader_id': 'stork', }, - 'skip': 'Requires safaribooksonline account credentials', }, { 'url': 'https://www.safaribooksonline.com/api/v1/book/9780133392838/chapter/part00.html', 'only_matching': True, @@ -106,15 +111,30 @@ class SafariIE(SafariBaseIE): course_id = mobj.group('course_id') part = mobj.group('part') - webpage = self._download_webpage( - '%s/%s/chapter-content/%s.html' % (self._API_BASE, course_id, part), - part) + webpage = self._download_webpage(url, '%s/%s' % (course_id, part)) + reference_id = self._search_regex(r'data-reference-id="([^"]+)"', webpage, 'kaltura reference id') + partner_id = self._search_regex(r'data-partner-id="([^"]+)"', webpage, 'kaltura widget id') + ui_id = self._search_regex(r'data-ui-id="([^"]+)"', webpage, 'kaltura uiconf id') + + query = { + 'wid': '_%s' % partner_id, + 'uiconf_id': ui_id, + 'flashvars[referenceId]': reference_id, + } - bc_url = BrightcoveLegacyIE._extract_brightcove_url(webpage) - if not bc_url: - raise ExtractorError('Could not extract Brightcove URL from %s' % url, expected=True) + if self.LOGGED_IN: + kaltura_session = self._download_json( + '%s/player/kaltura_session/?reference_id=%s' % (self._API_BASE, reference_id), + course_id, 'Downloading kaltura session JSON', + 'Unable to download kaltura session JSON', fatal=False) + if kaltura_session: + session = kaltura_session.get('session') + if session: + query['flashvars[ks]'] = session - return self.url_result(smuggle_url(bc_url, {'Referer': url}), 'BrightcoveLegacy') + return self.url_result(update_url_query( + 'https://cdnapisec.kaltura.com/html5/html5lib/v2.37.1/mwEmbedFrame.php', query), + 'Kaltura') class SafariCourseIE(SafariBaseIE): @@ -140,7 +160,7 @@ class SafariCourseIE(SafariBaseIE): course_id = self._match_id(url) course_json = self._download_json( - '%s/%s/?override_format=%s' % (self._API_BASE, course_id, self._API_FORMAT), + '%s/book/%s/?override_format=%s' % (self._API_BASE, course_id, self._API_FORMAT), course_id, 'Downloading course JSON') if 'chapters' not in course_json: diff --git a/youtube_dl/extractor/screenwavemedia.py b/youtube_dl/extractor/screenwavemedia.py index 2cf210e0d..44b0bbee6 100644 --- a/youtube_dl/extractor/screenwavemedia.py +++ b/youtube_dl/extractor/screenwavemedia.py @@ -70,25 +70,27 @@ class ScreenwaveMediaIE(InfoExtractor): formats = [] for source in sources: - if source['type'] == 'hls': - formats.extend(self._extract_m3u8_formats(source['file'], video_id, ext='mp4')) + file_ = source.get('file') + if not file_: + continue + if source.get('type') == 'hls': + formats.extend(self._extract_m3u8_formats(file_, video_id, ext='mp4')) else: - file_ = source.get('file') - if not file_: - continue - format_label = source.get('label') format_id = self._search_regex( r'_(.+?)\.[^.]+$', file_, 'format id', default=None) + if not self._is_valid_url(file_, video_id, format_id or 'video'): + continue + format_label = source.get('label') height = int_or_none(self._search_regex( r'^(\d+)[pP]', format_label, 'height', default=None)) formats.append({ - 'url': source['file'], + 'url': file_, 'format_id': format_id, 'format': format_label, 'ext': source.get('type'), 'height': height, }) - self._sort_formats(formats) + self._sort_formats(formats, field_preference=('height', 'width', 'tbr', 'format_id')) return { 'id': video_id, diff --git a/youtube_dl/extractor/sexu.py b/youtube_dl/extractor/sexu.py index 6365a8779..a99b2a8e7 100644 --- a/youtube_dl/extractor/sexu.py +++ b/youtube_dl/extractor/sexu.py @@ -1,7 +1,5 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor @@ -14,7 +12,7 @@ class SexuIE(InfoExtractor): 'id': '961791', 'ext': 'mp4', 'title': 'md5:4d05a19a5fc049a63dbbaf05fb71d91b', - 'description': 'md5:c5ed8625eb386855d5a7967bd7b77a54', + 'description': 'md5:2b75327061310a3afb3fbd7d09e2e403', 'categories': list, # NSFW 'thumbnail': 're:https?://.*\.jpg$', 'age_limit': 18, @@ -25,13 +23,18 @@ class SexuIE(InfoExtractor): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - quality_arr = self._search_regex( - r'sources:\s*\[([^\]]+)\]', webpage, 'forrmat string') + jwvideo = self._parse_json( + self._search_regex(r'\.setup\(\s*({.+?})\s*\);', webpage, 'jwvideo'), + video_id) + + sources = jwvideo['sources'] + formats = [{ - 'url': fmt[0].replace('\\', ''), - 'format_id': fmt[1], - 'height': int(fmt[1][:3]), - } for fmt in re.findall(r'"file":"([^"]+)","label":"([^"]+)"', quality_arr)] + 'url': source['file'].replace('\\', ''), + 'format_id': source.get('label'), + 'height': self._search_regex( + r'^(\d+)[pP]', source.get('label', ''), 'height', default=None), + } for source in sources if source.get('file')] self._sort_formats(formats) title = self._html_search_regex( @@ -40,9 +43,7 @@ class SexuIE(InfoExtractor): description = self._html_search_meta( 'description', webpage, 'description') - thumbnail = self._html_search_regex( - r'image:\s*"([^"]+)"', - webpage, 'thumbnail', fatal=False) + thumbnail = jwvideo.get('image') categories_str = self._html_search_meta( 'keywords', webpage, 'categories') diff --git a/youtube_dl/extractor/space.py b/youtube_dl/extractor/space.py deleted file mode 100644 index ebb5d6ec0..000000000 --- a/youtube_dl/extractor/space.py +++ /dev/null @@ -1,38 +0,0 @@ -from __future__ import unicode_literals - -import re - -from .common import InfoExtractor -from .brightcove import BrightcoveLegacyIE -from ..utils import RegexNotFoundError, ExtractorError - - -class SpaceIE(InfoExtractor): - _VALID_URL = r'https?://(?:(?:www|m)\.)?space\.com/\d+-(?P<title>[^/\.\?]*?)-video\.html' - _TEST = { - 'add_ie': ['BrightcoveLegacy'], - 'url': 'http://www.space.com/23373-huge-martian-landforms-detail-revealed-by-european-probe-video.html', - 'info_dict': { - 'id': '2780937028001', - 'ext': 'mp4', - 'title': 'Huge Martian Landforms\' Detail Revealed By European Probe | Video', - 'description': 'md5:db81cf7f3122f95ed234b631a6ea1e61', - 'uploader': 'TechMedia Networks', - }, - } - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - title = mobj.group('title') - webpage = self._download_webpage(url, title) - try: - # Some videos require the playerKey field, which isn't define in - # the BrightcoveExperience object - brightcove_url = self._og_search_video_url(webpage) - except RegexNotFoundError: - # Other videos works fine with the info from the object - brightcove_url = BrightcoveLegacyIE._extract_brightcove_url(webpage) - if brightcove_url is None: - raise ExtractorError( - 'The webpage does not contain a video', expected=True) - return self.url_result(brightcove_url, BrightcoveLegacyIE.ie_key()) diff --git a/youtube_dl/extractor/ted.py b/youtube_dl/extractor/ted.py index a48d77c30..cf8851438 100644 --- a/youtube_dl/extractor/ted.py +++ b/youtube_dl/extractor/ted.py @@ -73,7 +73,7 @@ class TEDIE(InfoExtractor): 'add_ie': ['Youtube'], 'info_dict': { 'id': '_ZG8HBuDjgc', - 'ext': 'mp4', + 'ext': 'webm', 'title': 'Douglas Adams: Parrots the Universe and Everything', 'description': 'md5:01ad1e199c49ac640cb1196c0e9016af', 'uploader': 'University of California Television (UCTV)', diff --git a/youtube_dl/extractor/tf1.py b/youtube_dl/extractor/tf1.py index 6890021cf..9ee844684 100644 --- a/youtube_dl/extractor/tf1.py +++ b/youtube_dl/extractor/tf1.py @@ -48,8 +48,6 @@ class TF1IE(InfoExtractor): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) wat_id = self._html_search_regex( - r'(["\'])(?:https?:)?//www\.wat\.tv/embedframe/.*?(?P<id>\d{8})\1', + r'(["\'])(?:https?:)?//www\.wat\.tv/embedframe/.*?(?P<id>\d{8})(?:#.*?)?\1', webpage, 'wat id', group='id') - wat_info = self._download_json( - 'http://www.wat.tv/interface/contentv3/%s' % wat_id, video_id) - return self.url_result(wat_info['media']['url'], 'Wat') + return self.url_result('wat:%s' % wat_id, 'Wat') diff --git a/youtube_dl/extractor/theplatform.py b/youtube_dl/extractor/theplatform.py index 755f816ff..9a57b49df 100644 --- a/youtube_dl/extractor/theplatform.py +++ b/youtube_dl/extractor/theplatform.py @@ -21,6 +21,8 @@ from ..utils import ( sanitized_Request, unsmuggle_url, xpath_with_ns, + mimetype2ext, + find_xpath_attr, ) default_ns = 'http://www.w3.org/2005/SMIL21/Language' @@ -30,15 +32,11 @@ _x = lambda p: xpath_with_ns(p, {'smil': default_ns}) class ThePlatformBaseIE(InfoExtractor): def _extract_theplatform_smil(self, smil_url, video_id, note='Downloading SMIL data'): meta = self._download_xml(smil_url, video_id, note=note) - try: - error_msg = next( - n.attrib['abstract'] - for n in meta.findall(_x('.//smil:ref')) - if n.attrib.get('title') == 'Geographic Restriction' or n.attrib.get('title') == 'Expired') - except StopIteration: - pass - else: - raise ExtractorError(error_msg, expected=True) + error_element = find_xpath_attr( + meta, _x('.//smil:ref'), 'src', + 'http://link.theplatform.com/s/errorFiles/Unavailable.mp4') + if error_element is not None: + raise ExtractorError(error_element.attrib['abstract'], expected=True) formats = self._parse_smil_formats( meta, smil_url, video_id, namespace=default_ns, @@ -68,7 +66,7 @@ class ThePlatformBaseIE(InfoExtractor): for caption in captions: lang, src, mime = caption.get('lang', 'en'), caption.get('src'), caption.get('type') subtitles[lang] = [{ - 'ext': 'srt' if mime == 'text/srt' else 'ttml', + 'ext': mimetype2ext(mime), 'url': src, }] diff --git a/youtube_dl/extractor/tnaflix.py b/youtube_dl/extractor/tnaflix.py index 49516abca..79f036fe4 100644 --- a/youtube_dl/extractor/tnaflix.py +++ b/youtube_dl/extractor/tnaflix.py @@ -71,7 +71,7 @@ class TNAFlixNetworkBaseIE(InfoExtractor): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') - display_id = mobj.group('display_id') + display_id = mobj.group('display_id') if 'display_id' in mobj.groupdict() else video_id webpage = self._download_webpage(url, display_id) @@ -117,7 +117,7 @@ class TNAFlixNetworkBaseIE(InfoExtractor): title = self._html_search_regex( self._TITLE_REGEX, webpage, 'title') if self._TITLE_REGEX else self._og_search_title(webpage) - age_limit = self._rta_search(webpage) + age_limit = self._rta_search(webpage) or 18 duration = parse_duration(self._html_search_meta( 'duration', webpage, 'duration', default=None)) @@ -152,6 +152,36 @@ class TNAFlixNetworkBaseIE(InfoExtractor): } +class TNAFlixNetworkEmbedIE(TNAFlixNetworkBaseIE): + _VALID_URL = r'https?://player\.(?:tna|emp)flix\.com/video/(?P<id>\d+)' + + _TITLE_REGEX = r'<title>([^<]+)</title>' + + _TESTS = [{ + 'url': 'https://player.tnaflix.com/video/6538', + 'info_dict': { + 'id': '6538', + 'display_id': '6538', + 'ext': 'mp4', + 'title': 'Educational xxx video', + 'thumbnail': 're:https?://.*\.jpg$', + 'age_limit': 18, + }, + 'params': { + 'skip_download': True, + }, + }, { + 'url': 'https://player.empflix.com/video/33051', + 'only_matching': True, + }] + + @staticmethod + def _extract_urls(webpage): + return [url for _, url in re.findall( + r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.(?:tna|emp)flix\.com/video/\d+)\1', + webpage)] + + class TNAFlixIE(TNAFlixNetworkBaseIE): _VALID_URL = r'https?://(?:www\.)?tnaflix\.com/[^/]+/(?P<display_id>[^/]+)/video(?P<id>\d+)' diff --git a/youtube_dl/extractor/twitch.py b/youtube_dl/extractor/twitch.py index 69882da63..958bf8fff 100644 --- a/youtube_dl/extractor/twitch.py +++ b/youtube_dl/extractor/twitch.py @@ -17,6 +17,7 @@ from ..utils import ( encode_dict, ExtractorError, int_or_none, + orderedSet, parse_duration, parse_iso8601, sanitized_Request, @@ -251,6 +252,7 @@ class TwitchVodIE(TwitchItemBaseIE): self._USHER_BASE, item_id, compat_urllib_parse.urlencode({ 'allow_source': 'true', + 'allow_audio_only': 'true', 'allow_spectre': 'true', 'player': 'twitchweb', 'nauth': access_token['token'], @@ -281,17 +283,36 @@ class TwitchPlaylistBaseIE(TwitchBaseIE): entries = [] offset = 0 limit = self._PAGE_LIMIT + broken_paging_detected = False + counter_override = None for counter in itertools.count(1): response = self._download_json( self._PLAYLIST_URL % (channel_id, offset, limit), - channel_id, 'Downloading %s videos JSON page %d' % (self._PLAYLIST_TYPE, counter)) + channel_id, + 'Downloading %s videos JSON page %s' + % (self._PLAYLIST_TYPE, counter_override or counter)) page_entries = self._extract_playlist_page(response) if not page_entries: break + total = int_or_none(response.get('_total')) + # Since the beginning of March 2016 twitch's paging mechanism + # is completely broken on the twitch side. It simply ignores + # a limit and returns the whole offset number of videos. + # Working around by just requesting all videos at once. + if not broken_paging_detected and total and len(page_entries) > limit: + self.report_warning( + 'Twitch paging is broken on twitch side, requesting all videos at once', + channel_id) + broken_paging_detected = True + offset = total + counter_override = '(all at once)' + continue entries.extend(page_entries) + if broken_paging_detected or total and len(page_entries) >= total: + break offset += limit return self.playlist_result( - [self.url_result(entry) for entry in set(entries)], + [self.url_result(entry) for entry in orderedSet(entries)], channel_id, channel_name) def _extract_playlist_page(self, response): @@ -411,6 +432,7 @@ class TwitchStreamIE(TwitchBaseIE): query = { 'allow_source': 'true', + 'allow_audio_only': 'true', 'p': random.randint(1000000, 10000000), 'player': 'twitchweb', 'segment_preference': '4', diff --git a/youtube_dl/extractor/twitter.py b/youtube_dl/extractor/twitter.py index a161f046b..e70b2ab3c 100644 --- a/youtube_dl/extractor/twitter.py +++ b/youtube_dl/extractor/twitter.py @@ -10,21 +10,26 @@ from ..utils import ( remove_end, int_or_none, ExtractorError, - sanitized_Request, ) -class TwitterCardIE(InfoExtractor): +class TwitterBaseIE(InfoExtractor): + def _get_vmap_video_url(self, vmap_url, video_id): + vmap_data = self._download_xml(vmap_url, video_id) + return xpath_text(vmap_data, './/MediaFile').strip() + + +class TwitterCardIE(TwitterBaseIE): IE_NAME = 'twitter:card' - _VALID_URL = r'https?://(?:www\.)?twitter\.com/i/cards/tfw/v1/(?P<id>\d+)' + _VALID_URL = r'https?://(?:www\.)?twitter\.com/i/(?:cards/tfw/v1|videos/tweet)/(?P<id>\d+)' _TESTS = [ { 'url': 'https://twitter.com/i/cards/tfw/v1/560070183650213889', - 'md5': '4fa26a35f9d1bf4b646590ba8e84be19', + # MD5 checksums are different in different places 'info_dict': { 'id': '560070183650213889', 'ext': 'mp4', - 'title': 'TwitterCard', + 'title': 'Twitter Card', 'thumbnail': 're:^https?://.*\.jpg$', 'duration': 30.033, } @@ -35,14 +40,14 @@ class TwitterCardIE(InfoExtractor): 'info_dict': { 'id': '623160978427936768', 'ext': 'mp4', - 'title': 'TwitterCard', + 'title': 'Twitter Card', 'thumbnail': 're:^https?://.*\.jpg', 'duration': 80.155, }, }, { 'url': 'https://twitter.com/i/cards/tfw/v1/654001591733886977', - 'md5': 'b6f35e8b08a0bec6c8af77a2f4b3a814', + 'md5': 'd4724ffe6d2437886d004fa5de1043b3', 'info_dict': { 'id': 'dq4Oj5quskI', 'ext': 'mp4', @@ -62,69 +67,106 @@ class TwitterCardIE(InfoExtractor): 'ext': 'mp4', 'upload_date': '20151113', 'uploader_id': '1189339351084113920', - 'uploader': '@ArsenalTerje', - 'title': 'Vine by @ArsenalTerje', + 'uploader': 'ArsenalTerje', + 'title': 'Vine by ArsenalTerje', }, 'add_ie': ['Vine'], - } + }, { + 'url': 'https://twitter.com/i/videos/tweet/705235433198714880', + 'md5': '3846d0a07109b5ab622425449b59049d', + 'info_dict': { + 'id': '705235433198714880', + 'ext': 'mp4', + 'title': 'Twitter web player', + 'thumbnail': 're:^https?://.*\.jpg', + }, + }, ] def _real_extract(self, url): video_id = self._match_id(url) - # Different formats served for different User-Agents - USER_AGENTS = [ - 'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) Gecko/20150101 Firefox/20.0 (Chrome)', # mp4 - 'Mozilla/5.0 (Windows NT 5.2; WOW64; rv:38.0) Gecko/20100101 Firefox/38.0', # webm - ] - config = None formats = [] - for user_agent in USER_AGENTS: - request = sanitized_Request(url) - request.add_header('User-Agent', user_agent) - webpage = self._download_webpage(request, video_id) - - iframe_url = self._html_search_regex( - r'<iframe[^>]+src="((?:https?:)?//(?:www.youtube.com/embed/[^"]+|(?:www\.)?vine\.co/v/\w+/card))"', - webpage, 'video iframe', default=None) - if iframe_url: - return self.url_result(iframe_url) - - config = self._parse_json(self._html_search_regex( - r'data-player-config="([^"]+)"', webpage, 'data player config'), - video_id) - if 'playlist' not in config: - if 'vmapUrl' in config: - vmap_data = self._download_xml(config['vmapUrl'], video_id) - video_url = xpath_text(vmap_data, './/MediaFile').strip() - formats.append({ - 'url': video_url, - }) - break # same video regardless of UA - continue - - video_url = config['playlist'][0]['source'] + duration = None - f = { - 'url': video_url, - } + webpage = self._download_webpage(url, video_id) + + iframe_url = self._html_search_regex( + r'<iframe[^>]+src="((?:https?:)?//(?:www.youtube.com/embed/[^"]+|(?:www\.)?vine\.co/v/\w+/card))"', + webpage, 'video iframe', default=None) + if iframe_url: + return self.url_result(iframe_url) + + config = self._parse_json(self._html_search_regex( + r'data-(?:player-)?config="([^"]+)"', webpage, 'data player config'), + video_id) + def _search_dimensions_in_video_url(a_format, video_url): m = re.search(r'/(?P<width>\d+)x(?P<height>\d+)/', video_url) if m: - f.update({ + a_format.update({ 'width': int(m.group('width')), 'height': int(m.group('height')), }) + + playlist = config.get('playlist') + if playlist: + video_url = playlist[0]['source'] + + f = { + 'url': video_url, + } + + _search_dimensions_in_video_url(f, video_url) + formats.append(f) + + vmap_url = config.get('vmapUrl') or config.get('vmap_url') + if vmap_url: + formats.append({ + 'url': self._get_vmap_video_url(vmap_url, video_id), + }) + + media_info = None + + for entity in config.get('status', {}).get('entities', []): + if 'mediaInfo' in entity: + media_info = entity['mediaInfo'] + + if media_info: + for media_variant in media_info['variants']: + media_url = media_variant['url'] + if media_url.endswith('.m3u8'): + formats.extend(self._extract_m3u8_formats(media_url, video_id, ext='mp4', m3u8_id='hls')) + elif media_url.endswith('.mpd'): + formats.extend(self._extract_mpd_formats(media_url, video_id, mpd_id='dash')) + else: + vbr = int_or_none(media_variant.get('bitRate'), scale=1000) + a_format = { + 'url': media_url, + 'format_id': 'http-%d' % vbr if vbr else 'http', + 'vbr': vbr, + } + # Reported bitRate may be zero + if not a_format['vbr']: + del a_format['vbr'] + + _search_dimensions_in_video_url(a_format, media_url) + + formats.append(a_format) + + duration = float_or_none(media_info.get('duration', {}).get('nanos'), scale=1e9) + self._sort_formats(formats) - thumbnail = config.get('posterImageUrl') - duration = float_or_none(config.get('duration')) + title = self._search_regex(r'<title>([^<]+)</title>', webpage, 'title') + thumbnail = config.get('posterImageUrl') or config.get('image_src') + duration = float_or_none(config.get('duration')) or duration return { 'id': video_id, - 'title': 'TwitterCard', + 'title': title, 'thumbnail': thumbnail, 'duration': duration, 'formats': formats, @@ -138,7 +180,6 @@ class TwitterIE(InfoExtractor): _TESTS = [{ 'url': 'https://twitter.com/freethenipple/status/643211948184596480', - 'md5': 'db6612ec5d03355953c3ca9250c97e5e', 'info_dict': { 'id': '643211948184596480', 'ext': 'mp4', @@ -149,6 +190,9 @@ class TwitterIE(InfoExtractor): 'uploader': 'FREE THE NIPPLE', 'uploader_id': 'freethenipple', }, + 'params': { + 'skip_download': True, # requires ffmpeg + }, }, { 'url': 'https://twitter.com/giphz/status/657991469417025536/photo/1', 'md5': 'f36dcd5fb92bf7057f155e7d927eeb42', @@ -161,6 +205,7 @@ class TwitterIE(InfoExtractor): 'uploader': 'Gifs', 'uploader_id': 'giphz', }, + 'expected_warnings': ['height', 'width'], }, { 'url': 'https://twitter.com/starwars/status/665052190608723968', 'md5': '39b7199856dee6cd4432e72c74bc69d4', @@ -172,6 +217,36 @@ class TwitterIE(InfoExtractor): 'uploader_id': 'starwars', 'uploader': 'Star Wars', }, + }, { + 'url': 'https://twitter.com/BTNBrentYarina/status/705235433198714880', + 'info_dict': { + 'id': '705235433198714880', + 'ext': 'mp4', + 'title': 'Brent Yarina - Khalil Iverson\'s missed highlight dunk. And made highlight dunk. In one highlight.', + 'description': 'Brent Yarina on Twitter: "Khalil Iverson\'s missed highlight dunk. And made highlight dunk. In one highlight."', + 'uploader_id': 'BTNBrentYarina', + 'uploader': 'Brent Yarina', + }, + 'params': { + # The same video as https://twitter.com/i/videos/tweet/705235433198714880 + # Test case of TwitterCardIE + 'skip_download': True, + }, + }, { + 'url': 'https://twitter.com/jaydingeer/status/700207533655363584', + 'md5': '', + 'info_dict': { + 'id': '700207533655363584', + 'ext': 'mp4', + 'title': 'jay - BEAT PROD: @suhmeduh #Damndaniel', + 'description': 'jay on Twitter: "BEAT PROD: @suhmeduh https://t.co/HBrQ4AfpvZ #Damndaniel https://t.co/byBooq2ejZ"', + 'thumbnail': 're:^https?://.*\.jpg', + 'uploader': 'jay', + 'uploader_id': 'jaydingeer', + }, + 'params': { + 'skip_download': True, # requires ffmpeg + }, }] def _real_extract(self, url): @@ -208,21 +283,91 @@ class TwitterIE(InfoExtractor): return info mobj = re.search(r'''(?x) - <video[^>]+class="animated-gif"[^>]+ - (?:data-height="(?P<height>\d+)")?[^>]+ - (?:data-width="(?P<width>\d+)")?[^>]+ - (?:poster="(?P<poster>[^"]+)")?[^>]*>\s* + <video[^>]+class="animated-gif"(?P<more_info>[^>]+)>\s* <source[^>]+video-src="(?P<url>[^"]+)" ''', webpage) if mobj: + more_info = mobj.group('more_info') + height = int_or_none(self._search_regex( + r'data-height="(\d+)"', more_info, 'height', fatal=False)) + width = int_or_none(self._search_regex( + r'data-width="(\d+)"', more_info, 'width', fatal=False)) + thumbnail = self._search_regex( + r'poster="([^"]+)"', more_info, 'poster', fatal=False) info.update({ 'id': twid, 'url': mobj.group('url'), - 'height': int_or_none(mobj.group('height')), - 'width': int_or_none(mobj.group('width')), - 'thumbnail': mobj.group('poster'), + 'height': height, + 'width': width, + 'thumbnail': thumbnail, }) return info - raise ExtractorError('There\'s not video in this tweet.') + if 'class="PlayableMedia' in webpage: + info.update({ + '_type': 'url_transparent', + 'ie_key': 'TwitterCard', + 'url': '%s//twitter.com/i/videos/tweet/%s' % (self.http_scheme(), twid), + }) + + return info + + raise ExtractorError('There\'s no video in this tweet.') + + +class TwitterAmplifyIE(TwitterBaseIE): + IE_NAME = 'twitter:amplify' + _VALID_URL = 'https?://amp\.twimg\.com/v/(?P<id>[0-9a-f\-]{36})' + + _TEST = { + 'url': 'https://amp.twimg.com/v/0ba0c3c7-0af3-4c0a-bed5-7efd1ffa2951', + 'md5': '7df102d0b9fd7066b86f3159f8e81bf6', + 'info_dict': { + 'id': '0ba0c3c7-0af3-4c0a-bed5-7efd1ffa2951', + 'ext': 'mp4', + 'title': 'Twitter Video', + 'thumbnail': 're:^https?://.*', + }, + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + vmap_url = self._html_search_meta( + 'twitter:amplify:vmap', webpage, 'vmap url') + video_url = self._get_vmap_video_url(vmap_url, video_id) + + thumbnails = [] + thumbnail = self._html_search_meta( + 'twitter:image:src', webpage, 'thumbnail', fatal=False) + + def _find_dimension(target): + w = int_or_none(self._html_search_meta( + 'twitter:%s:width' % target, webpage, fatal=False)) + h = int_or_none(self._html_search_meta( + 'twitter:%s:height' % target, webpage, fatal=False)) + return w, h + + if thumbnail: + thumbnail_w, thumbnail_h = _find_dimension('image') + thumbnails.append({ + 'url': thumbnail, + 'width': thumbnail_w, + 'height': thumbnail_h, + }) + + video_w, video_h = _find_dimension('player') + formats = [{ + 'url': video_url, + 'width': video_w, + 'height': video_h, + }] + + return { + 'id': video_id, + 'title': 'Twitter Video', + 'formats': formats, + 'thumbnails': thumbnails, + } diff --git a/youtube_dl/extractor/ustudio.py b/youtube_dl/extractor/ustudio.py new file mode 100644 index 000000000..cafc082b6 --- /dev/null +++ b/youtube_dl/extractor/ustudio.py @@ -0,0 +1,67 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + int_or_none, + unified_strdate, +) + + +class UstudioIE(InfoExtractor): + _VALID_URL = r'https?://(?:(?:www|v1)\.)?ustudio\.com/video/(?P<id>[^/]+)/(?P<display_id>[^/?#&]+)' + _TEST = { + 'url': 'http://ustudio.com/video/Uxu2my9bgSph/san_francisco_golden_gate_bridge', + 'md5': '58bbfca62125378742df01fc2abbdef6', + 'info_dict': { + 'id': 'Uxu2my9bgSph', + 'display_id': 'san_francisco_golden_gate_bridge', + 'ext': 'mp4', + 'title': 'San Francisco: Golden Gate Bridge', + 'description': 'md5:23925500697f2c6d4830e387ba51a9be', + 'thumbnail': 're:^https?://.*\.jpg$', + 'upload_date': '20111107', + 'uploader': 'Tony Farley', + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + display_id = mobj.group('display_id') + + config = self._download_xml( + 'http://v1.ustudio.com/embed/%s/ustudio/config.xml' % video_id, + display_id) + + def extract(kind): + return [{ + 'url': item.attrib['url'], + 'width': int_or_none(item.get('width')), + 'height': int_or_none(item.get('height')), + } for item in config.findall('./qualities/quality/%s' % kind) if item.get('url')] + + formats = extract('video') + self._sort_formats(formats) + + webpage = self._download_webpage(url, display_id) + + title = self._og_search_title(webpage) + upload_date = unified_strdate(self._search_regex( + r'(?s)Uploaded by\s*.+?\s*on\s*<span>([^<]+)</span>', + webpage, 'upload date', fatal=False)) + uploader = self._search_regex( + r'Uploaded by\s*<a[^>]*>([^<]+)<', + webpage, 'uploader', fatal=False) + + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'description': self._og_search_description(webpage), + 'thumbnails': extract('image'), + 'upload_date': upload_date, + 'uploader': uploader, + 'formats': formats, + } diff --git a/youtube_dl/extractor/vgtv.py b/youtube_dl/extractor/vgtv.py index 14e945d49..e148b1ef5 100644 --- a/youtube_dl/extractor/vgtv.py +++ b/youtube_dl/extractor/vgtv.py @@ -20,6 +20,7 @@ class VGTVIE(XstreamIE): 'aftenbladet.no/tv': 'satv', 'fvn.no/fvntv': 'fvntv', 'aftenposten.no/webtv': 'aptv', + 'ap.vgtv.no/webtv': 'aptv', } _APP_NAME_TO_VENDOR = { @@ -35,7 +36,7 @@ class VGTVIE(XstreamIE): (?P<host> %s ) - / + /? (?: \#!/(?:video|live)/| embed?.*id= @@ -107,19 +108,27 @@ class VGTVIE(XstreamIE): 'md5': 'fd828cd29774a729bf4d4425fe192972', 'info_dict': { 'id': '21039', - 'ext': 'mov', + 'ext': 'mp4', 'title': 'TRAILER: «SWEATSHOP» - I can´t take any more', 'description': 'md5:21891f2b0dd7ec2f78d84a50e54f8238', 'duration': 66, 'timestamp': 1417002452, 'upload_date': '20141126', 'view_count': int, - } + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, }, { 'url': 'http://www.bt.no/tv/#!/video/100250/norling-dette-er-forskjellen-paa-1-divisjon-og-eliteserien', 'only_matching': True, }, + { + 'url': 'http://ap.vgtv.no/webtv#!/video/111084/de-nye-bysyklene-lettere-bedre-gir-stoerre-hjul-og-feste-til-mobil', + 'only_matching': True, + }, ] def _real_extract(self, url): @@ -144,8 +153,6 @@ class VGTVIE(XstreamIE): if len(video_id) == 5: if appname == 'bttv': info = self._extract_video_info('btno', video_id) - elif appname == 'aptv': - info = self._extract_video_info('ap', video_id) streams = data['streamUrls'] stream_type = data.get('streamType') diff --git a/youtube_dl/extractor/vice.py b/youtube_dl/extractor/vice.py index 3db6286e4..46c785ae1 100644 --- a/youtube_dl/extractor/vice.py +++ b/youtube_dl/extractor/vice.py @@ -1,31 +1,37 @@ from __future__ import unicode_literals +import re + from .common import InfoExtractor from .ooyala import OoyalaIE from ..utils import ExtractorError class ViceIE(InfoExtractor): - _VALID_URL = r'https?://(?:.+?\.)?vice\.com/(?:[^/]+/)+(?P<id>.+)' - - _TESTS = [ - { - 'url': 'http://www.vice.com/Fringes/cowboy-capitalists-part-1', - 'info_dict': { - 'id': '43cW1mYzpia9IlestBjVpd23Yu3afAfp', - 'ext': 'mp4', - 'title': 'VICE_COWBOYCAPITALISTS_PART01_v1_VICE_WM_1080p.mov', - 'duration': 725.983, - }, - 'params': { - # Requires ffmpeg (m3u8 manifest) - 'skip_download': True, - }, - }, { - 'url': 'https://news.vice.com/video/experimenting-on-animals-inside-the-monkey-lab', - 'only_matching': True, - } - ] + _VALID_URL = r'https?://(?:.+?\.)?vice\.com/(?:[^/]+/)?videos?/(?P<id>[^/?#&]+)' + + _TESTS = [{ + 'url': 'http://www.vice.com/video/cowboy-capitalists-part-1', + 'info_dict': { + 'id': '43cW1mYzpia9IlestBjVpd23Yu3afAfp', + 'ext': 'mp4', + 'title': 'VICE_COWBOYCAPITALISTS_PART01_v1_VICE_WM_1080p.mov', + 'duration': 725.983, + }, + 'params': { + # Requires ffmpeg (m3u8 manifest) + 'skip_download': True, + }, + }, { + 'url': 'https://news.vice.com/video/experimenting-on-animals-inside-the-monkey-lab', + 'only_matching': True, + }, { + 'url': 'http://www.vice.com/ru/video/big-night-out-ibiza-clive-martin-229', + 'only_matching': True, + }, { + 'url': 'https://munchies.vice.com/en/videos/watch-the-trailer-for-our-new-series-the-pizza-show', + 'only_matching': True, + }] def _real_extract(self, url): video_id = self._match_id(url) @@ -38,3 +44,35 @@ class ViceIE(InfoExtractor): except ExtractorError: raise ExtractorError('The page doesn\'t contain a video', expected=True) return self.url_result(ooyala_url, ie='Ooyala') + + +class ViceShowIE(InfoExtractor): + _VALID_URL = r'https?://(?:.+?\.)?vice\.com/(?:[^/]+/)?show/(?P<id>[^/?#&]+)' + + _TEST = { + 'url': 'https://munchies.vice.com/en/show/fuck-thats-delicious-2', + 'info_dict': { + 'id': 'fuck-thats-delicious-2', + 'title': "Fuck, That's Delicious", + 'description': 'Follow the culinary adventures of rapper Action Bronson during his ongoing world tour.', + }, + 'playlist_count': 17, + } + + def _real_extract(self, url): + show_id = self._match_id(url) + webpage = self._download_webpage(url, show_id) + + entries = [ + self.url_result(video_url, ViceIE.ie_key()) + for video_url, _ in re.findall( + r'<h2[^>]+class="article-title"[^>]+data-id="\d+"[^>]*>\s*<a[^>]+href="(%s.*?)"' + % ViceIE._VALID_URL, webpage)] + + title = self._search_regex( + r'<title>(.+?)</title>', webpage, 'title', default=None) + if title: + title = re.sub(r'(.+)\s*\|\s*.+$', r'\1', title).strip() + description = self._html_search_meta('description', webpage, 'description') + + return self.playlist_result(entries, show_id, title, description) diff --git a/youtube_dl/extractor/videomega.py b/youtube_dl/extractor/videomega.py index 5e2e7cbac..4f0dcd18c 100644 --- a/youtube_dl/extractor/videomega.py +++ b/youtube_dl/extractor/videomega.py @@ -4,11 +4,13 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import sanitized_Request +from ..utils import ( + decode_packed_codes, + sanitized_Request, +) class VideoMegaIE(InfoExtractor): - _WORKING = False _VALID_URL = r'(?:videomega:|https?://(?:www\.)?videomega\.tv/(?:(?:view|iframe|cdn)\.php)?\?ref=)(?P<id>[A-Za-z0-9]+)' _TESTS = [{ 'url': 'http://videomega.tv/cdn.php?ref=AOSQBJYKIDDIKYJBQSOA', @@ -42,8 +44,10 @@ class VideoMegaIE(InfoExtractor): r'(?:^[Vv]ideo[Mm]ega\.tv\s-\s*|\s*-\svideomega\.tv$)', '', title) thumbnail = self._search_regex( r'<video[^>]+?poster="([^"]+)"', webpage, 'thumbnail', fatal=False) + + real_codes = decode_packed_codes(webpage) video_url = self._search_regex( - r'<source[^>]+?src="([^"]+)"', webpage, 'video URL') + r'"src"\s*,\s*"([^"]+)"', real_codes, 'video URL') return { 'id': video_id, diff --git a/youtube_dl/extractor/vidzi.py b/youtube_dl/extractor/vidzi.py index 7c6e98026..3c78fb3d5 100644 --- a/youtube_dl/extractor/vidzi.py +++ b/youtube_dl/extractor/vidzi.py @@ -1,11 +1,14 @@ # coding: utf-8 from __future__ import unicode_literals -from .common import InfoExtractor -from ..utils import smuggle_url +from .jwplatform import JWPlatformBaseIE +from ..utils import ( + decode_packed_codes, + js_to_json, +) -class VidziIE(InfoExtractor): +class VidziIE(JWPlatformBaseIE): _VALID_URL = r'https?://(?:www\.)?vidzi\.tv/(?P<id>\w+)' _TEST = { 'url': 'http://vidzi.tv/cghql9yq6emu.html', @@ -14,7 +17,6 @@ class VidziIE(InfoExtractor): 'id': 'cghql9yq6emu', 'ext': 'mp4', 'title': 'youtube-dl test video 1\\\\2\'3/4<5\\\\6ä7↭', - 'uploader': 'vidzi.tv', }, 'params': { # m3u8 download @@ -29,11 +31,12 @@ class VidziIE(InfoExtractor): title = self._html_search_regex( r'(?s)<h2 class="video-title">(.*?)</h2>', webpage, 'title') - # Vidzi now uses jwplayer, which can be handled by GenericIE - return { - '_type': 'url_transparent', - 'id': video_id, - 'title': title, - 'url': smuggle_url(url, {'to_generic': True}), - 'ie_key': 'Generic', - } + code = decode_packed_codes(webpage).replace('\\\'', '\'') + jwplayer_data = self._parse_json( + self._search_regex(r'setup\(([^)]+)\)', code, 'jwplayer data'), + video_id, transform_source=js_to_json) + + info_dict = self._parse_jwplayer_data(jwplayer_data, video_id, require_title=False) + info_dict['title'] = title + + return info_dict diff --git a/youtube_dl/extractor/viki.py b/youtube_dl/extractor/viki.py index 433fc9914..e04b814c8 100644 --- a/youtube_dl/extractor/viki.py +++ b/youtube_dl/extractor/viki.py @@ -176,13 +176,13 @@ class VikiIE(VikiBaseIE): }, { # youtube external 'url': 'http://www.viki.com/videos/50562v-poor-nastya-complete-episode-1', - 'md5': '216d1afdc0c64d1febc1e9f2bd4b864b', + 'md5': '63f8600c1da6f01b7640eee7eca4f1da', 'info_dict': { 'id': '50562v', - 'ext': 'mp4', + 'ext': 'webm', 'title': 'Poor Nastya [COMPLETE] - Episode 1', 'description': '', - 'duration': 607, + 'duration': 606, 'timestamp': 1274949505, 'upload_date': '20101213', 'uploader': 'ad14065n', diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index 3049dffb6..71c30d2cd 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -73,15 +73,26 @@ class VimeoIE(VimeoBaseInfoExtractor): # _VALID_URL matches Vimeo URLs _VALID_URL = r'''(?x) - https?:// - (?:(?:www|(?P<player>player))\.)? - vimeo(?P<pro>pro)?\.com/ - (?!channels/[^/?#]+/?(?:$|[?#])|album/) - (?:.*?/)? - (?:(?:play_redirect_hls|moogaloop\.swf)\?clip_id=)? - (?:videos?/)? - (?P<id>[0-9]+) - /?(?:[?&].*)?(?:[#].*)?$''' + https?:// + (?: + (?: + www| + (?P<player>player) + ) + \. + )? + vimeo(?P<pro>pro)?\.com/ + (?!channels/[^/?#]+/?(?:$|[?#])|(?:album|ondemand)/) + (?:.*?/)? + (?: + (?: + play_redirect_hls| + moogaloop\.swf)\?clip_id= + )? + (?:videos?/)? + (?P<id>[0-9]+) + /?(?:[?&].*)?(?:[#].*)?$ + ''' IE_NAME = 'vimeo' _TESTS = [ { @@ -93,6 +104,7 @@ class VimeoIE(VimeoBaseInfoExtractor): 'title': "youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550", 'description': 'md5:2d3305bad981a06ff79f027f19865021', 'upload_date': '20121220', + 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/user7108434', 'uploader_id': 'user7108434', 'uploader': 'Filippo Valsorda', 'duration': 10, @@ -105,6 +117,7 @@ class VimeoIE(VimeoBaseInfoExtractor): 'info_dict': { 'id': '68093876', 'ext': 'mp4', + 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/openstreetmapus', 'uploader_id': 'openstreetmapus', 'uploader': 'OpenStreetMap US', 'title': 'Andy Allan - Putting the Carto into OpenStreetMap Cartography', @@ -121,6 +134,7 @@ class VimeoIE(VimeoBaseInfoExtractor): 'ext': 'mp4', 'title': 'Kathy Sierra: Building the minimum Badass User, Business of Software 2012', 'uploader': 'The BLN & Business of Software', + 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/theblnbusinessofsoftware', 'uploader_id': 'theblnbusinessofsoftware', 'duration': 3610, 'description': None, @@ -135,6 +149,7 @@ class VimeoIE(VimeoBaseInfoExtractor): 'ext': 'mp4', 'title': 'youtube-dl password protected test video', 'upload_date': '20130614', + 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/user18948128', 'uploader_id': 'user18948128', 'uploader': 'Jaime Marquínez Ferrándiz', 'duration': 10, @@ -154,6 +169,7 @@ class VimeoIE(VimeoBaseInfoExtractor): 'ext': 'mp4', 'title': 'Key & Peele: Terrorist Interrogation', 'description': 'md5:8678b246399b070816b12313e8b4eb5c', + 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/atencio', 'uploader_id': 'atencio', 'uploader': 'Peter Atencio', 'upload_date': '20130927', @@ -169,6 +185,7 @@ class VimeoIE(VimeoBaseInfoExtractor): 'title': 'The New Vimeo Player (You Know, For Videos)', 'description': 'md5:2ec900bf97c3f389378a96aee11260ea', 'upload_date': '20131015', + 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/staff', 'uploader_id': 'staff', 'uploader': 'Vimeo Staff', 'duration': 62, @@ -183,6 +200,7 @@ class VimeoIE(VimeoBaseInfoExtractor): 'ext': 'mp4', 'title': 'Pier Solar OUYA Official Trailer', 'uploader': 'Tulio Gonçalves', + 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/user28849593', 'uploader_id': 'user28849593', }, }, @@ -195,6 +213,7 @@ class VimeoIE(VimeoBaseInfoExtractor): 'ext': 'mp4', 'title': 'FOX CLASSICS - Forever Classic ID - A Full Minute', 'uploader': 'The DMCI', + 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/dmci', 'uploader_id': 'dmci', 'upload_date': '20111220', 'description': 'md5:ae23671e82d05415868f7ad1aec21147', @@ -269,9 +288,8 @@ class VimeoIE(VimeoBaseInfoExtractor): def _real_extract(self, url): url, data = unsmuggle_url(url, {}) - headers = std_headers + headers = std_headers.copy() if 'http_headers' in data: - headers = headers.copy() headers.update(data['http_headers']) if 'Referer' not in headers: headers['Referer'] = url @@ -286,7 +304,7 @@ class VimeoIE(VimeoBaseInfoExtractor): url = 'https://vimeo.com/' + video_id # Retrieve video webpage to extract further information - request = sanitized_Request(url, None, headers) + request = sanitized_Request(url, headers=headers) try: webpage = self._download_webpage(request, video_id) except ExtractorError as ee: @@ -370,9 +388,10 @@ class VimeoIE(VimeoBaseInfoExtractor): # Extract title video_title = config['video']['title'] - # Extract uploader and uploader_id - video_uploader = config['video']['owner']['name'] - video_uploader_id = config['video']['owner']['url'].split('/')[-1] if config['video']['owner']['url'] else None + # Extract uploader, uploader_url and uploader_id + video_uploader = config['video'].get('owner', {}).get('name') + video_uploader_url = config['video'].get('owner', {}).get('url') + video_uploader_id = video_uploader_url.split('/')[-1] if video_uploader_url else None # Extract video thumbnail video_thumbnail = config['video'].get('thumbnail') @@ -473,6 +492,7 @@ class VimeoIE(VimeoBaseInfoExtractor): return { 'id': video_id, 'uploader': video_uploader, + 'uploader_url': video_uploader_url, 'uploader_id': video_uploader_id, 'upload_date': video_upload_date, 'title': video_title, @@ -488,6 +508,38 @@ class VimeoIE(VimeoBaseInfoExtractor): } +class VimeoOndemandIE(VimeoBaseInfoExtractor): + IE_NAME = 'vimeo:ondemand' + _VALID_URL = r'https?://(?:www\.)?vimeo\.com/ondemand/(?P<id>[^/?#&]+)' + _TESTS = [{ + # ondemand video not available via https://vimeo.com/id + 'url': 'https://vimeo.com/ondemand/20704', + 'md5': 'c424deda8c7f73c1dfb3edd7630e2f35', + 'info_dict': { + 'id': '105442900', + 'ext': 'mp4', + 'title': 'המעבדה - במאי יותם פלדמן', + 'uploader': 'גם סרטים', + 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/gumfilms', + 'uploader_id': 'gumfilms', + }, + }, { + 'url': 'https://vimeo.com/ondemand/nazmaalik', + 'only_matching': True, + }, { + 'url': 'https://vimeo.com/ondemand/141692381', + 'only_matching': True, + }, { + 'url': 'https://vimeo.com/ondemand/thelastcolony/150274832', + 'only_matching': True, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + return self.url_result(self._og_search_video_url(webpage), VimeoIE.ie_key()) + + class VimeoChannelIE(VimeoBaseInfoExtractor): IE_NAME = 'vimeo:channel' _VALID_URL = r'https://vimeo\.com/channels/(?P<id>[^/?#]+)/?(?:$|[?#])' diff --git a/youtube_dl/extractor/vk.py b/youtube_dl/extractor/vk.py index 0805e3c08..d560a4b5e 100644 --- a/youtube_dl/extractor/vk.py +++ b/youtube_dl/extractor/vk.py @@ -11,6 +11,7 @@ from ..compat import ( ) from ..utils import ( ExtractorError, + int_or_none, orderedSet, sanitized_Request, str_to_int, @@ -141,10 +142,10 @@ class VKIE(InfoExtractor): 'url': 'https://vk.com/video276849682_170681728', 'info_dict': { 'id': 'V3K4mi0SYkc', - 'ext': 'mp4', + 'ext': 'webm', 'title': "DSWD Awards 'Children's Joy Foundation, Inc.' Certificate of Registration and License to Operate", 'description': 'md5:bf9c26cfa4acdfb146362682edd3827a', - 'duration': 179, + 'duration': 178, 'upload_date': '20130116', 'uploader': "Children's Joy Foundation", 'uploader_id': 'thecjf', @@ -152,6 +153,19 @@ class VKIE(InfoExtractor): }, }, { + # video key is extra_data not url\d+ + 'url': 'http://vk.com/video-110305615_171782105', + 'md5': 'e13fcda136f99764872e739d13fac1d1', + 'info_dict': { + 'id': '171782105', + 'ext': 'mp4', + 'title': 'S-Dance, репетиции к The way show', + 'uploader': 'THE WAY SHOW | 17 апреля', + 'upload_date': '20160207', + 'view_count': int, + }, + }, + { # removed video, just testing that we match the pattern 'url': 'http://vk.com/feed?z=video-43215063_166094326%2Fbb50cacd3177146d7a', 'only_matching': True, @@ -298,12 +312,17 @@ class VKIE(InfoExtractor): view_count = str_to_int(self._search_regex( r'([\d,.]+)', views, 'view count', fatal=False)) - formats = [{ - 'format_id': k, - 'url': v, - 'width': int(k[len('url'):]), - } for k, v in data.items() - if k.startswith('url')] + formats = [] + for k, v in data.items(): + if not k.startswith('url') and k != 'extra_data' or not v: + continue + height = int_or_none(self._search_regex( + r'^url(\d+)', k, 'height', default=None)) + formats.append({ + 'format_id': k, + 'url': v, + 'height': height, + }) self._sort_formats(formats) return { diff --git a/youtube_dl/extractor/wat.py b/youtube_dl/extractor/wat.py index affcc52f6..37cf3d309 100644 --- a/youtube_dl/extractor/wat.py +++ b/youtube_dl/extractor/wat.py @@ -12,7 +12,7 @@ from ..utils import ( class WatIE(InfoExtractor): - _VALID_URL = r'http://www\.wat\.tv/video/(?P<display_id>.*)-(?P<short_id>.*?)_.*?\.html' + _VALID_URL = r'(?:wat:(?P<real_id>\d{8})|http://www\.wat\.tv/video/(?P<display_id>.*)-(?P<short_id>.*?)_.*?\.html)' IE_NAME = 'wat.tv' _TESTS = [ { @@ -54,10 +54,12 @@ class WatIE(InfoExtractor): def real_id_for_chapter(chapter): return chapter['tc_start'].split('-')[0] mobj = re.match(self._VALID_URL, url) - short_id = mobj.group('short_id') display_id = mobj.group('display_id') - webpage = self._download_webpage(url, display_id or short_id) - real_id = self._search_regex(r'xtpage = ".*-(.*?)";', webpage, 'real id') + real_id = mobj.group('real_id') + if not real_id: + short_id = mobj.group('short_id') + webpage = self._download_webpage(url, display_id or short_id) + real_id = self._search_regex(r'xtpage = ".*-(.*?)";', webpage, 'real id') video_info = self.download_video_info(real_id) diff --git a/youtube_dl/extractor/webofstories.py b/youtube_dl/extractor/webofstories.py index 2037d9b3d..7aea47ed5 100644 --- a/youtube_dl/extractor/webofstories.py +++ b/youtube_dl/extractor/webofstories.py @@ -12,38 +12,52 @@ class WebOfStoriesIE(InfoExtractor): _VIDEO_DOMAIN = 'http://eu-mobile.webofstories.com/' _GREAT_LIFE_STREAMER = 'rtmp://eu-cdn1.webofstories.com/cfx/st/' _USER_STREAMER = 'rtmp://eu-users.webofstories.com/cfx/st/' - _TESTS = [ - { - 'url': 'http://www.webofstories.com/play/hans.bethe/71', - 'md5': '373e4dd915f60cfe3116322642ddf364', - 'info_dict': { - 'id': '4536', - 'ext': 'mp4', - 'title': 'The temperature of the sun', - 'thumbnail': 're:^https?://.*\.jpg$', - 'description': 'Hans Bethe talks about calculating the temperature of the sun', - 'duration': 238, - } + _TESTS = [{ + 'url': 'http://www.webofstories.com/play/hans.bethe/71', + 'md5': '373e4dd915f60cfe3116322642ddf364', + 'info_dict': { + 'id': '4536', + 'ext': 'mp4', + 'title': 'The temperature of the sun', + 'thumbnail': 're:^https?://.*\.jpg$', + 'description': 'Hans Bethe talks about calculating the temperature of the sun', + 'duration': 238, + } + }, { + 'url': 'http://www.webofstories.com/play/55908', + 'md5': '2985a698e1fe3211022422c4b5ed962c', + 'info_dict': { + 'id': '55908', + 'ext': 'mp4', + 'title': 'The story of Gemmata obscuriglobus', + 'thumbnail': 're:^https?://.*\.jpg$', + 'description': 'Planctomycete talks about The story of Gemmata obscuriglobus', + 'duration': 169, + }, + 'skip': 'notfound', + }, { + # malformed og:title meta + 'url': 'http://www.webofstories.com/play/54215?o=MS', + 'info_dict': { + 'id': '54215', + 'ext': 'mp4', + 'title': '"A Leg to Stand On"', + 'thumbnail': 're:^https?://.*\.jpg$', + 'description': 'Oliver Sacks talks about the death and resurrection of a limb', + 'duration': 97, }, - { - 'url': 'http://www.webofstories.com/play/55908', - 'md5': '2985a698e1fe3211022422c4b5ed962c', - 'info_dict': { - 'id': '55908', - 'ext': 'mp4', - 'title': 'The story of Gemmata obscuriglobus', - 'thumbnail': 're:^https?://.*\.jpg$', - 'description': 'Planctomycete talks about The story of Gemmata obscuriglobus', - 'duration': 169, - } + 'params': { + 'skip_download': True, }, - ] + }] def _real_extract(self, url): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - title = self._og_search_title(webpage) + # Sometimes og:title meta is malformed + title = self._og_search_title(webpage, default=None) or self._html_search_regex( + r'(?s)<strong>Title:\s*</strong>(.+?)<', webpage, 'title') description = self._html_search_meta('description', webpage) thumbnail = self._og_search_thumbnail(webpage) diff --git a/youtube_dl/extractor/wimp.py b/youtube_dl/extractor/wimp.py index 041ff6c55..fb0accac7 100644 --- a/youtube_dl/extractor/wimp.py +++ b/youtube_dl/extractor/wimp.py @@ -20,7 +20,7 @@ class WimpIE(InfoExtractor): 'md5': '4e2986c793694b55b37cf92521d12bb4', 'info_dict': { 'id': 'clowncar', - 'ext': 'mp4', + 'ext': 'webm', 'title': 'It\'s like a clown car.', 'description': 'md5:0e56db1370a6e49c5c1d19124c0d2fb2', }, diff --git a/youtube_dl/extractor/wistia.py b/youtube_dl/extractor/wistia.py index fdb16d91c..41061dd31 100644 --- a/youtube_dl/extractor/wistia.py +++ b/youtube_dl/extractor/wistia.py @@ -35,7 +35,8 @@ class WistiaIE(InfoExtractor): formats = [] thumbnails = [] - for atype, a in data['assets'].items(): + for a in data['assets']: + atype = a.get('type') if atype == 'still': thumbnails.append({ 'url': a['url'], diff --git a/youtube_dl/extractor/xfileshare.py b/youtube_dl/extractor/xfileshare.py index a3236e66c..94abdb4f3 100644 --- a/youtube_dl/extractor/xfileshare.py +++ b/youtube_dl/extractor/xfileshare.py @@ -17,7 +17,7 @@ class XFileShareIE(InfoExtractor): IE_DESC = 'XFileShare based sites: GorillaVid.in, daclips.in, movpod.in, fastvideo.in, realvid.net, filehoot.com and vidto.me' _VALID_URL = r'''(?x) https?://(?P<host>(?:www\.)? - (?:daclips\.in|gorillavid\.in|movpod\.in|fastvideo\.in|realvid\.net|filehoot\.com|vidto\.me))/ + (?:daclips\.in|gorillavid\.in|movpod\.in|fastvideo\.in|realvid\.net|filehoot\.com|vidto\.me|powerwatch\.pw))/ (?:embed-)?(?P<id>[0-9a-zA-Z]+)(?:-[0-9]+x[0-9]+\.html)? ''' @@ -81,6 +81,13 @@ class XFileShareIE(InfoExtractor): 'ext': 'mp4', 'title': 'test' } + }, { + 'url': 'http://powerwatch.pw/duecjibvicbu', + 'info_dict': { + 'id': 'duecjibvicbu', + 'ext': 'mp4', + 'title': 'Big Buck Bunny trailer', + }, }] def _real_extract(self, url): @@ -112,6 +119,7 @@ class XFileShareIE(InfoExtractor): title = (self._search_regex( [r'style="z-index: [0-9]+;">([^<]+)</span>', r'<td nowrap>([^<]+)</td>', + r'h4-fine[^>]*>([^<]+)<', r'>Watch (.+) ', r'<h2 class="video-page-head">([^<]+)</h2>'], webpage, 'title', default=None) or self._og_search_title(webpage)).strip() diff --git a/youtube_dl/extractor/yandexmusic.py b/youtube_dl/extractor/yandexmusic.py index d3cc1a29f..e699e663f 100644 --- a/youtube_dl/extractor/yandexmusic.py +++ b/youtube_dl/extractor/yandexmusic.py @@ -10,13 +10,27 @@ from ..compat import ( compat_urllib_parse, ) from ..utils import ( + ExtractorError, int_or_none, float_or_none, sanitized_Request, ) -class YandexMusicTrackIE(InfoExtractor): +class YandexMusicBaseIE(InfoExtractor): + @staticmethod + def _handle_error(response): + error = response.get('error') + if error: + raise ExtractorError(error, expected=True) + + def _download_json(self, *args, **kwargs): + response = super(YandexMusicBaseIE, self)._download_json(*args, **kwargs) + self._handle_error(response) + return response + + +class YandexMusicTrackIE(YandexMusicBaseIE): IE_NAME = 'yandexmusic:track' IE_DESC = 'Яндекс.Музыка - Трек' _VALID_URL = r'https?://music\.yandex\.(?:ru|kz|ua|by)/album/(?P<album_id>\d+)/track/(?P<id>\d+)' @@ -73,7 +87,7 @@ class YandexMusicTrackIE(InfoExtractor): return self._get_track_info(track) -class YandexMusicPlaylistBaseIE(InfoExtractor): +class YandexMusicPlaylistBaseIE(YandexMusicBaseIE): def _build_playlist(self, tracks): return [ self.url_result( diff --git a/youtube_dl/extractor/youporn.py b/youtube_dl/extractor/youporn.py index b29baafc4..1124fe6c2 100644 --- a/youtube_dl/extractor/youporn.py +++ b/youtube_dl/extractor/youporn.py @@ -75,7 +75,7 @@ class YouPornIE(InfoExtractor): links = [] sources = self._search_regex( - r'sources\s*:\s*({.+?})', webpage, 'sources', default=None) + r'(?s)sources\s*:\s*({.+?})', webpage, 'sources', default=None) if sources: for _, link in re.findall(r'[^:]+\s*:\s*(["\'])(http.+?)\1', sources): links.append(link) @@ -101,8 +101,9 @@ class YouPornIE(InfoExtractor): } # Video URL's path looks like this: # /201012/17/505835/720p_1500k_505835/YouPorn%20-%20Sex%20Ed%20Is%20It%20Safe%20To%20Masturbate%20Daily.mp4 + # /201012/17/505835/vl_240p_240k_505835/YouPorn%20-%20Sex%20Ed%20Is%20It%20Safe%20To%20Masturbate%20Daily.mp4 # We will benefit from it by extracting some metadata - mobj = re.search(r'/(?P<height>\d{3,4})[pP]_(?P<bitrate>\d+)[kK]_\d+/', video_url) + mobj = re.search(r'(?P<height>\d{3,4})[pP]_(?P<bitrate>\d+)[kK]_\d+/', video_url) if mobj: height = int(mobj.group('height')) bitrate = int(mobj.group('bitrate')) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index e24dd3e5b..27e67feb4 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -6,6 +6,7 @@ from __future__ import unicode_literals import itertools import json import os.path +import random import re import time import traceback @@ -382,7 +383,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'title': 'youtube-dl test video "\'/\\ä↭𝕐', 'uploader': 'Philipp Hagemeister', 'uploader_id': 'phihag', + 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/phihag', 'upload_date': '20121002', + 'license': 'Standard YouTube License', 'description': 'test chars: "\'/\\ä↭𝕐\ntest URL: https://github.com/rg3/youtube-dl/issues/1892\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de .', 'categories': ['Science & Technology'], 'tags': ['youtube-dl'], @@ -401,12 +404,14 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'upload_date': '20120506', 'title': 'Icona Pop - I Love It (feat. Charli XCX) [OFFICIAL VIDEO]', 'alt_title': 'I Love It (feat. Charli XCX)', - 'description': 'md5:782e8651347686cba06e58f71ab51773', + 'description': 'md5:f3ceb5ef83a08d95b9d146f973157cc8', 'tags': ['Icona Pop i love it', 'sweden', 'pop music', 'big beat records', 'big beat', 'charli', 'xcx', 'charli xcx', 'girls', 'hbo', 'i love it', "i don't care", 'icona', 'pop', 'iconic ep', 'iconic', 'love', 'it'], 'uploader': 'Icona Pop', 'uploader_id': 'IconaPop', + 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/IconaPop', + 'license': 'Standard YouTube License', 'creator': 'Icona Pop', } }, @@ -422,6 +427,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'description': 'md5:64249768eec3bc4276236606ea996373', 'uploader': 'justintimberlakeVEVO', 'uploader_id': 'justintimberlakeVEVO', + 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/justintimberlakeVEVO', + 'license': 'Standard YouTube License', 'creator': 'Justin Timberlake', 'age_limit': 18, } @@ -437,6 +444,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7', 'uploader': 'SET India', 'uploader_id': 'setindia', + 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/setindia', + 'license': 'Standard YouTube License', 'age_limit': 18, } }, @@ -449,7 +458,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'title': 'youtube-dl test video "\'/\\ä↭𝕐', 'uploader': 'Philipp Hagemeister', 'uploader_id': 'phihag', + 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/phihag', 'upload_date': '20121002', + 'license': 'Standard YouTube License', 'description': 'test chars: "\'/\\ä↭𝕐\ntest URL: https://github.com/rg3/youtube-dl/issues/1892\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de .', 'categories': ['Science & Technology'], 'tags': ['youtube-dl'], @@ -468,8 +479,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'ext': 'm4a', 'upload_date': '20121002', 'uploader_id': '8KVIDEO', + 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/8KVIDEO', 'description': '', 'uploader': '8KVIDEO', + 'license': 'Standard YouTube License', 'title': 'UHDTV TEST 8K VIDEO.mp4' }, 'params': { @@ -488,6 +501,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'uploader': 'AfrojackVEVO', 'uploader_id': 'AfrojackVEVO', 'upload_date': '20131011', + 'license': 'Standard YouTube License', }, 'params': { 'youtube_include_dash_manifest': True, @@ -506,6 +520,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'uploader': 'TaylorSwiftVEVO', 'uploader_id': 'TaylorSwiftVEVO', 'upload_date': '20140818', + 'license': 'Standard YouTube License', 'creator': 'Taylor Swift', }, 'params': { @@ -522,6 +537,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'upload_date': '20100909', 'uploader': 'The Amazing Atheist', 'uploader_id': 'TheAmazingAtheist', + 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/TheAmazingAtheist', + 'license': 'Standard YouTube License', 'title': 'Burning Everyone\'s Koran', 'description': 'SUBSCRIBE: http://www.youtube.com/saturninefilms\n\nEven Obama has taken a stand against freedom on this issue: http://www.huffingtonpost.com/2010/09/09/obama-gma-interview-quran_n_710282.html', } @@ -536,7 +553,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'description': 're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}', 'uploader': 'The Witcher', 'uploader_id': 'WitcherGame', + 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/WitcherGame', 'upload_date': '20140605', + 'license': 'Standard YouTube License', 'age_limit': 18, }, }, @@ -550,7 +569,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'description': 'md5:33765bb339e1b47e7e72b5490139bb41', 'uploader': 'LloydVEVO', 'uploader_id': 'LloydVEVO', + 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/LloydVEVO', 'upload_date': '20110629', + 'license': 'Standard YouTube License', 'age_limit': 18, }, }, @@ -562,9 +583,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'ext': 'mp4', 'upload_date': '20100430', 'uploader_id': 'deadmau5', + 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/deadmau5', 'creator': 'deadmau5', 'description': 'md5:12c56784b8032162bb936a5f76d55360', 'uploader': 'deadmau5', + 'license': 'Standard YouTube License', 'title': 'Deadmau5 - Some Chords (HD)', 'alt_title': 'Some Chords', }, @@ -580,6 +603,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'ext': 'mp4', 'upload_date': '20150827', 'uploader_id': 'olympic', + 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/olympic', + 'license': 'Standard YouTube License', 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games', 'uploader': 'Olympics', 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games', @@ -597,8 +622,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'stretched_ratio': 16 / 9., 'upload_date': '20110310', 'uploader_id': 'AllenMeow', + 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/AllenMeow', 'description': 'made by Wacom from Korea | 字幕&加油添醋 by TY\'s Allen | 感謝heylisa00cavey1001同學熱情提供梗及翻譯', 'uploader': '孫艾倫', + 'license': 'Standard YouTube License', 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人', }, }, @@ -629,7 +656,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'description': 'md5:116377fd2963b81ec4ce64b542173306', 'upload_date': '20150625', 'uploader_id': 'dorappi2000', + 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/dorappi2000', 'uploader': 'dorappi2000', + 'license': 'Standard YouTube License', 'formats': 'mincount:33', }, }, @@ -644,6 +673,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'uploader': 'Airtek', 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.', 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ', + 'license': 'Standard YouTube License', 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015', }, 'params': { @@ -668,6 +698,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'upload_date': '20150721', 'uploader': 'Beer Games Beer', 'uploader_id': 'beergamesbeer', + 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/beergamesbeer', + 'license': 'Standard YouTube License', }, }, { 'info_dict': { @@ -678,6 +710,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'upload_date': '20150721', 'uploader': 'Beer Games Beer', 'uploader_id': 'beergamesbeer', + 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/beergamesbeer', + 'license': 'Standard YouTube License', }, }, { 'info_dict': { @@ -688,6 +722,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'upload_date': '20150721', 'uploader': 'Beer Games Beer', 'uploader_id': 'beergamesbeer', + 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/beergamesbeer', + 'license': 'Standard YouTube License', }, }, { 'info_dict': { @@ -698,6 +734,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'upload_date': '20150721', 'uploader': 'Beer Games Beer', 'uploader_id': 'beergamesbeer', + 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/beergamesbeer', + 'license': 'Standard YouTube License', }, }], 'params': { @@ -731,7 +769,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a', 'upload_date': '20151119', 'uploader_id': 'IronSoulElf', + 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/IronSoulElf', 'uploader': 'IronSoulElf', + 'license': 'Standard YouTube License', 'creator': 'Todd Haberman, Daniel Law Heath & Aaron Kaplan', }, 'params': { @@ -760,6 +800,42 @@ class YoutubeIE(YoutubeBaseInfoExtractor): }, }, { + # Video licensed under Creative Commons + 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA', + 'info_dict': { + 'id': 'M4gD1WSo5mA', + 'ext': 'mp4', + 'title': 'md5:e41008789470fc2533a3252216f1c1d1', + 'description': 'md5:a677553cf0840649b731a3024aeff4cc', + 'upload_date': '20150127', + 'uploader_id': 'BerkmanCenter', + 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter', + 'uploader': 'BerkmanCenter', + 'license': 'Creative Commons Attribution license (reuse allowed)', + }, + 'params': { + 'skip_download': True, + }, + }, + { + # Channel-like uploader_url + 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg', + 'info_dict': { + 'id': 'eQcmzGIKrzg', + 'ext': 'mp4', + 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders', + 'description': 'md5:dda0d780d5a6e120758d1711d062a867', + 'upload_date': '20151119', + 'uploader': 'Bernie 2016', + 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg', + 'uploader_url': 're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg', + 'license': 'Creative Commons Attribution license (reuse allowed)', + }, + 'params': { + 'skip_download': True, + }, + }, + { 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;v=V36LpHqtcDY', 'only_matching': True, } @@ -975,40 +1051,67 @@ class YoutubeIE(YoutubeBaseInfoExtractor): return {} try: args = player_config['args'] - caption_url = args['ttsurl'] - if not caption_url: - self._downloader.report_warning(err_msg) - return {} - timestamp = args['timestamp'] - # We get the available subtitles - list_params = compat_urllib_parse.urlencode({ - 'type': 'list', - 'tlangs': 1, - 'asrs': 1, - }) - list_url = caption_url + '&' + list_params - caption_list = self._download_xml(list_url, video_id) - original_lang_node = caption_list.find('track') - if original_lang_node is None: - self._downloader.report_warning('Video doesn\'t have automatic captions') - return {} - original_lang = original_lang_node.attrib['lang_code'] - caption_kind = original_lang_node.attrib.get('kind', '') + caption_url = args.get('ttsurl') + if caption_url: + timestamp = args['timestamp'] + # We get the available subtitles + list_params = compat_urllib_parse.urlencode({ + 'type': 'list', + 'tlangs': 1, + 'asrs': 1, + }) + list_url = caption_url + '&' + list_params + caption_list = self._download_xml(list_url, video_id) + original_lang_node = caption_list.find('track') + if original_lang_node is None: + self._downloader.report_warning('Video doesn\'t have automatic captions') + return {} + original_lang = original_lang_node.attrib['lang_code'] + caption_kind = original_lang_node.attrib.get('kind', '') + + sub_lang_list = {} + for lang_node in caption_list.findall('target'): + sub_lang = lang_node.attrib['lang_code'] + sub_formats = [] + for ext in self._SUBTITLE_FORMATS: + params = compat_urllib_parse.urlencode({ + 'lang': original_lang, + 'tlang': sub_lang, + 'fmt': ext, + 'ts': timestamp, + 'kind': caption_kind, + }) + sub_formats.append({ + 'url': caption_url + '&' + params, + 'ext': ext, + }) + sub_lang_list[sub_lang] = sub_formats + return sub_lang_list + + # Some videos don't provide ttsurl but rather caption_tracks and + # caption_translation_languages (e.g. 20LmZk1hakA) + caption_tracks = args['caption_tracks'] + caption_translation_languages = args['caption_translation_languages'] + caption_url = compat_parse_qs(caption_tracks.split(',')[0])['u'][0] + parsed_caption_url = compat_urlparse.urlparse(caption_url) + caption_qs = compat_parse_qs(parsed_caption_url.query) sub_lang_list = {} - for lang_node in caption_list.findall('target'): - sub_lang = lang_node.attrib['lang_code'] + for lang in caption_translation_languages.split(','): + lang_qs = compat_parse_qs(compat_urllib_parse_unquote_plus(lang)) + sub_lang = lang_qs.get('lc', [None])[0] + if not sub_lang: + continue sub_formats = [] for ext in self._SUBTITLE_FORMATS: - params = compat_urllib_parse.urlencode({ - 'lang': original_lang, - 'tlang': sub_lang, - 'fmt': ext, - 'ts': timestamp, - 'kind': caption_kind, + caption_qs.update({ + 'tlang': [sub_lang], + 'fmt': [ext], }) + sub_url = compat_urlparse.urlunparse(parsed_caption_url._replace( + query=compat_urllib_parse.urlencode(caption_qs, True))) sub_formats.append({ - 'url': caption_url + '&' + params, + 'url': sub_url, 'ext': ext, }) sub_lang_list[sub_lang] = sub_formats @@ -1019,6 +1122,29 @@ class YoutubeIE(YoutubeBaseInfoExtractor): self._downloader.report_warning(err_msg) return {} + def _mark_watched(self, video_id, video_info): + playback_url = video_info.get('videostats_playback_base_url', [None])[0] + if not playback_url: + return + parsed_playback_url = compat_urlparse.urlparse(playback_url) + qs = compat_urlparse.parse_qs(parsed_playback_url.query) + + # cpn generation algorithm is reverse engineered from base.js. + # In fact it works even with dummy cpn. + CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_' + cpn = ''.join((CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16))) + + qs.update({ + 'ver': ['2'], + 'cpn': [cpn], + }) + playback_url = compat_urlparse.urlunparse( + parsed_playback_url._replace(query=compat_urllib_parse.urlencode(qs, True))) + + self._download_webpage( + playback_url, video_id, 'Marking watched', + 'Unable to mark watched', fatal=False) + @classmethod def extract_id(cls, url): mobj = re.match(cls._VALID_URL, url, re.VERBOSE) @@ -1245,9 +1371,13 @@ class YoutubeIE(YoutubeBaseInfoExtractor): # uploader_id video_uploader_id = None - mobj = re.search(r'<link itemprop="url" href="http://www.youtube.com/(?:user|channel)/([^"]+)">', video_webpage) + video_uploader_url = None + mobj = re.search( + r'<link itemprop="url" href="(?P<uploader_url>https?://www.youtube.com/(?:user|channel)/(?P<uploader_id>[^"]+))">', + video_webpage) if mobj is not None: - video_uploader_id = mobj.group(1) + video_uploader_id = mobj.group('uploader_id') + video_uploader_url = mobj.group('uploader_url') else: self._downloader.report_warning('unable to extract uploader nickname') @@ -1275,6 +1405,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor): upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split()) upload_date = unified_strdate(upload_date) + video_license = self._html_search_regex( + r'<h4[^>]+class="title"[^>]*>\s*License\s*</h4>\s*<ul[^>]*>\s*<li>(.+?)</li', + video_webpage, 'license', default=None) + m_music = re.search( r'<h4[^>]+class="title"[^>]*>\s*Music\s*</h4>\s*<ul[^>]*>\s*<li>(?P<title>.+?) by (?P<creator>.+?)(?:\(.+?\))?</li', video_webpage) @@ -1348,6 +1482,19 @@ class YoutubeIE(YoutubeBaseInfoExtractor): encoded_url_map = video_info.get('url_encoded_fmt_stream_map', [''])[0] + ',' + video_info.get('adaptive_fmts', [''])[0] if 'rtmpe%3Dyes' in encoded_url_map: raise ExtractorError('rtmpe downloads are not supported, see https://github.com/rg3/youtube-dl/issues/343 for more information.', expected=True) + formats_spec = {} + fmt_list = video_info.get('fmt_list', [''])[0] + if fmt_list: + for fmt in fmt_list.split(','): + spec = fmt.split('/') + if len(spec) > 1: + width_height = spec[1].split('x') + if len(width_height) == 2: + formats_spec[spec[0]] = { + 'resolution': spec[1], + 'width': int_or_none(width_height[0]), + 'height': int_or_none(width_height[1]), + } formats = [] for url_data_str in encoded_url_map.split(','): url_data = compat_parse_qs(url_data_str) @@ -1416,6 +1563,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor): } if format_id in self._formats: dct.update(self._formats[format_id]) + if format_id in formats_spec: + dct.update(formats_spec[format_id]) # Some itags are not included in DASH manifest thus corresponding formats will # lack metadata (see https://github.com/rg3/youtube-dl/pull/5993). @@ -1528,11 +1677,15 @@ class YoutubeIE(YoutubeBaseInfoExtractor): self._sort_formats(formats) + self.mark_watched(video_id, video_info) + return { 'id': video_id, 'uploader': video_uploader, 'uploader_id': video_uploader_id, + 'uploader_url': video_uploader_url, 'upload_date': upload_date, + 'license': video_license, 'creator': video_creator, 'title': video_title, 'alt_title': video_alt_title, diff --git a/youtube_dl/extractor/zdf.py b/youtube_dl/extractor/zdf.py index c619a75e2..81c22a627 100644 --- a/youtube_dl/extractor/zdf.py +++ b/youtube_dl/extractor/zdf.py @@ -137,6 +137,10 @@ class ZDFIE(InfoExtractor): formats.extend(self._extract_smil_formats( video_url, video_id, fatal=False)) elif ext == 'm3u8': + # the certificates are misconfigured (see + # https://github.com/rg3/youtube-dl/issues/8665) + if video_url.startswith('https://'): + continue formats.extend(self._extract_m3u8_formats( video_url, video_id, 'mp4', m3u8_id=format_id, fatal=False)) elif ext == 'f4m': diff --git a/youtube_dl/options.py b/youtube_dl/options.py index 3afa8bb6f..9dd7a8034 100644 --- a/youtube_dl/options.py +++ b/youtube_dl/options.py @@ -171,6 +171,14 @@ def parseOpts(overrideArguments=None): default=False, help='Do not extract the videos of a playlist, only list them.') general.add_option( + '--mark-watched', + action='store_true', dest='mark_watched', default=False, + help='Mark videos watched (YouTube only)') + general.add_option( + '--no-mark-watched', + action='store_false', dest='mark_watched', default=False, + help='Do not mark videos watched (YouTube only)') + general.add_option( '--no-color', '--no-colors', action='store_true', dest='no_color', default=False, diff --git a/youtube_dl/postprocessor/__init__.py b/youtube_dl/postprocessor/__init__.py index 0d8ef6ca2..3ea518399 100644 --- a/youtube_dl/postprocessor/__init__.py +++ b/youtube_dl/postprocessor/__init__.py @@ -6,6 +6,7 @@ from .ffmpeg import ( FFmpegEmbedSubtitlePP, FFmpegExtractAudioPP, FFmpegFixupStretchedPP, + FFmpegFixupM3u8PP, FFmpegFixupM4aPP, FFmpegMergerPP, FFmpegMetadataPP, @@ -26,6 +27,7 @@ __all__ = [ 'ExecAfterDownloadPP', 'FFmpegEmbedSubtitlePP', 'FFmpegExtractAudioPP', + 'FFmpegFixupM3u8PP', 'FFmpegFixupM4aPP', 'FFmpegFixupStretchedPP', 'FFmpegMergerPP', diff --git a/youtube_dl/postprocessor/embedthumbnail.py b/youtube_dl/postprocessor/embedthumbnail.py index e19dbf73d..3bad5a266 100644 --- a/youtube_dl/postprocessor/embedthumbnail.py +++ b/youtube_dl/postprocessor/embedthumbnail.py @@ -40,7 +40,7 @@ class EmbedThumbnailPP(FFmpegPostProcessor): 'Skipping embedding the thumbnail because the file is missing.') return [], info - if info['ext'] == 'mp3': + if info['ext'] in ('mp3', 'mkv'): options = [ '-c', 'copy', '-map', '0', '-map', '1', '-metadata:s:v', 'title="Album cover"', '-metadata:s:v', 'comment="Cover (Front)"'] diff --git a/youtube_dl/postprocessor/ffmpeg.py b/youtube_dl/postprocessor/ffmpeg.py index cc7aaeda3..a8819f258 100644 --- a/youtube_dl/postprocessor/ffmpeg.py +++ b/youtube_dl/postprocessor/ffmpeg.py @@ -404,10 +404,6 @@ class FFmpegMetadataPP(FFmpegPostProcessor): for (name, value) in metadata.items(): options.extend(['-metadata', '%s=%s' % (name, value)]) - # https://github.com/rg3/youtube-dl/issues/8350 - if info.get('protocol') == 'm3u8_native' or info.get('protocol') == 'm3u8' and self._downloader.params.get('hls_prefer_native', False): - options.extend(['-bsf:a', 'aac_adtstoasc']) - self._downloader.to_screen('[ffmpeg] Adding metadata to \'%s\'' % filename) self.run_ffmpeg(filename, temp_filename, options) os.remove(encodeFilename(filename)) @@ -480,6 +476,21 @@ class FFmpegFixupM4aPP(FFmpegPostProcessor): return [], info +class FFmpegFixupM3u8PP(FFmpegPostProcessor): + def run(self, info): + filename = info['filepath'] + temp_filename = prepend_extension(filename, 'temp') + + options = ['-c', 'copy', '-f', 'mp4', '-bsf:a', 'aac_adtstoasc'] + self._downloader.to_screen('[ffmpeg] Fixing malformated aac bitstream in "%s"' % filename) + self.run_ffmpeg(filename, temp_filename, options) + + os.remove(encodeFilename(filename)) + os.rename(encodeFilename(temp_filename), encodeFilename(filename)) + + return [], info + + class FFmpegSubtitlesConvertorPP(FFmpegPostProcessor): def __init__(self, downloader=None, format=None): super(FFmpegSubtitlesConvertorPP, self).__init__(downloader) diff --git a/youtube_dl/postprocessor/xattrpp.py b/youtube_dl/postprocessor/xattrpp.py index 480d48d05..e39ca60aa 100644 --- a/youtube_dl/postprocessor/xattrpp.py +++ b/youtube_dl/postprocessor/xattrpp.py @@ -6,6 +6,7 @@ import sys import errno from .common import PostProcessor +from ..compat import compat_os_name from ..utils import ( check_executable, hyphenate_date, @@ -73,7 +74,7 @@ class XAttrMetadataPP(PostProcessor): raise XAttrMetadataError(e.errno, e.strerror) except ImportError: - if os.name == 'nt': + if compat_os_name == 'nt': # Write xattrs to NTFS Alternate Data Streams: # http://en.wikipedia.org/wiki/NTFS#Alternate_data_streams_.28ADS.29 def write_xattr(path, key, value): @@ -168,7 +169,7 @@ class XAttrMetadataPP(PostProcessor): 'Unable to write extended attributes due to too long values.') else: msg = 'This filesystem doesn\'t support extended attributes. ' - if os.name == 'nt': + if compat_os_name == 'nt': msg += 'You need to use NTFS.' else: msg += '(You may have to enable them in your /etc/fstab)' diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index 672ce05ea..9fd0ec8d5 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -4,6 +4,7 @@ from __future__ import unicode_literals import base64 +import binascii import calendar import codecs import contextlib @@ -159,8 +160,6 @@ if sys.version_info >= (2, 7): def find_xpath_attr(node, xpath, key, val=None): """ Find the xpath xpath[@key=val] """ assert re.match(r'^[a-zA-Z_-]+$', key) - if val: - assert re.match(r'^[a-zA-Z0-9@\s:._-]*$', val) expr = xpath + ('[@%s]' % key if val is None else "[@%s='%s']" % (key, val)) return node.find(expr) else: @@ -466,6 +465,10 @@ def encodeFilename(s, for_subprocess=False): if not for_subprocess and sys.platform == 'win32' and sys.getwindowsversion()[0] >= 5: return s + # Jython assumes filenames are Unicode strings though reported as Python 2.x compatible + if sys.platform.startswith('java'): + return s + return s.encode(get_subprocess_encoding(), 'ignore') @@ -904,9 +907,9 @@ def unified_strdate(date_str, day_first=True): '%d %b %Y', '%B %d %Y', '%b %d %Y', - '%b %dst %Y %I:%M%p', - '%b %dnd %Y %I:%M%p', - '%b %dth %Y %I:%M%p', + '%b %dst %Y %I:%M', + '%b %dnd %Y %I:%M', + '%b %dth %Y %I:%M', '%Y %m %d', '%Y-%m-%d', '%Y/%m/%d', @@ -1216,13 +1219,23 @@ if sys.platform == 'win32': raise OSError('Unlocking file failed: %r' % ctypes.FormatError()) else: - import fcntl + # Some platforms, such as Jython, is missing fcntl + try: + import fcntl - def _lock_file(f, exclusive): - fcntl.flock(f, fcntl.LOCK_EX if exclusive else fcntl.LOCK_SH) + def _lock_file(f, exclusive): + fcntl.flock(f, fcntl.LOCK_EX if exclusive else fcntl.LOCK_SH) - def _unlock_file(f): - fcntl.flock(f, fcntl.LOCK_UN) + def _unlock_file(f): + fcntl.flock(f, fcntl.LOCK_UN) + except ImportError: + UNSUPPORTED_MSG = 'file locking is not supported on this platform' + + def _lock_file(f, exclusive): + raise IOError(UNSUPPORTED_MSG) + + def _unlock_file(f): + raise IOError(UNSUPPORTED_MSG) class locked_file(object): @@ -1303,6 +1316,17 @@ def format_bytes(bytes): return '%.2f%s' % (converted, suffix) +def lookup_unit_table(unit_table, s): + units_re = '|'.join(re.escape(u) for u in unit_table) + m = re.match( + r'(?P<num>[0-9]+(?:[,.][0-9]*)?)\s*(?P<unit>%s)' % units_re, s) + if not m: + return None + num_str = m.group('num').replace(',', '.') + mult = unit_table[m.group('unit')] + return int(float(num_str) * mult) + + def parse_filesize(s): if s is None: return None @@ -1346,15 +1370,28 @@ def parse_filesize(s): 'Yb': 1000 ** 8, } - units_re = '|'.join(re.escape(u) for u in _UNIT_TABLE) - m = re.match( - r'(?P<num>[0-9]+(?:[,.][0-9]*)?)\s*(?P<unit>%s)' % units_re, s) - if not m: + return lookup_unit_table(_UNIT_TABLE, s) + + +def parse_count(s): + if s is None: return None - num_str = m.group('num').replace(',', '.') - mult = _UNIT_TABLE[m.group('unit')] - return int(float(num_str) * mult) + s = s.strip() + + if re.match(r'^[\d,.]+$', s): + return str_to_int(s) + + _UNIT_TABLE = { + 'k': 1000, + 'K': 1000, + 'm': 1000 ** 2, + 'M': 1000 ** 2, + 'kk': 1000 ** 2, + 'KK': 1000 ** 2, + } + + return lookup_unit_table(_UNIT_TABLE, s) def month_by_name(name): @@ -1386,6 +1423,12 @@ def fix_xml_ampersands(xml_str): def setproctitle(title): assert isinstance(title, compat_str) + + # ctypes in Jython is not complete + # http://bugs.jython.org/issue2148 + if sys.platform.startswith('java'): + return + try: libc = ctypes.cdll.LoadLibrary('libc.so.6') except OSError: @@ -1569,9 +1612,12 @@ class PagedList(object): class OnDemandPagedList(PagedList): - def __init__(self, pagefunc, pagesize): + def __init__(self, pagefunc, pagesize, use_cache=False): self._pagefunc = pagefunc self._pagesize = pagesize + self._use_cache = use_cache + if use_cache: + self._cache = {} def getslice(self, start=0, end=None): res = [] @@ -1581,7 +1627,13 @@ class OnDemandPagedList(PagedList): if start >= nextfirstid: continue - page_results = list(self._pagefunc(pagenum)) + page_results = None + if self._use_cache: + page_results = self._cache.get(pagenum) + if page_results is None: + page_results = list(self._pagefunc(pagenum)) + if self._use_cache: + self._cache[pagenum] = page_results startv = ( start % self._pagesize @@ -1711,6 +1763,15 @@ def urlencode_postdata(*args, **kargs): return compat_urllib_parse.urlencode(*args, **kargs).encode('ascii') +def update_url_query(url, query): + parsed_url = compat_urlparse.urlparse(url) + qs = compat_parse_qs(parsed_url.query) + qs.update(query) + qs = encode_dict(qs) + return compat_urlparse.urlunparse(parsed_url._replace( + query=compat_urllib_parse.urlencode(qs, True))) + + def encode_dict(d, encoding='utf-8'): def encode(v): return v.encode(encoding) if isinstance(v, compat_basestring) else v @@ -1835,11 +1896,21 @@ def error_to_compat_str(err): def mimetype2ext(mt): + ext = { + 'audio/mp4': 'm4a', + }.get(mt) + if ext is not None: + return ext + _, _, res = mt.rpartition('/') return { '3gpp': '3gp', + 'smptett+xml': 'tt', + 'srt': 'srt', + 'ttaf+xml': 'dfxp', 'ttml+xml': 'ttml', + 'vtt': 'vtt', 'x-flv': 'flv', 'x-mp4-fragmented': 'mp4', 'x-ms-wmv': 'wmv', @@ -2582,3 +2653,58 @@ class PerRequestProxyHandler(compat_urllib_request.ProxyHandler): return None # No Proxy return compat_urllib_request.ProxyHandler.proxy_open( self, req, proxy, type) + + +def ohdave_rsa_encrypt(data, exponent, modulus): + ''' + Implement OHDave's RSA algorithm. See http://www.ohdave.com/rsa/ + + Input: + data: data to encrypt, bytes-like object + exponent, modulus: parameter e and N of RSA algorithm, both integer + Output: hex string of encrypted data + + Limitation: supports one block encryption only + ''' + + payload = int(binascii.hexlify(data[::-1]), 16) + encrypted = pow(payload, exponent, modulus) + return '%x' % encrypted + + +def encode_base_n(num, n, table=None): + FULL_TABLE = '0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ' + if not table: + table = FULL_TABLE[:n] + + if n > len(table): + raise ValueError('base %d exceeds table length %d' % (n, len(table))) + + if num == 0: + return table[0] + + ret = '' + while num: + ret = table[num % n] + ret + num = num // n + return ret + + +def decode_packed_codes(code): + mobj = re.search( + r"}\('(.+)',(\d+),(\d+),'([^']+)'\.split\('\|'\)", + code) + obfucasted_code, base, count, symbols = mobj.groups() + base = int(base) + count = int(count) + symbols = symbols.split('|') + symbol_table = {} + + while count: + count -= 1 + base_n_count = encode_base_n(count, base) + symbol_table[base_n_count] = symbols[count] or base_n_count + + return re.sub( + r'\b(\w+)\b', lambda mobj: symbol_table[mobj.group(0)], + obfucasted_code) diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 9aca8001a..246f5740d 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2016.02.13' +__version__ = '2016.03.06' |