From 1fb07d10a3f5f2baf1ebbdbc69d8ee8615cec2f9 Mon Sep 17 00:00:00 2001 From: Jai Grimshaw Date: Mon, 14 Oct 2013 16:18:58 +1100 Subject: [youtube] Adds #1312 Download annotations Adds #1321 Download annotations from youtube Annotations are downloaded and written to a .annotations.xml file using the https://www.youtube.com/annotations_invideo?features=1&legacy=1&video_id=$VIDEOID API. Added unit test for annotations. --- youtube_dl/YoutubeDL.py | 17 +++++++++++++++++ youtube_dl/__init__.py | 4 ++++ youtube_dl/extractor/youtube.py | 10 ++++++++++ 3 files changed, 31 insertions(+) (limited to 'youtube_dl') diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py index e85e03fa4..c8054544a 100644 --- a/youtube_dl/YoutubeDL.py +++ b/youtube_dl/YoutubeDL.py @@ -71,6 +71,7 @@ class YoutubeDL(object): 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 + writeannotations: Write the video annotations to a .annotations.xml file writethumbnail: Write the thumbnail image to a file writesubtitles: Write the video subtitles to a file writeautomaticsub: Write the automatic subtitles to a file @@ -258,6 +259,10 @@ class YoutubeDL(object): """ Report that the metadata file has been written """ self.to_screen(u'[info] Video description metadata as JSON to: ' + infofn) + def report_writeannotations(self, annofn): + """ Report that the annotations file has been written. """ + self.to_screen(u'[info] Writing video annotations to: ' + annofn) + def report_file_already_downloaded(self, file_name): """Report file has already been fully downloaded.""" try: @@ -522,6 +527,18 @@ class YoutubeDL(object): self.report_error(u'Cannot write description file ' + descfn) return + if self.params.get('writeannotations', False): + try: + annofn = filename + u'.annotations.xml' + self.report_writeannotations(annofn) + with io.open(encodeFilename(annofn), 'w', encoding='utf-8') as annofile: + annofile.write(info_dict['annotations']) + except (KeyError, TypeError): + self.report_warning(u'There are no annotations to write.') + except (OSError, IOError): + self.report_error(u'Cannot write annotations file: ' + annofn) + return + subtitles_are_requested = any([self.params.get('writesubtitles', False), self.params.get('writeautomaticsub')]) diff --git a/youtube_dl/__init__.py b/youtube_dl/__init__.py index 3513d719f..fb1270ea2 100644 --- a/youtube_dl/__init__.py +++ b/youtube_dl/__init__.py @@ -339,6 +339,9 @@ def parseOpts(overrideArguments=None): filesystem.add_option('--write-info-json', action='store_true', dest='writeinfojson', help='write video metadata to a .info.json file', default=False) + filesystem.add_option('--write-annotations', + action='store_true', dest='writeannotations', + help='write video annotations to a .annotation file', default=False) filesystem.add_option('--write-thumbnail', action='store_true', dest='writethumbnail', help='write thumbnail image to disk', default=False) @@ -601,6 +604,7 @@ def _real_main(argv=None): 'nopart': opts.nopart, 'updatetime': opts.updatetime, 'writedescription': opts.writedescription, + 'writeannotations': opts.writeannotations, 'writeinfojson': opts.writeinfojson, 'writethumbnail': opts.writethumbnail, 'writesubtitles': opts.writesubtitles, diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 8222a880f..4347651d7 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -1250,6 +1250,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): url_map[itag] = format_url return url_map + def _extract_annotations(self, video_id): + url = 'https://www.youtube.com/annotations_invideo?features=1&legacy=1&video_id=%s' % video_id + return self._download_webpage(url, video_id, note=u'Searching for annotations.', errnote=u'Unable to download video annotations.') + def _real_extract(self, url): # Extract original video URL from URL with redirection, like age verification, using next_url parameter mobj = re.search(self._NEXT_URL_RE, url) @@ -1382,6 +1386,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): else: video_duration = compat_urllib_parse.unquote_plus(video_info['length_seconds'][0]) + # annotations + video_annotations = None + if self._downloader.params.get('writeannotations', False): + video_annotations = self._extract_annotations(video_id) + # Decide which formats to download try: @@ -1495,6 +1504,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): 'subtitles': video_subtitles, 'duration': video_duration, 'age_limit': 18 if age_gate else 0, + 'annotations': video_annotations }) return results -- cgit v1.2.3 From ea62a2da466e3fce802930d3685d53a159520719 Mon Sep 17 00:00:00 2001 From: Filippo Valsorda Date: Mon, 14 Oct 2013 01:32:47 -0400 Subject: add VideoPremium.tv RTMP support --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/videopremium.py | 40 ++++++++++++++++++++++++++++++++++++ 2 files changed, 41 insertions(+) create mode 100644 youtube_dl/extractor/videopremium.py (limited to 'youtube_dl') diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index d76945a48..748f12e5a 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -131,6 +131,7 @@ from .vice import ViceIE from .viddler import ViddlerIE from .videodetective import VideoDetectiveIE from .videofyme import VideofyMeIE +from .videopremium import VideoPremiumIE from .vimeo import VimeoIE, VimeoChannelIE from .vine import VineIE from .wat import WatIE diff --git a/youtube_dl/extractor/videopremium.py b/youtube_dl/extractor/videopremium.py new file mode 100644 index 000000000..65f39b982 --- /dev/null +++ b/youtube_dl/extractor/videopremium.py @@ -0,0 +1,40 @@ +import re +import random + +from .common import InfoExtractor + + +class VideoPremiumIE(InfoExtractor): + _VALID_URL = r'(?:https?://)?(?:www\.)?videopremium\.tv/(?P\w+)(?:/.*)?' + _TEST = { + u'url': u'http://videopremium.tv/4w7oadjsf156', + u'file': u'4w7oadjsf156.f4v', + u'info_dict': { + u"title": u"youtube-dl_test_video____a_________-BaW_jenozKc.mp4.mp4" + }, + u'params': { + u'skip_download': True, + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + + video_id = mobj.group('id') + webpage_url = 'http://videopremium.tv/' + video_id + webpage = self._download_webpage(webpage_url, video_id) + + self.report_extraction(video_id) + + video_title = self._html_search_regex(r'\s*(.+?)\s*<', + webpage, u'video title') + + return [{ + 'id': video_id, + 'url': "rtmp://e%d.md.iplay.md/play" % random.randint(1, 16), + 'play_path': "mp4:%s.f4v" % video_id, + 'page_url': "http://videopremium.tv/" + video_id, + 'player_url': "http://videopremium.tv/uplayer/uppod.swf", + 'ext': 'f4v', + 'title': video_title, + }] -- cgit v1.2.3