diff options
| -rw-r--r-- | setup.py | 3 | ||||
| -rw-r--r-- | test/test_download.py | 20 | ||||
| -rw-r--r-- | test/test_write_info_json.py | 12 | ||||
| -rw-r--r-- | test/test_youtube_lists.py | 22 | ||||
| -rw-r--r-- | test/test_youtube_subtitles.py | 22 | ||||
| -rw-r--r-- | test/tests.json | 37 | ||||
| -rw-r--r-- | youtube_dl/FileDownloader.py | 542 | ||||
| -rw-r--r-- | youtube_dl/YoutubeDL.py | 595 | ||||
| -rw-r--r-- | youtube_dl/__init__.py | 41 | ||||
| -rw-r--r-- | youtube_dl/extractor/__init__.py | 2 | ||||
| -rw-r--r-- | youtube_dl/extractor/common.py | 2 | ||||
| -rw-r--r-- | youtube_dl/extractor/mtv.py | 8 | ||||
| -rw-r--r-- | youtube_dl/extractor/vevo.py | 44 | ||||
| -rw-r--r-- | youtube_dl/extractor/youtube.py | 19 | ||||
| -rw-r--r-- | youtube_dl/utils.py | 2 | ||||
| -rw-r--r-- | youtube_dl/version.py | 2 |
16 files changed, 775 insertions, 598 deletions
@@ -3,7 +3,6 @@ from __future__ import print_function -from glob import glob import pkg_resources import sys @@ -26,8 +25,6 @@ py2exe_options = { "optimize": 2, "dist_dir": '.', "dll_excludes": ['w9xpopen.exe'], - "includes": [m.replace('\\', '.').replace('/', '.')[:-3] - for m in glob('youtube_dl/*/*.py')] } py2exe_console = [{ "script": "./youtube_dl/__main__.py", diff --git a/test/test_download.py b/test/test_download.py index 8d8698478..067bde4bb 100644 --- a/test/test_download.py +++ b/test/test_download.py @@ -13,7 +13,7 @@ import binascii # Allow direct execution sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) -import youtube_dl.FileDownloader +import youtube_dl.YoutubeDL import youtube_dl.extractor from youtube_dl.utils import * @@ -40,17 +40,17 @@ def _try_rm(filename): md5 = lambda s: hashlib.md5(s.encode('utf-8')).hexdigest() -class FileDownloader(youtube_dl.FileDownloader): +class YoutubeDL(youtube_dl.YoutubeDL): def __init__(self, *args, **kwargs): self.to_stderr = self.to_screen self.processed_info_dicts = [] - return youtube_dl.FileDownloader.__init__(self, *args, **kwargs) + super(YoutubeDL, self).__init__(*args, **kwargs) def report_warning(self, message): # Don't accept warnings during tests raise ExtractorError(message) def process_info(self, info_dict): self.processed_info_dicts.append(info_dict) - return youtube_dl.FileDownloader.process_info(self, info_dict) + return super(YoutubeDL, self).process_info(info_dict) def _file_md5(fn): with open(fn, 'rb') as f: @@ -86,14 +86,14 @@ def generator(test_case): params = self.parameters.copy() params.update(test_case.get('params', {})) - fd = FileDownloader(params) + ydl = YoutubeDL(params) for ie in youtube_dl.extractor.gen_extractors(): - fd.add_info_extractor(ie) + ydl.add_info_extractor(ie) finished_hook_called = set() def _hook(status): if status['status'] == 'finished': finished_hook_called.add(status['filename']) - fd.add_progress_hook(_hook) + ydl.fd.add_progress_hook(_hook) test_cases = test_case.get('playlist', [test_case]) for tc in test_cases: @@ -103,7 +103,7 @@ def generator(test_case): try: for retry in range(1, RETRIES + 1): try: - fd.download([test_case['url']]) + ydl.download([test_case['url']]) except (DownloadError, ExtractorError) as err: if retry == RETRIES: raise @@ -153,9 +153,11 @@ def generator(test_case): return test_template ### And add them to TestDownload -for test_case in defs: +for n, test_case in enumerate(defs): test_method = generator(test_case) test_method.__name__ = "test_{0}".format(test_case["name"]) + if getattr(TestDownload, test_method.__name__, False): + test_method.__name__ = "test_{0}_{1}".format(test_case["name"], n) setattr(TestDownload, test_method.__name__, test_method) del test_method diff --git a/test/test_write_info_json.py b/test/test_write_info_json.py index b5eca7649..de6d5180f 100644 --- a/test/test_write_info_json.py +++ b/test/test_write_info_json.py @@ -9,7 +9,7 @@ import unittest # Allow direct execution sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) -import youtube_dl.FileDownloader +import youtube_dl.YoutubeDL import youtube_dl.extractor from youtube_dl.utils import * @@ -22,9 +22,9 @@ proxy_handler = compat_urllib_request.ProxyHandler() opener = compat_urllib_request.build_opener(proxy_handler, cookie_processor, YoutubeDLHandler()) compat_urllib_request.install_opener(opener) -class FileDownloader(youtube_dl.FileDownloader): +class YoutubeDL(youtube_dl.YoutubeDL): def __init__(self, *args, **kwargs): - youtube_dl.FileDownloader.__init__(self, *args, **kwargs) + super(YoutubeDL, self).__init__(*args, **kwargs) self.to_stderr = self.to_screen with io.open(PARAMETERS_FILE, encoding='utf-8') as pf: @@ -49,9 +49,9 @@ class TestInfoJSON(unittest.TestCase): def test_info_json(self): ie = youtube_dl.extractor.YoutubeIE() - fd = FileDownloader(params) - fd.add_info_extractor(ie) - fd.download([TEST_ID]) + ydl = YoutubeDL(params) + ydl.add_info_extractor(ie) + ydl.download([TEST_ID]) self.assertTrue(os.path.exists(INFO_JSON_FILE)) with io.open(INFO_JSON_FILE, 'r', encoding='utf-8') as jsonf: jd = json.load(jsonf) diff --git a/test/test_youtube_lists.py b/test/test_youtube_lists.py index 2c46edfa6..320b44082 100644 --- a/test/test_youtube_lists.py +++ b/test/test_youtube_lists.py @@ -10,7 +10,7 @@ sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) from youtube_dl.extractor import YoutubeUserIE, YoutubePlaylistIE, YoutubeIE, YoutubeChannelIE from youtube_dl.utils import * -from youtube_dl.FileDownloader import FileDownloader +from youtube_dl import YoutubeDL PARAMETERS_FILE = os.path.join(os.path.dirname(os.path.abspath(__file__)), "parameters.json") with io.open(PARAMETERS_FILE, encoding='utf-8') as pf: @@ -23,7 +23,7 @@ proxy_handler = compat_urllib_request.ProxyHandler() opener = compat_urllib_request.build_opener(proxy_handler, cookie_processor, YoutubeDLHandler()) compat_urllib_request.install_opener(opener) -class FakeDownloader(FileDownloader): +class FakeYDL(YoutubeDL): def __init__(self): self.result = [] self.params = parameters @@ -41,7 +41,7 @@ class TestYoutubeLists(unittest.TestCase): self.assertEqual(info['_type'], 'playlist') def test_youtube_playlist(self): - dl = FakeDownloader() + dl = FakeYDL() ie = YoutubePlaylistIE(dl) result = ie.extract('https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re')[0] self.assertIsPlaylist(result) @@ -50,13 +50,13 @@ class TestYoutubeLists(unittest.TestCase): self.assertEqual(ytie_results, [ 'bV9L5Ht9LgY', 'FXxLjLQi3Fg', 'tU3Bgo5qJZE']) def test_issue_673(self): - dl = FakeDownloader() + dl = FakeYDL() ie = YoutubePlaylistIE(dl) result = ie.extract('PLBB231211A4F62143')[0] self.assertTrue(len(result['entries']) > 25) def test_youtube_playlist_long(self): - dl = FakeDownloader() + dl = FakeYDL() ie = YoutubePlaylistIE(dl) result = ie.extract('https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q')[0] self.assertIsPlaylist(result) @@ -64,7 +64,7 @@ class TestYoutubeLists(unittest.TestCase): def test_youtube_playlist_with_deleted(self): #651 - dl = FakeDownloader() + dl = FakeYDL() ie = YoutubePlaylistIE(dl) result = ie.extract('https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC')[0] ytie_results = [YoutubeIE()._extract_id(url['url']) for url in result['entries']] @@ -72,14 +72,14 @@ class TestYoutubeLists(unittest.TestCase): self.assertFalse('KdPEApIVdWM' in ytie_results) def test_youtube_playlist_empty(self): - dl = FakeDownloader() + dl = FakeYDL() ie = YoutubePlaylistIE(dl) result = ie.extract('https://www.youtube.com/playlist?list=PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx')[0] self.assertIsPlaylist(result) self.assertEqual(len(result['entries']), 0) def test_youtube_course(self): - dl = FakeDownloader() + dl = FakeYDL() ie = YoutubePlaylistIE(dl) # TODO find a > 100 (paginating?) videos course result = ie.extract('https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')[0] @@ -89,7 +89,7 @@ class TestYoutubeLists(unittest.TestCase): self.assertEqual(YoutubeIE()._extract_id(entries[-1]['url']), 'rYefUsYuEp0') def test_youtube_channel(self): - dl = FakeDownloader() + dl = FakeYDL() ie = YoutubeChannelIE(dl) #test paginated channel result = ie.extract('https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w')[0] @@ -99,13 +99,13 @@ class TestYoutubeLists(unittest.TestCase): self.assertTrue(len(result['entries']) >= 18) def test_youtube_user(self): - dl = FakeDownloader() + dl = FakeYDL() ie = YoutubeUserIE(dl) result = ie.extract('https://www.youtube.com/user/TheLinuxFoundation')[0] self.assertTrue(len(result['entries']) >= 320) def test_youtube_safe_search(self): - dl = FakeDownloader() + dl = FakeYDL() ie = YoutubePlaylistIE(dl) result = ie.extract('PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl')[0] self.assertEqual(len(result['entries']), 2) diff --git a/test/test_youtube_subtitles.py b/test/test_youtube_subtitles.py index 129e23963..e8f5e4ae7 100644 --- a/test/test_youtube_subtitles.py +++ b/test/test_youtube_subtitles.py @@ -12,7 +12,7 @@ sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) from youtube_dl.extractor import YoutubeIE from youtube_dl.utils import * -from youtube_dl import FileDownloader +from youtube_dl import YoutubeDL PARAMETERS_FILE = os.path.join(os.path.dirname(os.path.abspath(__file__)), "parameters.json") with io.open(PARAMETERS_FILE, encoding='utf-8') as pf: @@ -25,7 +25,7 @@ proxy_handler = compat_urllib_request.ProxyHandler() opener = compat_urllib_request.build_opener(proxy_handler, cookie_processor, YoutubeDLHandler()) compat_urllib_request.install_opener(opener) -class FakeDownloader(FileDownloader): +class FakeYDL(YoutubeDL): def __init__(self): self.result = [] # Different instances of the downloader can't share the same dictionary @@ -42,27 +42,27 @@ md5 = lambda s: hashlib.md5(s.encode('utf-8')).hexdigest() class TestYoutubeSubtitles(unittest.TestCase): def setUp(self): - DL = FakeDownloader() + DL = FakeYDL() DL.params['allsubtitles'] = False DL.params['writesubtitles'] = False DL.params['subtitlesformat'] = 'srt' DL.params['listsubtitles'] = False def test_youtube_no_subtitles(self): - DL = FakeDownloader() + DL = FakeYDL() DL.params['writesubtitles'] = False IE = YoutubeIE(DL) info_dict = IE.extract('QRS8MkLhQmM') subtitles = info_dict[0]['subtitles'] self.assertEqual(subtitles, None) def test_youtube_subtitles(self): - DL = FakeDownloader() + DL = FakeYDL() DL.params['writesubtitles'] = True IE = YoutubeIE(DL) info_dict = IE.extract('QRS8MkLhQmM') sub = info_dict[0]['subtitles'][0] self.assertEqual(md5(sub[2]), '4cd9278a35ba2305f47354ee13472260') def test_youtube_subtitles_it(self): - DL = FakeDownloader() + DL = FakeYDL() DL.params['writesubtitles'] = True DL.params['subtitleslang'] = 'it' IE = YoutubeIE(DL) @@ -70,7 +70,7 @@ class TestYoutubeSubtitles(unittest.TestCase): sub = info_dict[0]['subtitles'][0] self.assertEqual(md5(sub[2]), '164a51f16f260476a05b50fe4c2f161d') def test_youtube_onlysubtitles(self): - DL = FakeDownloader() + DL = FakeYDL() DL.params['writesubtitles'] = True DL.params['onlysubtitles'] = True IE = YoutubeIE(DL) @@ -78,14 +78,14 @@ class TestYoutubeSubtitles(unittest.TestCase): sub = info_dict[0]['subtitles'][0] self.assertEqual(md5(sub[2]), '4cd9278a35ba2305f47354ee13472260') def test_youtube_allsubtitles(self): - DL = FakeDownloader() + DL = FakeYDL() DL.params['allsubtitles'] = True IE = YoutubeIE(DL) info_dict = IE.extract('QRS8MkLhQmM') subtitles = info_dict[0]['subtitles'] self.assertEqual(len(subtitles), 13) def test_youtube_subtitles_format(self): - DL = FakeDownloader() + DL = FakeYDL() DL.params['writesubtitles'] = True DL.params['subtitlesformat'] = 'sbv' IE = YoutubeIE(DL) @@ -93,13 +93,13 @@ class TestYoutubeSubtitles(unittest.TestCase): sub = info_dict[0]['subtitles'][0] self.assertEqual(md5(sub[2]), '13aeaa0c245a8bed9a451cb643e3ad8b') def test_youtube_list_subtitles(self): - DL = FakeDownloader() + DL = FakeYDL() DL.params['listsubtitles'] = True IE = YoutubeIE(DL) info_dict = IE.extract('QRS8MkLhQmM') self.assertEqual(info_dict, None) def test_youtube_automatic_captions(self): - DL = FakeDownloader() + DL = FakeYDL() DL.params['writesubtitles'] = True DL.params['subtitleslang'] = 'it' IE = YoutubeIE(DL) diff --git a/test/tests.json b/test/tests.json index 01367b0fb..f6a70f153 100644 --- a/test/tests.json +++ b/test/tests.json @@ -12,6 +12,32 @@ } }, { + "name": "Youtube", + "url": "http://www.youtube.com/watch?v=1ltcDfZMA3U", + "file": "1ltcDfZMA3U.flv", + "note": "Test VEVO video (#897)", + "info_dict": { + "upload_date": "20070518", + "title": "Maps - It Will Find You", + "description": "Music video by Maps performing It Will Find You.", + "uploader": "MuteUSA", + "uploader_id": "MuteUSA" + } + }, + { + "name": "Youtube", + "url": "http://www.youtube.com/watch?v=UxxajLWwzqY", + "file": "UxxajLWwzqY.mp4", + "note": "Test generic use_cipher_signature video (#897)", + "info_dict": { + "upload_date": "20120506", + "title": "Icona Pop - I Love It (feat. Charli XCX) [OFFICIAL VIDEO]", + "description": "md5:b085c9804f5ab69f4adea963a2dceb3c", + "uploader": "IconaPop", + "uploader_id": "IconaPop" + } + }, + { "name": "Dailymotion", "md5": "392c4b85a60a90dc4792da41ce3144eb", "url": "http://www.dailymotion.com/video/x33vw9_tutoriel-de-youtubeur-dl-des-video_tech", @@ -649,5 +675,16 @@ "info_dict": { "title": "When Girls Act Like D-Bags" } + }, + { + "name": "Vevo", + "url": "http://www.vevo.com/watch/hurts/somebody-to-die-for/GB1101300280", + "file": "GB1101300280.mp4", + "md5": "06bea460acb744eab74a9d7dcb4bfd61", + "info_dict": { + "title": "Somebody To Die For", + "upload_date": "20130624", + "uploader": "Hurts" + } } ] diff --git a/youtube_dl/FileDownloader.py b/youtube_dl/FileDownloader.py index f21c66c29..445f3e85e 100644 --- a/youtube_dl/FileDownloader.py +++ b/youtube_dl/FileDownloader.py @@ -1,9 +1,6 @@ import math -import io import os import re -import shutil -import socket import subprocess import sys import time @@ -13,103 +10,45 @@ if os.name == 'nt': import ctypes from .utils import * -from .extractor import get_info_extractor class FileDownloader(object): """File Downloader class. File downloader objects are the ones responsible of downloading the - actual video file and writing it to disk if the user has requested - it, among some other tasks. In most cases there should be one per - program. As, given a video URL, the downloader doesn't know how to - extract all the needed information, task that InfoExtractors do, it - has to pass the URL to one of them. - - For this, file downloader objects have a method that allows - InfoExtractors to be registered in a given order. When it is passed - a URL, the file downloader handles it to the first InfoExtractor it - finds that reports being able to handle it. The InfoExtractor extracts - all the information about the video or videos the URL refers to, and - asks the FileDownloader to process the video information, possibly - downloading the video. + actual video file and writing it to disk. File downloaders accept a lot of parameters. In order not to saturate the object constructor with arguments, it receives a dictionary of - options instead. These options are available through the params - attribute for the InfoExtractors to use. The FileDownloader also - registers itself as the downloader in charge for the InfoExtractors - that are added to it, so this is a "mutual registration". + options instead. Available options: - username: Username for authentication purposes. - password: Password for authentication purposes. - usenetrc: Use netrc for authentication instead. + verbose: Print additional info to stdout. quiet: Do not print messages to stdout. - forceurl: Force printing final URL. - forcetitle: Force printing title. - forceid: Force printing ID. - forcethumbnail: Force printing thumbnail URL. - forcedescription: Force printing description. - forcefilename: Force printing final filename. - simulate: Do not download the video files. - format: Video format code. - format_limit: Highest quality format to try. - outtmpl: Template for output names. - restrictfilenames: Do not allow "&" and spaces in file names - ignoreerrors: Do not stop on download errors. ratelimit: Download speed limit, in bytes/sec. - nooverwrites: Prevent overwriting files. retries: Number of times to retry for HTTP error 5xx buffersize: Size of download buffer in bytes. noresizebuffer: Do not automatically resize the download buffer. continuedl: Try to continue downloads if possible. noprogress: Do not print the progress bar. - playliststart: Playlist item to start at. - playlistend: Playlist item to end at. - matchtitle: Download only matching titles. - rejecttitle: Reject downloads for matching titles. logtostderr: Log messages to stderr instead of stdout. consoletitle: Display progress in console window's titlebar. nopart: Do not use temporary .part files. updatetime: Use the Last-modified header to set output file timestamps. - writedescription: Write the video description to a .description file - writeinfojson: Write the video description to a .info.json file - writethumbnail: Write the thumbnail image to a file - writesubtitles: Write the video subtitles to a file - allsubtitles: Downloads all the subtitles of the video - listsubtitles: Lists all available subtitles for the video - subtitlesformat: Subtitle format [sbv/srt] (default=srt) - subtitleslang: Language of the subtitles to download test: Download only first bytes to test the downloader. - keepvideo: Keep the video file after post-processing min_filesize: Skip files smaller than this size max_filesize: Skip files larger than this size - daterange: A DateRange object, download only if the upload_date is in the range. - skip_download: Skip the actual download of the video file """ params = None - _ies = [] - _pps = [] - _download_retcode = None - _num_downloads = None - _screen_file = None - def __init__(self, params): + def __init__(self, ydl, params): """Create a FileDownloader object with the given options.""" - self._ies = [] - self._pps = [] + self.ydl = ydl self._progress_hooks = [] - self._download_retcode = 0 - self._num_downloads = 0 - self._screen_file = [sys.stdout, sys.stderr][params.get('logtostderr', False)] self.params = params - if '%(stitle)s' in self.params['outtmpl']: - self.report_warning(u'%(stitle)s is deprecated. Use the %(title)s and the --restrict-filenames flag(which also secures %(uploader)s et al) instead.') - @staticmethod def format_bytes(bytes): if bytes is None: @@ -174,34 +113,11 @@ class FileDownloader(object): multiplier = 1024.0 ** 'bkmgtpezy'.index(matchobj.group(2).lower()) return int(round(number * multiplier)) - def add_info_extractor(self, ie): - """Add an InfoExtractor object to the end of the list.""" - self._ies.append(ie) - ie.set_downloader(self) - - def add_post_processor(self, pp): - """Add a PostProcessor object to the end of the chain.""" - self._pps.append(pp) - pp.set_downloader(self) - - def to_screen(self, message, skip_eol=False): - """Print message to stdout if not in quiet mode.""" - assert type(message) == type(u'') - if not self.params.get('quiet', False): - terminator = [u'\n', u''][skip_eol] - output = message + terminator - if 'b' in getattr(self._screen_file, 'mode', '') or sys.version_info[0] < 3: # Python 2 lies about the mode of sys.stdout/sys.stderr - output = output.encode(preferredencoding(), 'ignore') - self._screen_file.write(output) - self._screen_file.flush() + def to_screen(self, *args, **kargs): + self.ydl.to_screen(*args, **kargs) def to_stderr(self, message): - """Print message to stderr.""" - assert type(message) == type(u'') - output = message + u'\n' - if 'b' in getattr(self._screen_file, 'mode', '') or sys.version_info[0] < 3: # Python 2 lies about the mode of sys.stdout/sys.stderr - output = output.encode(preferredencoding()) - sys.stderr.write(output) + self.ydl.to_screen(message) def to_cons_title(self, message): """Set console/terminal window title to message.""" @@ -214,63 +130,14 @@ class FileDownloader(object): elif 'TERM' in os.environ: self.to_screen('\033]0;%s\007' % message, skip_eol=True) - def fixed_template(self): - """Checks if the output template is fixed.""" - return (re.search(u'(?u)%\\(.+?\\)s', self.params['outtmpl']) is None) - - def trouble(self, message=None, tb=None): - """Determine action to take when a download problem appears. + def trouble(self, *args, **kargs): + self.ydl.trouble(*args, **kargs) - Depending on if the downloader has been configured to ignore - download errors or not, this method may throw an exception or - not when errors are found, after printing the message. + def report_warning(self, *args, **kargs): + self.ydl.report_warning(*args, **kargs) - tb, if given, is additional traceback information. - """ - if message is not None: - self.to_stderr(message) - if self.params.get('verbose'): - if tb is None: - if sys.exc_info()[0]: # if .trouble has been called from an except block - tb = u'' - if hasattr(sys.exc_info()[1], 'exc_info') and sys.exc_info()[1].exc_info[0]: - tb += u''.join(traceback.format_exception(*sys.exc_info()[1].exc_info)) - tb += compat_str(traceback.format_exc()) - else: - tb_data = traceback.format_list(traceback.extract_stack()) - tb = u''.join(tb_data) - self.to_stderr(tb) - if not self.params.get('ignoreerrors', False): - if sys.exc_info()[0] and hasattr(sys.exc_info()[1], 'exc_info') and sys.exc_info()[1].exc_info[0]: - exc_info = sys.exc_info()[1].exc_info - else: - exc_info = sys.exc_info() - raise DownloadError(message, exc_info) - self._download_retcode = 1 - - def report_warning(self, 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': - _msg_header=u'\033[0;33mWARNING:\033[0m' - else: - _msg_header=u'WARNING:' - warning_message=u'%s %s' % (_msg_header,message) - self.to_stderr(warning_message) - - def report_error(self, message, tb=None): - ''' - Do the same as trouble, but prefixes the message with 'ERROR:', colored - in red if stderr is a tty file. - ''' - if sys.stderr.isatty() and os.name != 'nt': - _msg_header = u'\033[0;31mERROR:\033[0m' - else: - _msg_header = u'ERROR:' - error_message = u'%s %s' % (_msg_header, message) - self.trouble(error_message, tb) + def report_error(self, *args, **kargs): + self.ydl.error(*args, **kargs) def slow_down(self, start_time, byte_counter): """Sleep if the download speed is over the rate limit.""" @@ -326,18 +193,6 @@ class FileDownloader(object): pass return filetime - def report_writedescription(self, descfn): - """ Report that the description file is being written """ - self.to_screen(u'[info] Writing video description to: ' + descfn) - - def report_writesubtitles(self, sub_filename): - """ Report that the subtitles file is being written """ - self.to_screen(u'[info] Writing video subtitles to: ' + sub_filename) - - def report_writeinfojson(self, infofn): - """ Report that the metadata file has been written """ - self.to_screen(u'[info] Video description metadata as JSON to: ' + infofn) - def report_destination(self, filename): """Report destination filename.""" self.to_screen(u'[download] Destination: ' + filename) @@ -382,375 +237,6 @@ class FileDownloader(object): else: self.to_screen(u'') - def increment_downloads(self): - """Increment the ordinal that assigns a number to each file.""" - self._num_downloads += 1 - - def prepare_filename(self, info_dict): - """Generate the output filename.""" - try: - template_dict = dict(info_dict) - - template_dict['epoch'] = int(time.time()) - autonumber_size = self.params.get('autonumber_size') - if autonumber_size is None: - autonumber_size = 5 - autonumber_templ = u'%0' + str(autonumber_size) + u'd' - template_dict['autonumber'] = autonumber_templ % self._num_downloads - if template_dict['playlist_index'] is not None: - template_dict['playlist_index'] = u'%05d' % template_dict['playlist_index'] - - sanitize = lambda k,v: sanitize_filename( - u'NA' if v is None else compat_str(v), - restricted=self.params.get('restrictfilenames'), - is_id=(k==u'id')) - template_dict = dict((k, sanitize(k, v)) for k,v in template_dict.items()) - - filename = self.params['outtmpl'] % template_dict - return filename - except KeyError as err: - self.report_error(u'Erroneous output template') - return None - except ValueError as err: - self.report_error(u'Insufficient system charset ' + repr(preferredencoding())) - return None - - def _match_entry(self, info_dict): - """ Returns None iff the file should be downloaded """ - - title = info_dict['title'] - matchtitle = self.params.get('matchtitle', False) - if matchtitle: - if not re.search(matchtitle, title, re.IGNORECASE): - return u'[download] "' + title + '" title did not match pattern "' + matchtitle + '"' - rejecttitle = self.params.get('rejecttitle', False) - if rejecttitle: - if re.search(rejecttitle, title, re.IGNORECASE): - return u'"' + title + '" title matched reject pattern "' + rejecttitle + '"' - date = info_dict.get('upload_date', None) - if date is not None: - dateRange = self.params.get('daterange', DateRange()) - if date not in dateRange: - return u'[download] %s upload date is not in range %s' % (date_from_str(date).isoformat(), dateRange) - return None - - def extract_info(self, url, download=True, ie_key=None, extra_info={}): - ''' - Returns a list with a dictionary for each video we find. - If 'download', also downloads the videos. - extra_info is a dict containing the extra values to add to each result - ''' - - if ie_key: - ie = get_info_extractor(ie_key)() - ie.set_downloader(self) - ies = [ie] - else: - ies = self._ies - - for ie in ies: - if not ie.suitable(url): - continue - - if not ie.working(): - self.report_warning(u'The program functionality for this site has been marked as broken, ' - u'and will probably not work.') - - try: - ie_result = ie.extract(url) - if ie_result is None: # Finished already (backwards compatibility; listformats and friends should be moved here) - break - if isinstance(ie_result, list): - # Backwards compatibility: old IE result format - for result in ie_result: - result.update(extra_info) - ie_result = { - '_type': 'compat_list', - 'entries': ie_result, - } - else: - ie_result.update(extra_info) - if 'extractor' not in ie_result: - ie_result['extractor'] = ie.IE_NAME - return self.process_ie_result(ie_result, download=download) - except ExtractorError as de: # An error we somewhat expected - self.report_error(compat_str(de), de.format_traceback()) - break - except Exception as e: - if self.params.get('ignoreerrors', False): - self.report_error(compat_str(e), tb=compat_str(traceback.format_exc())) - break - else: - raise - else: - self.report_error(u'no suitable InfoExtractor: %s' % url) - - def process_ie_result(self, ie_result, download=True, extra_info={}): - """ - Take the result of the ie(may be modified) and resolve all unresolved - references (URLs, playlist items). - - It will also download the videos if 'download'. - Returns the resolved ie_result. - """ - - result_type = ie_result.get('_type', 'video') # If not given we suppose it's a video, support the default old system - if result_type == 'video': - if 'playlist' not in ie_result: - # It isn't part of a playlist - ie_result['playlist'] = None - ie_result['playlist_index'] = None - if download: - self.process_info(ie_result) - return ie_result - elif result_type == 'url': - # We have to add extra_info to the results because it may be - # contained in a playlist - return self.extract_info(ie_result['url'], - download, - ie_key=ie_result.get('ie_key'), - extra_info=extra_info) - elif result_type == 'playlist': - # We process each entry in the playlist - playlist = ie_result.get('title', None) or ie_result.get('id', None) - self.to_screen(u'[download] Downloading playlist: %s' % playlist) - - playlist_results = [] - - n_all_entries = len(ie_result['entries']) - playliststart = self.params.get('playliststart', 1) - 1 - playlistend = self.params.get('playlistend', -1) - - if playlistend == -1: - entries = ie_result['entries'][playliststart:] - else: - entries = ie_result['entries'][playliststart:playlistend] - - n_entries = len(entries) - - self.to_screen(u"[%s] playlist '%s': Collected %d video ids (downloading %d of them)" % - (ie_result['extractor'], playlist, n_all_entries, n_entries)) - - for i,entry in enumerate(entries,1): - self.to_screen(u'[download] Downloading video #%s of %s' %(i, n_entries)) - extra = { - 'playlist': playlist, - 'playlist_index': i + playliststart, - } - if not 'extractor' in entry: - # We set the extractor, if it's an url it will be set then to - # the new extractor, but if it's already a video we must make - # sure it's present: see issue #877 - entry['extractor'] = ie_result['extractor'] - entry_result = self.process_ie_result(entry, - download=download, - extra_info=extra) - playlist_results.append(entry_result) - ie_result['entries'] = playlist_results - return ie_result - elif result_type == 'compat_list': - def _fixup(r): - r.setdefault('extractor', ie_result['extractor']) - return r - ie_result['entries'] = [ - self.process_ie_result(_fixup(r), download=download) - for r in ie_result['entries'] - ] - return ie_result - else: - raise Exception('Invalid result type: %s' % result_type) - - def process_info(self, info_dict): - """Process a single resolved IE result.""" - - assert info_dict.get('_type', 'video') == 'video' - #We increment the download the download count here to match the previous behaviour. - self.increment_downloads() - - info_dict['fulltitle'] = info_dict['title'] - if len(info_dict['title']) > 200: - info_dict['title'] = info_dict['title'][:197] + u'...' - - # Keep for backwards compatibility - info_dict['stitle'] = info_dict['title'] - - if not 'format' in info_dict: - info_dict['format'] = info_dict['ext'] - - reason = self._match_entry(info_dict) - if reason is not None: - self.to_screen(u'[download] ' + reason) - return - - max_downloads = self.params.get('max_downloads') - if max_downloads is not None: - if self._num_downloads > int(max_downloads): - raise MaxDownloadsReached() - - filename = self.prepare_filename(info_dict) - - # Forced printings - if self.params.get('forcetitle', False): - compat_print(info_dict['title']) - if self.params.get('forceid', False): - compat_print(info_dict['id']) - if self.params.get('forceurl', False): - compat_print(info_dict['url']) - if self.params.get('forcethumbnail', False) and 'thumbnail' in info_dict: - compat_print(info_dict['thumbnail']) - if self.params.get('forcedescription', False) and 'description' in info_dict: - compat_print(info_dict['description']) - if self.params.get('forcefilename', False) and filename is not None: - compat_print(filename) - if self.params.get('forceformat', False): - compat_print(info_dict['format']) - - # Do nothing else if in simulate mode - if self.params.get('simulate', False): - return - - if filename is None: - return - - try: - dn = os.path.dirname(encodeFilename(filename)) - if dn != '' and not os.path.exists(dn): - os.makedirs(dn) - except (OSError, IOError) as err: - self.report_error(u'unable to create directory ' + compat_str(err)) - return - - if self.params.get('writedescription', False): - try: - descfn = filename + u'.description' - self.report_writedescription(descfn) - with io.open(encodeFilename(descfn), 'w', encoding='utf-8') as descfile: - descfile.write(info_dict['description']) - except (OSError, IOError): - self.report_error(u'Cannot write description file ' + descfn) - return - - if self.params.get('writesubtitles', False) and 'subtitles' in info_dict and info_dict['subtitles']: - # subtitles download errors are already managed as troubles in relevant IE - # that way it will silently go on when used with unsupporting IE - subtitle = info_dict['subtitles'][0] - (sub_error, sub_lang, sub) = subtitle - sub_format = self.params.get('subtitlesformat') - if sub_error: - self.report_warning("Some error while getting the subtitles") - else: - try: - sub_filename = filename.rsplit('.', 1)[0] + u'.' + sub_lang + u'.' + sub_format - self.report_writesubtitles(sub_filename) - with io.open(encodeFilename(sub_filename), 'w', encoding='utf-8') as subfile: - subfile.write(sub) - except (OSError, IOError): - self.report_error(u'Cannot write subtitles file ' + descfn) - return - - if self.params.get('allsubtitles', False) and 'subtitles' in info_dict and info_dict['subtitles']: - subtitles = info_dict['subtitles'] - sub_format = self.params.get('subtitlesformat') - for subtitle in subtitles: - (sub_error, sub_lang, sub) = subtitle - if sub_error: - self.report_warning("Some error while getting the subtitles") - else: - try: - sub_filename = filename.rsplit('.', 1)[0] + u'.' + sub_lang + u'.' + sub_format - self.report_writesubtitles(sub_filename) - with io.open(encodeFilename(sub_filename), 'w', encoding='utf-8') as subfile: - subfile.write(sub) - except (OSError, IOError): - self.report_error(u'Cannot write subtitles file ' + descfn) - return - - if self.params.get('writeinfojson', False): - infofn = filename + u'.info.json' - self.report_writeinfojson(infofn) - try: - json_info_dict = dict((k, v) for k,v in info_dict.items() if not k in ['urlhandle']) - write_json_file(json_info_dict, encodeFilename(infofn)) - except (OSError, IOError): - self.report_error(u'Cannot write metadata to JSON file ' + infofn) - return - - if self.params.get('writethumbnail', False): - if 'thumbnail' in info_dict: - thumb_format = info_dict['thumbnail'].rpartition(u'/')[2].rpartition(u'.')[2] - if not thumb_format: - thumb_format = 'jpg' - thumb_filename = filename.rpartition('.')[0] + u'.' + thumb_format - self.to_screen(u'[%s] %s: Downloading thumbnail ...' % - (info_dict['extractor'], info_dict['id'])) - uf = compat_urllib_request.urlopen(info_dict['thumbnail']) - with open(thumb_filename, 'wb') as thumbf: - shutil.copyfileobj(uf, thumbf) - self.to_screen(u'[%s] %s: Writing thumbnail to: %s' % - (info_dict['extractor'], info_dict['id'], thumb_filename)) - - if not self.params.get('skip_download', False): - if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(filename)): - success = True - else: - try: - success = self._do_download(filename, info_dict) - except (OSError, IOError) as err: - raise UnavailableVideoError() - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - self.report_error(u'unable to download video data: %s' % str(err)) - return - except (ContentTooShortError, ) as err: - self.report_error(u'content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded)) - return - - if success: - try: - self.post_process(filename, info_dict) - except (PostProcessingError) as err: - self.report_error(u'postprocessing: %s' % str(err)) - return - - def download(self, url_list): - """Download a given list of URLs.""" - if len(url_list) > 1 and self.fixed_template(): - raise SameFileError(self.params['outtmpl']) - - for url in url_list: - try: - #It also downloads the videos - videos = self.extract_info(url) - except UnavailableVideoError: - self.report_error(u'unable to download video') - except MaxDownloadsReached: - self.to_screen(u'[info] Maximum number of downloaded files reached.') - raise - - return self._download_retcode - - def post_process(self, filename, ie_info): - """Run all the postprocessors on the given file.""" - info = dict(ie_info) - info['filepath'] = filename - keep_video = None - for pp in self._pps: - try: - keep_video_wish,new_info = pp.run(info) - if keep_video_wish is not None: - if keep_video_wish: - keep_video = keep_video_wish - elif keep_video is None: - # No clear decision yet, let IE decide - keep_video = keep_video_wish - except PostProcessingError as e: - self.to_stderr(u'ERROR: ' + e.msg) - if keep_video is False and not self.params.get('keepvideo', False): - try: - self.to_screen(u'Deleting original file %s (pass -k to keep)' % filename) - os.remove(encodeFilename(filename)) - except (IOError, OSError): - self.report_warning(u'Unable to remove downloaded video file') - def _download_with_rtmpdump(self, filename, url, player_url, page_url, play_path, tc_url): self.report_destination(filename) tmpfilename = self.temp_name(filename) diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py new file mode 100644 index 000000000..52ee8cedb --- /dev/null +++ b/youtube_dl/YoutubeDL.py @@ -0,0 +1,595 @@ +#!/usr/bin/env python +# -*- coding: utf-8 -*- + +from __future__ import absolute_import + +import io +import os +import re +import shutil +import socket +import sys +import time +import traceback + +from .utils import * +from .extractor import get_info_extractor +from .FileDownloader import FileDownloader + + +class YoutubeDL(object): + """YoutubeDL class. + + YoutubeDL objects are the ones responsible of downloading the + actual video file and writing it to disk if the user has requested + it, among some other tasks. In most cases there should be one per + program. As, given a video URL, the downloader doesn't know how to + extract all the needed information, task that InfoExtractors do, it + has to pass the URL to one of them. + + For this, YoutubeDL objects have a method that allows + InfoExtractors to be registered in a given order. When it is passed + a URL, the YoutubeDL object handles it to the first InfoExtractor it + finds that reports being able to handle it. The InfoExtractor extracts + all the information about the video or videos the URL refers to, and + YoutubeDL process the extracted information, possibly using a File + Downloader to download the video. + + YoutubeDL objects accept a lot of parameters. In order not to saturate + the object constructor with arguments, it receives a dictionary of + options instead. These options are available through the params + attribute for the InfoExtractors to use. The YoutubeDL also + registers itself as the downloader in charge for the InfoExtractors + that are added to it, so this is a "mutual registration". + + Available options: + + username: Username for authentication purposes. + password: Password for authentication purposes. + usenetrc: Use netrc for authentication instead. + verbose: Print additional info to stdout. + quiet: Do not print messages to stdout. + forceurl: Force printing final URL. + forcetitle: Force printing title. + forceid: Force printing ID. + forcethumbnail: Force printing thumbnail URL. + forcedescription: Force printing description. + forcefilename: Force printing final filename. + simulate: Do not download the video files. + format: Video format code. + format_limit: Highest quality format to try. + outtmpl: Template for output names. + restrictfilenames: Do not allow "&" and spaces in file names + ignoreerrors: Do not stop on download errors. + nooverwrites: Prevent overwriting files. + playliststart: Playlist item to start at. + playlistend: Playlist item to end at. + matchtitle: Download only matching titles. + rejecttitle: Reject downloads for matching titles. + logtostderr: Log messages to stderr instead of stdout. + writedescription: Write the video description to a .description file + writeinfojson: Write the video description to a .info.json file + writethumbnail: Write the thumbnail image to a file + writesubtitles: Write the video subtitles to a file + allsubtitles: Downloads all the subtitles of the video + listsubtitles: Lists all available subtitles for the video + subtitlesformat: Subtitle format [sbv/srt] (default=srt) + subtitleslang: Language of the subtitles to download + keepvideo: Keep the video file after post-processing + daterange: A DateRange object, download only if the upload_date is in the range. + skip_download: Skip the actual download of the video file + + The following parameters are not used by YoutubeDL itself, they are used by + the FileDownloader: + nopart, updatetime, buffersize, ratelimit, min_filesize, max_filesize, test, + noresizebuffer, retries, continuedl, noprogress, consoletitle + """ + + params = None + _ies = [] + _pps = [] + _download_retcode = None + _num_downloads = None + _screen_file = None + + def __init__(self, params): + """Create a FileDownloader object with the given options.""" + self._ies = [] + self._pps = [] + self._progress_hooks = [] + self._download_retcode = 0 + self._num_downloads = 0 + self._screen_file = [sys.stdout, sys.stderr][params.get('logtostderr', False)] + self.params = params + self.fd = FileDownloader(self, self.params) + + if '%(stitle)s' in self.params['outtmpl']: + self.report_warning(u'%(stitle)s is deprecated. Use the %(title)s and the --restrict-filenames flag(which also secures %(uploader)s et al) instead.') + + def add_info_extractor(self, ie): + """Add an InfoExtractor object to the end of the list.""" + self._ies.append(ie) + ie.set_downloader(self) + + def add_post_processor(self, pp): + """Add a PostProcessor object to the end of the chain.""" + self._pps.append(pp) + pp.set_downloader(self) + + def to_screen(self, message, skip_eol=False): + """Print message to stdout if not in quiet mode.""" + assert type(message) == type(u'') + if not self.params.get('quiet', False): + terminator = [u'\n', u''][skip_eol] + output = message + terminator + if 'b' in getattr(self._screen_file, 'mode', '') or sys.version_info[0] < 3: # Python 2 lies about the mode of sys.stdout/sys.stderr + output = output.encode(preferredencoding(), 'ignore') + self._screen_file.write(output) + self._screen_file.flush() + + def to_stderr(self, message): + """Print message to stderr.""" + assert type(message) == type(u'') + output = message + u'\n' + if 'b' in getattr(self._screen_file, 'mode', '') or sys.version_info[0] < 3: # Python 2 lies about the mode of sys.stdout/sys.stderr + output = output.encode(preferredencoding()) + sys.stderr.write(output) + + def fixed_template(self): + """Checks if the output template is fixed.""" + return (re.search(u'(?u)%\\(.+?\\)s', self.params['outtmpl']) is None) + + def trouble(self, message=None, tb=None): + """Determine action to take when a download problem appears. + + Depending on if the downloader has been configured to ignore + download errors or not, this method may throw an exception or + not when errors are found, after printing the message. + + tb, if given, is additional traceback information. + """ + if message is not None: + self.to_stderr(message) + if self.params.get('verbose'): + if tb is None: + if sys.exc_info()[0]: # if .trouble has been called from an except block + tb = u'' + if hasattr(sys.exc_info()[1], 'exc_info') and sys.exc_info()[1].exc_info[0]: + tb += u''.join(traceback.format_exception(*sys.exc_info()[1].exc_info)) + tb += compat_str(traceback.format_exc()) + else: + tb_data = traceback.format_list(traceback.extract_stack()) + tb = u''.join(tb_data) + self.to_stderr(tb) + if not self.params.get('ignoreerrors', False): + if sys.exc_info()[0] and hasattr(sys.exc_info()[1], 'exc_info') and sys.exc_info()[1].exc_info[0]: + exc_info = sys.exc_info()[1].exc_info + else: + exc_info = sys.exc_info() + raise DownloadError(message, exc_info) + self._download_retcode = 1 + + def report_warning(self, 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': + _msg_header=u'\033[0;33mWARNING:\033[0m' + else: + _msg_header=u'WARNING:' + warning_message=u'%s %s' % (_msg_header,message) + self.to_stderr(warning_message) + + def report_error(self, message, tb=None): + ''' + Do the same as trouble, but prefixes the message with 'ERROR:', colored + in red if stderr is a tty file. + ''' + if sys.stderr.isatty() and os.name != 'nt': + _msg_header = u'\033[0;31mERROR:\033[0m' + else: + _msg_header = u'ERROR:' + error_message = u'%s %s' % (_msg_header, message) + self.trouble(error_message, tb) + + def slow_down(self, start_time, byte_counter): + """Sleep if the download speed is over the rate limit.""" + rate_limit = self.params.get('ratelimit', None) + if rate_limit is None or byte_counter == 0: + return + now = time.time() + elapsed = now - start_time + if elapsed <= 0.0: + return + speed = float(byte_counter) / elapsed + if speed > rate_limit: + time.sleep((byte_counter - rate_limit * (now - start_time)) / rate_limit) + + def report_writedescription(self, descfn): + """ Report that the description file is being written """ + self.to_screen(u'[info] Writing video description to: ' + descfn) + + def report_writesubtitles(self, sub_filename): + """ Report that the subtitles file is being written """ + self.to_screen(u'[info] Writing video subtitles to: ' + sub_filename) + + def report_writeinfojson(self, infofn): + """ Report that the metadata file has been written """ + self.to_screen(u'[info] Video description metadata as JSON to: ' + infofn) + + def report_file_already_downloaded(self, file_name): + """Report file has already been fully downloaded.""" + try: + self.to_screen(u'[download] %s has already been downloaded' % file_name) + except (UnicodeEncodeError) as err: + self.to_screen(u'[download] The file has already been downloaded') + + def increment_downloads(self): + """Increment the ordinal that assigns a number to each file.""" + self._num_downloads += 1 + + def prepare_filename(self, info_dict): + """Generate the output filename.""" + try: + template_dict = dict(info_dict) + + template_dict['epoch'] = int(time.time()) + autonumber_size = self.params.get('autonumber_size') + if autonumber_size is None: + autonumber_size = 5 + autonumber_templ = u'%0' + str(autonumber_size) + u'd' + template_dict['autonumber'] = autonumber_templ % self._num_downloads + if template_dict['playlist_index'] is not None: + template_dict['playlist_index'] = u'%05d' % template_dict['playlist_index'] + + sanitize = lambda k,v: sanitize_filename( + u'NA' if v is None else compat_str(v), + restricted=self.params.get('restrictfilenames'), + is_id=(k==u'id')) + template_dict = dict((k, sanitize(k, v)) for k,v in template_dict.items()) + + filename = self.params['outtmpl'] % template_dict + return filename + except KeyError as err: + self.report_error(u'Erroneous output template') + return None + except ValueError as err: + self.report_error(u'Insufficient system charset ' + repr(preferredencoding())) + return None + + def _match_entry(self, info_dict): + """ Returns None iff the file should be downloaded """ + + title = info_dict['title'] + matchtitle = self.params.get('matchtitle', False) + if matchtitle: + if not re.search(matchtitle, title, re.IGNORECASE): + return u'[download] "' + title + '" title did not match pattern "' + matchtitle + '"' + rejecttitle = self.params.get('rejecttitle', False) + if rejecttitle: + if re.search(rejecttitle, title, re.IGNORECASE): + return u'"' + title + '" title matched reject pattern "' + rejecttitle + '"' + date = info_dict.get('upload_date', None) + if date is not None: + dateRange = self.params.get('daterange', DateRange()) + if date not in dateRange: + return u'[download] %s upload date is not in range %s' % (date_from_str(date).isoformat(), dateRange) + return None + + def extract_info(self, url, download=True, ie_key=None, extra_info={}): + ''' + Returns a list with a dictionary for each video we find. + If 'download', also downloads the videos. + extra_info is a dict containing the extra values to add to each result + ''' + + if ie_key: + ie = get_info_extractor(ie_key)() + ie.set_downloader(self) + ies = [ie] + else: + ies = self._ies + + for ie in ies: + if not ie.suitable(url): + continue + + if not ie.working(): + self.report_warning(u'The program functionality for this site has been marked as broken, ' + u'and will probably not work.') + + try: + ie_result = ie.extract(url) + if ie_result is None: # Finished already (backwards compatibility; listformats and friends should be moved here) + break + if isinstance(ie_result, list): + # Backwards compatibility: old IE result format + for result in ie_result: + result.update(extra_info) + ie_result = { + '_type': 'compat_list', + 'entries': ie_result, + } + else: + ie_result.update(extra_info) + if 'extractor' not in ie_result: + ie_result['extractor'] = ie.IE_NAME + return self.process_ie_result(ie_result, download=download) + except ExtractorError as de: # An error we somewhat expected + self.report_error(compat_str(de), de.format_traceback()) + break + except Exception as e: + if self.params.get('ignoreerrors', False): + self.report_error(compat_str(e), tb=compat_str(traceback.format_exc())) + break + else: + raise + else: + self.report_error(u'no suitable InfoExtractor: %s' % url) + + def process_ie_result(self, ie_result, download=True, extra_info={}): + """ + Take the result of the ie(may be modified) and resolve all unresolved + references (URLs, playlist items). + + It will also download the videos if 'download'. + Returns the resolved ie_result. + """ + + result_type = ie_result.get('_type', 'video') # If not given we suppose it's a video, support the default old system + if result_type == 'video': + if 'playlist' not in ie_result: + # It isn't part of a playlist + ie_result['playlist'] = None + ie_result['playlist_index'] = None + if download: + self.process_info(ie_result) + return ie_result + elif result_type == 'url': + # We have to add extra_info to the results because it may be + # contained in a playlist + return self.extract_info(ie_result['url'], + download, + ie_key=ie_result.get('ie_key'), + extra_info=extra_info) + elif result_type == 'playlist': + # We process each entry in the playlist + playlist = ie_result.get('title', None) or ie_result.get('id', None) + self.to_screen(u'[download] Downloading playlist: %s' % playlist) + + playlist_results = [] + + n_all_entries = len(ie_result['entries']) + playliststart = self.params.get('playliststart', 1) - 1 + playlistend = self.params.get('playlistend', -1) + + if playlistend == -1: + entries = ie_result['entries'][playliststart:] + else: + entries = ie_result['entries'][playliststart:playlistend] + + n_entries = len(entries) + + self.to_screen(u"[%s] playlist '%s': Collected %d video ids (downloading %d of them)" % + (ie_result['extractor'], playlist, n_all_entries, n_entries)) + + for i,entry in enumerate(entries,1): + self.to_screen(u'[download] Downloading video #%s of %s' %(i, n_entries)) + extra = { + 'playlist': playlist, + 'playlist_index': i + playliststart, + } + if not 'extractor' in entry: + # We set the extractor, if it's an url it will be set then to + # the new extractor, but if it's already a video we must make + # sure it's present: see issue #877 + entry['extractor'] = ie_result['extractor'] + entry_result = self.process_ie_result(entry, + download=download, + extra_info=extra) + playlist_results.append(entry_result) + ie_result['entries'] = playlist_results + return ie_result + elif result_type == 'compat_list': + def _fixup(r): + r.setdefault('extractor', ie_result['extractor']) + return r + ie_result['entries'] = [ + self.process_ie_result(_fixup(r), download=download) + for r in ie_result['entries'] + ] + return ie_result + else: + raise Exception('Invalid result type: %s' % result_type) + + def process_info(self, info_dict): + """Process a single resolved IE result.""" + + assert info_dict.get('_type', 'video') == 'video' + #We increment the download the download count here to match the previous behaviour. + self.increment_downloads() + + info_dict['fulltitle'] = info_dict['title'] + if len(info_dict['title']) > 200: + info_dict['title'] = info_dict['title'][:197] + u'...' + + # Keep for backwards compatibility + info_dict['stitle'] = info_dict['title'] + + if not 'format' in info_dict: + info_dict['format'] = info_dict['ext'] + + reason = self._match_entry(info_dict) + if reason is not None: + self.to_screen(u'[download] ' + reason) + return + + max_downloads = self.params.get('max_downloads') + if max_downloads is not None: + if self._num_downloads > int(max_downloads): + raise MaxDownloadsReached() + + filename = self.prepare_filename(info_dict) + + # Forced printings + if self.params.get('forcetitle', False): + compat_print(info_dict['title']) + if self.params.get('forceid', False): + compat_print(info_dict['id']) + if self.params.get('forceurl', False): + compat_print(info_dict['url']) + if self.params.get('forcethumbnail', False) and 'thumbnail' in info_dict: + compat_print(info_dict['thumbnail']) + if self.params.get('forcedescription', False) and 'description' in info_dict: + compat_print(info_dict['description']) + if self.params.get('forcefilename', False) and filename is not None: + compat_print(filename) + if self.params.get('forceformat', False): + compat_print(info_dict['format']) + + # Do nothing else if in simulate mode + if self.params.get('simulate', False): + return + + if filename is None: + return + + try: + dn = os.path.dirname(encodeFilename(filename)) + if dn != '' and not os.path.exists(dn): + os.makedirs(dn) + except (OSError, IOError) as err: + self.report_error(u'unable to create directory ' + compat_str(err)) + return + + if self.params.get('writedescription', False): + try: + descfn = filename + u'.description' + self.report_writedescription(descfn) + with io.open(encodeFilename(descfn), 'w', encoding='utf-8') as descfile: + descfile.write(info_dict['description']) + except (OSError, IOError): + self.report_error(u'Cannot write description file ' + descfn) + return + + if self.params.get('writesubtitles', False) and 'subtitles' in info_dict and info_dict['subtitles']: + # subtitles download errors are already managed as troubles in relevant IE + # that way it will silently go on when used with unsupporting IE + subtitle = info_dict['subtitles'][0] + (sub_error, sub_lang, sub) = subtitle + sub_format = self.params.get('subtitlesformat') + if sub_error: + self.report_warning("Some error while getting the subtitles") + else: + try: + sub_filename = filename.rsplit('.', 1)[0] + u'.' + sub_lang + u'.' + sub_format + self.report_writesubtitles(sub_filename) + with io.open(encodeFilename(sub_filename), 'w', encoding='utf-8') as subfile: + subfile.write(sub) + except (OSError, IOError): + self.report_error(u'Cannot write subtitles file ' + descfn) + return + + if self.params.get('allsubtitles', False) and 'subtitles' in info_dict and info_dict['subtitles']: + subtitles = info_dict['subtitles'] + sub_format = self.params.get('subtitlesformat') + for subtitle in subtitles: + (sub_error, sub_lang, sub) = subtitle + if sub_error: + self.report_warning("Some error while getting the subtitles") + else: + try: + sub_filename = filename.rsplit('.', 1)[0] + u'.' + sub_lang + u'.' + sub_format + self.report_writesubtitles(sub_filename) + with io.open(encodeFilename(sub_filename), 'w', encoding='utf-8') as subfile: + subfile.write(sub) + except (OSError, IOError): + self.report_error(u'Cannot write subtitles file ' + descfn) + return + + if self.params.get('writeinfojson', False): + infofn = filename + u'.info.json' + self.report_writeinfojson(infofn) + try: + json_info_dict = dict((k, v) for k,v in info_dict.items() if not k in ['urlhandle']) + write_json_file(json_info_dict, encodeFilename(infofn)) + except (OSError, IOError): + self.report_error(u'Cannot write metadata to JSON file ' + infofn) + return + + if self.params.get('writethumbnail', False): + if 'thumbnail' in info_dict: + thumb_format = info_dict['thumbnail'].rpartition(u'/')[2].rpartition(u'.')[2] + if not thumb_format: + thumb_format = 'jpg' + thumb_filename = filename.rpartition('.')[0] + u'.' + thumb_format + self.to_screen(u'[%s] %s: Downloading thumbnail ...' % + (info_dict['extractor'], info_dict['id'])) + uf = compat_urllib_request.urlopen(info_dict['thumbnail']) + with open(thumb_filename, 'wb') as thumbf: + shutil.copyfileobj(uf, thumbf) + self.to_screen(u'[%s] %s: Writing thumbnail to: %s' % + (info_dict['extractor'], info_dict['id'], thumb_filename)) + + if not self.params.get('skip_download', False): + if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(filename)): + success = True + else: + try: + success = self.fd._do_download(filename, info_dict) + except (OSError, IOError) as err: + raise UnavailableVideoError() + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self.report_error(u'unable to download video data: %s' % str(err)) + return + except (ContentTooShortError, ) as err: + self.report_error(u'content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded)) + return + + if success: + try: + self.post_process(filename, info_dict) + except (PostProcessingError) as err: + self.report_error(u'postprocessing: %s' % str(err)) + return + + def download(self, url_list): + """Download a given list of URLs.""" + if len(url_list) > 1 and self.fixed_template(): + raise SameFileError(self.params['outtmpl']) + + for url in url_list: + try: + #It also downloads the videos + videos = self.extract_info(url) + except UnavailableVideoError: + self.report_error(u'unable to download video') + except MaxDownloadsReached: + self.to_screen(u'[info] Maximum number of downloaded files reached.') + raise + + return self._download_retcode + + def post_process(self, filename, ie_info): + """Run all the postprocessors on the given file.""" + info = dict(ie_info) + info['filepath'] = filename + keep_video = None + for pp in self._pps: + try: + keep_video_wish,new_info = pp.run(info) + if keep_video_wish is not None: + if keep_video_wish: + keep_video = keep_video_wish + elif keep_video is None: + # No clear decision yet, let IE decide + keep_video = keep_video_wish + except PostProcessingError as e: + self.to_stderr(u'ERROR: ' + e.msg) + if keep_video is False and not self.params.get('keepvideo', False): + try: + self.to_screen(u'Deleting original file %s (pass -k to keep)' % filename) + os.remove(encodeFilename(filename)) + except (IOError, OSError): + self.report_warning(u'Unable to remove downloaded video file') diff --git a/youtube_dl/__init__.py b/youtube_dl/__init__.py index a8b62a6cd..70e7d53de 100644 --- a/youtube_dl/__init__.py +++ b/youtube_dl/__init__.py @@ -46,6 +46,7 @@ from .update import update_self from .version import __version__ from .FileDownloader import * from .extractor import gen_extractors +from .YoutubeDL import YoutubeDL from .PostProcessor import * def parseOpts(overrideArguments=None): @@ -318,7 +319,7 @@ def parseOpts(overrideArguments=None): if overrideArguments is not None: opts, args = parser.parse_args(overrideArguments) if opts.verbose: - print(u'[debug] Override config: ' + repr(overrideArguments)) + sys.stderr.write(u'[debug] Override config: ' + repr(overrideArguments) + '\n') else: xdg_config_home = os.environ.get('XDG_CONFIG_HOME') if xdg_config_home: @@ -331,9 +332,9 @@ def parseOpts(overrideArguments=None): argv = systemConf + userConf + commandLineConf opts, args = parser.parse_args(argv) if opts.verbose: - print(u'[debug] System config: ' + repr(systemConf)) - print(u'[debug] User config: ' + repr(userConf)) - print(u'[debug] Command-line args: ' + repr(commandLineConf)) + sys.stderr.write(u'[debug] System config: ' + repr(systemConf) + '\n') + sys.stderr.write(u'[debug] User config: ' + repr(userConf) + '\n') + sys.stderr.write(u'[debug] Command-line args: ' + repr(commandLineConf) + '\n') return parser, opts, args @@ -368,7 +369,7 @@ def _real_main(argv=None): # Dump user agent if opts.dump_user_agent: - print(std_headers['User-Agent']) + compat_print(std_headers['User-Agent']) sys.exit(0) # Batch file verification @@ -409,18 +410,18 @@ def _real_main(argv=None): if opts.list_extractors: for ie in extractors: - print(ie.IE_NAME + (' (CURRENTLY BROKEN)' if not ie._WORKING else '')) + compat_print(ie.IE_NAME + (' (CURRENTLY BROKEN)' if not ie._WORKING else '')) matchedUrls = [url for url in all_urls if ie.suitable(url)] all_urls = [url for url in all_urls if url not in matchedUrls] for mu in matchedUrls: - print(u' ' + mu) + compat_print(u' ' + mu) sys.exit(0) # Conflicting, missing and erroneous options if opts.usenetrc and (opts.username is not None or opts.password is not None): parser.error(u'using .netrc conflicts with giving username/password') if opts.password is not None and opts.username is None: - print(u'WARNING: account username missing') + sys.stderr.write(u'WARNING: account username missing\n') if opts.outtmpl is not None and (opts.usetitle or opts.autonumber or opts.useid): parser.error(u'using output template conflicts with using title, video ID or auto number') if opts.usetitle and opts.useid: @@ -492,8 +493,8 @@ def _real_main(argv=None): or (opts.autonumber and u'%(autonumber)s-%(id)s.%(ext)s') or u'%(title)s-%(id)s.%(ext)s') - # File downloader - fd = FileDownloader({ + # YoutubeDL + ydl = YoutubeDL({ 'usenetrc': opts.usenetrc, 'username': opts.username, 'password': opts.password, @@ -550,31 +551,31 @@ def _real_main(argv=None): }) if opts.verbose: - fd.to_screen(u'[debug] youtube-dl version ' + __version__) + ydl.to_screen(u'[debug] youtube-dl version ' + __version__) try: sp = subprocess.Popen(['git', 'rev-parse', '--short', 'HEAD'], stdout=subprocess.PIPE, stderr=subprocess.PIPE, cwd=os.path.dirname(os.path.abspath(__file__))) out, err = sp.communicate() out = out.decode().strip() if re.match('[0-9a-f]+', out): - fd.to_screen(u'[debug] Git HEAD: ' + out) + ydl.to_screen(u'[debug] Git HEAD: ' + out) except: pass - fd.to_screen(u'[debug] Python version %s - %s' %(platform.python_version(), platform.platform())) - fd.to_screen(u'[debug] Proxy map: ' + str(proxy_handler.proxies)) + ydl.to_screen(u'[debug] Python version %s - %s' %(platform.python_version(), platform.platform())) + ydl.to_screen(u'[debug] Proxy map: ' + str(proxy_handler.proxies)) for extractor in extractors: - fd.add_info_extractor(extractor) + ydl.add_info_extractor(extractor) # PostProcessors if opts.extractaudio: - fd.add_post_processor(FFmpegExtractAudioPP(preferredcodec=opts.audioformat, preferredquality=opts.audioquality, nopostoverwrites=opts.nopostoverwrites)) + ydl.add_post_processor(FFmpegExtractAudioPP(preferredcodec=opts.audioformat, preferredquality=opts.audioquality, nopostoverwrites=opts.nopostoverwrites)) if opts.recodevideo: - fd.add_post_processor(FFmpegVideoConvertor(preferedformat=opts.recodevideo)) + ydl.add_post_processor(FFmpegVideoConvertor(preferedformat=opts.recodevideo)) # Update version if opts.update_self: - update_self(fd.to_screen, opts.verbose, sys.argv[0]) + update_self(ydl.to_screen, opts.verbose, sys.argv[0]) # Maybe do nothing if len(all_urls) < 1: @@ -584,9 +585,9 @@ def _real_main(argv=None): sys.exit() try: - retcode = fd.download(all_urls) + retcode = ydl.download(all_urls) except MaxDownloadsReached: - fd.to_screen(u'--max-download limit reached, aborting.') + ydl.to_screen(u'--max-download limit reached, aborting.') retcode = 101 # Dump cookie jar if requested diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index e27f58496..7b291f907 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -45,6 +45,7 @@ from .ted import TEDIE from .tumblr import TumblrIE from .ustream import UstreamIE from .vbox7 import Vbox7IE +from .vevo import VevoIE from .vimeo import VimeoIE from .vine import VineIE from .worldstarhiphop import WorldStarHipHopIE @@ -126,6 +127,7 @@ def gen_extractors(): GametrailersIE(), StatigramIE(), BreakIE(), + VevoIE(), JukeboxIE(), GenericIE() ] diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 062f4cf1e..64d63e109 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -211,7 +211,7 @@ class InfoExtractor(object): raise ExtractorError(u'Unable to extract %s' % _name) else: self._downloader.report_warning(u'unable to extract %s; ' - u'please report this issue on GitHub.' % _name) + u'please report this issue on http://yt-dl.org/bug' % _name) return None def _html_search_regex(self, pattern, string, name, default=None, fatal=True, flags=0): diff --git a/youtube_dl/extractor/mtv.py b/youtube_dl/extractor/mtv.py index a801c8123..969db7113 100644 --- a/youtube_dl/extractor/mtv.py +++ b/youtube_dl/extractor/mtv.py @@ -27,6 +27,14 @@ class MTVIE(InfoExtractor): webpage = self._download_webpage(url, video_id) + # Some videos come from Vevo.com + m_vevo = re.search(r'isVevoVideo = true;.*?vevoVideoId = "(.*?)";', + webpage, re.DOTALL) + if m_vevo: + vevo_id = m_vevo.group(1); + self.to_screen(u'Vevo video detected: %s' % vevo_id) + return self.url_result('vevo:%s' % vevo_id, ie='Vevo') + #song_name = self._html_search_regex(r'<meta name="mtv_vt" content="([^"]+)"/>', # webpage, u'song name', fatal=False) diff --git a/youtube_dl/extractor/vevo.py b/youtube_dl/extractor/vevo.py new file mode 100644 index 000000000..aa88e1a92 --- /dev/null +++ b/youtube_dl/extractor/vevo.py @@ -0,0 +1,44 @@ +import re +import json + +from .common import InfoExtractor +from ..utils import ( + unified_strdate, + ExtractorError, +) + +class VevoIE(InfoExtractor): + """ + Accecps urls from vevo.com or in the format 'vevo:{id}' + (currently used by MTVIE) + """ + _VALID_URL = r'((http://www.vevo.com/watch/.*?/.*?/)|(vevo:))(?P<id>.*)$' + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + json_url = 'http://www.vevo.com/data/video/%s' % video_id + base_url = 'http://smil.lvl3.vevo.com' + videos_url = '%s/Video/V2/VFILE/%s/%sr.smil' % (base_url, video_id, video_id.lower()) + info_json = self._download_webpage(json_url, video_id, u'Downloading json info') + links_webpage = self._download_webpage(videos_url, video_id, u'Downloading videos urls') + + self.report_extraction(video_id) + video_info = json.loads(info_json) + m_urls = list(re.finditer(r'<video src="(?P<ext>.*?):(?P<url>.*?)"', links_webpage)) + if m_urls is None or len(m_urls) == 0: + raise ExtractorError(u'Unable to extract video url') + # They are sorted from worst to best quality + m_url = m_urls[-1] + video_url = base_url + m_url.group('url') + ext = m_url.group('ext') + + return {'url': video_url, + 'ext': ext, + 'id': video_id, + 'title': video_info['title'], + 'thumbnail': video_info['img'], + 'upload_date': video_info['launchDate'].replace('/',''), + 'uploader': video_info['Artists'][0]['title'], + } diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index fbe8d63a3..de653cb3d 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -58,7 +58,7 @@ class YoutubeIE(InfoExtractor): '18': 'mp4', '22': 'mp4', '37': 'mp4', - '38': 'video', # You actually don't know if this will be MOV, AVI or whatever + '38': 'mp4', '43': 'webm', '44': 'webm', '45': 'webm', @@ -129,12 +129,13 @@ class YoutubeIE(InfoExtractor): """Indicate the download will use the RTMP protocol.""" self.to_screen(u'RTMP download detected') - @staticmethod - def _decrypt_signature(s): + def _decrypt_signature(self, s): """Decrypt the key the two subkeys must have a length of 43""" (a,b) = s.split('.') if len(a) != 43 or len(b) != 43: - raise ExtractorError(u'Unable to decrypt signature, subkeys lengths not valid') + raise ExtractorError(u'Unable to decrypt signature, subkeys lengths %d.%d not supported; retrying might work' % (len(a), len(b))) + if self._downloader.params.get('verbose'): + self.to_screen('encrypted signature length %d.%d' % (len(a), len(b))) b = ''.join([b[:8],a[0],b[9:18],b[-4],b[19:39], b[18]])[0:40] a = a[-40:] s_dec = '.'.join((a,b))[::-1] @@ -484,11 +485,15 @@ class YoutubeIE(InfoExtractor): try: mobj = re.search(r';ytplayer.config = ({.*?});', video_webpage) + if not mobj: + raise ValueError('Could not find vevo ID') info = json.loads(mobj.group(1)) args = info['args'] - if args.get('ptk','') == 'vevo' or 'dashmpd': - # Vevo videos with encrypted signatures - self.to_screen(u'%s: Vevo video detected.' % video_id) + # Easy way to know if the 's' value is in url_encoded_fmt_stream_map + # this signatures are encrypted + m_s = re.search(r'[&,]s=', args['url_encoded_fmt_stream_map']) + if m_s is not None: + self.to_screen(u'%s: Encrypted signatures detected.' % video_id) video_info['url_encoded_fmt_stream_map'] = [args['url_encoded_fmt_stream_map']] except ValueError: pass diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index 66ae41e31..4d415bd61 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -474,7 +474,7 @@ class ExtractorError(Exception): """ tb, if given, is the original traceback (so that it can be printed out). """ if not sys.exc_info()[0] in (compat_urllib_error.URLError, socket.timeout, UnavailableVideoError): - msg = msg + u'; please report this issue on GitHub.' + msg = msg + u'; please report this issue on http://yt-dl.org/bug' super(ExtractorError, self).__init__(msg) self.traceback = tb diff --git a/youtube_dl/version.py b/youtube_dl/version.py index a671a601d..0962e284c 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,2 +1,2 @@ -__version__ = '2013.06.25' +__version__ = '2013.06.30' |