diff options
| -rw-r--r-- | test/test_playlists.py | 17 | ||||
| -rw-r--r-- | youtube_dl/extractor/__init__.py | 7 | ||||
| -rw-r--r-- | youtube_dl/extractor/brightcove.py | 13 | ||||
| -rw-r--r-- | youtube_dl/extractor/generic.py | 12 | ||||
| -rw-r--r-- | youtube_dl/extractor/imdb.py | 5 | ||||
| -rw-r--r-- | youtube_dl/extractor/rutube.py | 118 |
6 files changed, 133 insertions, 39 deletions
diff --git a/test/test_playlists.py b/test/test_playlists.py index 5eeba091e..b3ce6f71e 100644 --- a/test/test_playlists.py +++ b/test/test_playlists.py @@ -33,6 +33,7 @@ from youtube_dl.extractor import ( ImdbListIE, KhanAcademyIE, EveryonesMixtapeIE, + RutubeChannelIE, ) @@ -195,11 +196,11 @@ class TestPlaylists(unittest.TestCase): def test_imdb_list(self): dl = FakeYDL() ie = ImdbListIE(dl) - result = ie.extract('http://www.imdb.com/list/sMjedvGDd8U') + result = ie.extract('http://www.imdb.com/list/JFs9NWw6XI0') self.assertIsPlaylist(result) - self.assertEqual(result['id'], 'sMjedvGDd8U') - self.assertEqual(result['title'], 'Animated and Family Films') - self.assertTrue(len(result['entries']) >= 48) + self.assertEqual(result['id'], 'JFs9NWw6XI0') + self.assertEqual(result['title'], 'March 23, 2012 Releases') + self.assertEqual(len(result['entries']), 7) def test_khanacademy_topic(self): dl = FakeYDL() @@ -219,6 +220,14 @@ class TestPlaylists(unittest.TestCase): self.assertEqual(result['id'], 'm7m0jJAbMQi') self.assertEqual(result['title'], 'Driving') self.assertEqual(len(result['entries']), 24) + + def test_rutube_channel(self): + dl = FakeYDL() + ie = RutubeChannelIE(dl) + result = ie.extract('http://rutube.ru/tags/video/1409') + self.assertIsPlaylist(result) + self.assertEqual(result['id'], '1409') + self.assertTrue(len(result['entries']) >= 34) if __name__ == '__main__': diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 1e8556124..e89b5cf9d 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -161,7 +161,12 @@ from .ro220 import Ro220IE from .rottentomatoes import RottenTomatoesIE from .roxwel import RoxwelIE from .rtlnow import RTLnowIE -from .rutube import RutubeIE +from .rutube import ( + RutubeIE, + RutubeChannelIE, + RutubeMovieIE, + RutubePersonIE, +) from .servingsys import ServingSysIE from .sina import SinaIE from .slashdot import SlashdotIE diff --git a/youtube_dl/extractor/brightcove.py b/youtube_dl/extractor/brightcove.py index 443294e6f..9ccf923a6 100644 --- a/youtube_dl/extractor/brightcove.py +++ b/youtube_dl/extractor/brightcove.py @@ -23,7 +23,6 @@ from ..utils import ( class BrightcoveIE(InfoExtractor): _VALID_URL = r'https?://.*brightcove\.com/(services|viewer).*\?(?P<query>.*)' _FEDERATED_URL_TEMPLATE = 'http://c.brightcove.com/services/viewer/htmlFederated?%s' - _PLAYLIST_URL_TEMPLATE = 'http://c.brightcove.com/services/json/experience/runtime/?command=get_programming_for_experience&playerKey=%s' _TESTS = [ { @@ -70,7 +69,7 @@ class BrightcoveIE(InfoExtractor): 'description': 'md5:363109c02998fee92ec02211bd8000df', 'uploader': 'National Ballet of Canada', }, - }, + } ] @classmethod @@ -131,6 +130,11 @@ class BrightcoveIE(InfoExtractor): """Try to extract the brightcove url from the wepbage, returns None if it can't be found """ + + url_m = re.search(r'<meta\s+property="og:video"\s+content="(http://c.brightcove.com/[^"]+)"', webpage) + if url_m: + return url_m.group(1) + m_brightcove = re.search( r'''(?sx)<object (?: @@ -183,8 +187,9 @@ class BrightcoveIE(InfoExtractor): return self._extract_video_info(video_info) def _get_playlist_info(self, player_key): - playlist_info = self._download_webpage(self._PLAYLIST_URL_TEMPLATE % player_key, - player_key, 'Downloading playlist information') + info_url = 'http://c.brightcove.com/services/json/experience/runtime/?command=get_programming_for_experience&playerKey=%s' % player_key + playlist_info = self._download_webpage( + info_url, player_key, 'Downloading playlist information') json_data = json.loads(playlist_info) if 'videoList' not in json_data: diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 829e5894f..48de379b7 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -78,6 +78,18 @@ class GenericIE(InfoExtractor): 'skip_download': True, }, }, + { + # https://github.com/rg3/youtube-dl/issues/2253 + 'url': 'http://bcove.me/i6nfkrc3', + 'file': '3101154703001.mp4', + 'md5': '0ba9446db037002366bab3b3eb30c88c', + 'info_dict': { + 'title': 'Still no power', + 'uploader': 'thestar.com', + 'description': 'Mississauga resident David Farmer is still out of power as a result of the ice storm a month ago. To keep the house warm, Farmer cuts wood from his property for a wood burning stove downstairs.', + }, + 'add_ie': ['Brightcove'], + }, # Direct link to a video { 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4', diff --git a/youtube_dl/extractor/imdb.py b/youtube_dl/extractor/imdb.py index 1763af020..7cee505c0 100644 --- a/youtube_dl/extractor/imdb.py +++ b/youtube_dl/extractor/imdb.py @@ -69,12 +69,9 @@ class ImdbListIE(InfoExtractor): list_id = mobj.group('id') webpage = self._download_webpage(url, list_id) - list_code = self._search_regex( - r'(?s)<div\s+class="list\sdetail">(.*?)class="see-more"', - webpage, 'list code') entries = [ self.url_result('http://www.imdb.com' + m, 'Imdb') - for m in re.findall(r'href="(/video/imdb/vi[^"]+)"', webpage)] + for m in re.findall(r'href="(/video/imdb/vi[^"]+)"\s+data-type="playlist"', webpage)] list_title = self._html_search_regex( r'<h1 class="header">(.*?)</h1>', webpage, 'list title') diff --git a/youtube_dl/extractor/rutube.py b/youtube_dl/extractor/rutube.py index e3e9bc07f..4922dd764 100644 --- a/youtube_dl/extractor/rutube.py +++ b/youtube_dl/extractor/rutube.py @@ -1,58 +1,124 @@ # encoding: utf-8 +from __future__ import unicode_literals + import re import json +import itertools from .common import InfoExtractor from ..utils import ( - compat_urlparse, compat_str, + unified_strdate, ExtractorError, ) class RutubeIE(InfoExtractor): - _VALID_URL = r'https?://rutube\.ru/video/(?P<long_id>\w+)' + IE_NAME = 'rutube' + IE_DESC = 'Rutube videos' + _VALID_URL = r'https?://rutube\.ru/video/(?P<id>[\da-z]{32})' _TEST = { - u'url': u'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/', - u'file': u'3eac3b4561676c17df9132a9a1e62e3e.mp4', - u'info_dict': { - u'title': u'Раненный кенгуру забежал в аптеку', - u'uploader': u'NTDRussian', - u'uploader_id': u'29790', + 'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/', + 'file': '3eac3b4561676c17df9132a9a1e62e3e.mp4', + 'info_dict': { + 'title': 'Раненный кенгуру забежал в аптеку', + 'description': 'http://www.ntdtv.ru ', + 'duration': 80, + 'uploader': 'NTDRussian', + 'uploader_id': '29790', + 'upload_date': '20131016', }, - u'params': { + 'params': { # It requires ffmpeg (m3u8 download) - u'skip_download': True, + 'skip_download': True, }, } - def _get_api_response(self, short_id, subpath): - api_url = 'http://rutube.ru/api/play/%s/%s/?format=json' % (subpath, short_id) - response_json = self._download_webpage(api_url, short_id, - u'Downloading %s json' % subpath) - return json.loads(response_json) - def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - long_id = mobj.group('long_id') - webpage = self._download_webpage(url, long_id) - og_video = self._og_search_video_url(webpage) - short_id = compat_urlparse.urlparse(og_video).path[1:] - options = self._get_api_response(short_id, 'options') - trackinfo = self._get_api_response(short_id, 'trackinfo') + video_id = mobj.group('id') + + api_response = self._download_webpage('http://rutube.ru/api/video/%s/?format=json' % video_id, + video_id, 'Downloading video JSON') + video = json.loads(api_response) + + api_response = self._download_webpage('http://rutube.ru/api/play/trackinfo/%s/?format=json' % video_id, + video_id, 'Downloading trackinfo JSON') + trackinfo = json.loads(api_response) + # Some videos don't have the author field author = trackinfo.get('author') or {} m3u8_url = trackinfo['video_balancer'].get('m3u8') if m3u8_url is None: - raise ExtractorError(u'Couldn\'t find m3u8 manifest url') + raise ExtractorError('Couldn\'t find m3u8 manifest url') return { - 'id': trackinfo['id'], - 'title': trackinfo['title'], + 'id': video['id'], + 'title': video['title'], + 'description': video['description'], + 'duration': video['duration'], + 'view_count': video['hits'], 'url': m3u8_url, 'ext': 'mp4', - 'thumbnail': options['thumbnail_url'], + 'thumbnail': video['thumbnail_url'], 'uploader': author.get('name'), 'uploader_id': compat_str(author['id']) if author else None, + 'upload_date': unified_strdate(video['created_ts']), + 'age_limit': 18 if video['is_adult'] else 0, } + + +class RutubeChannelIE(InfoExtractor): + IE_NAME = 'rutube:channel' + IE_DESC = 'Rutube channels' + _VALID_URL = r'http://rutube\.ru/tags/video/(?P<id>\d+)' + + _PAGE_TEMPLATE = 'http://rutube.ru/api/tags/video/%s/?page=%s&format=json' + + def _extract_videos(self, channel_id, channel_title=None): + entries = [] + for pagenum in itertools.count(1): + api_response = self._download_webpage( + self._PAGE_TEMPLATE % (channel_id, pagenum), + channel_id, 'Downloading page %s' % pagenum) + page = json.loads(api_response) + results = page['results'] + if not results: + break + entries.extend(self.url_result(result['video_url'], 'Rutube') for result in results) + if not page['has_next']: + break + return self.playlist_result(entries, channel_id, channel_title) + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + channel_id = mobj.group('id') + return self._extract_videos(channel_id) + + +class RutubeMovieIE(RutubeChannelIE): + IE_NAME = 'rutube:movie' + IE_DESC = 'Rutube movies' + _VALID_URL = r'http://rutube\.ru/metainfo/tv/(?P<id>\d+)' + + _MOVIE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/?format=json' + _PAGE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/video?page=%s&format=json' + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + movie_id = mobj.group('id') + api_response = self._download_webpage( + self._MOVIE_TEMPLATE % movie_id, movie_id, + 'Downloading movie JSON') + movie = json.loads(api_response) + movie_name = movie['name'] + return self._extract_videos(movie_id, movie_name) + + +class RutubePersonIE(RutubeChannelIE): + IE_NAME = 'rutube:person' + IE_DESC = 'Rutube person videos' + _VALID_URL = r'http://rutube\.ru/video/person/(?P<id>\d+)' + + _PAGE_TEMPLATE = 'http://rutube.ru/api/video/person/%s/?page=%s&format=json' |