From 1547c8cc881b85f9f400f29c30b3a352eb679608 Mon Sep 17 00:00:00 2001 From: dst Date: Tue, 28 Jan 2014 06:56:09 +0700 Subject: [PATCH 1/4] [rutube] Add support for channels and movies --- youtube_dl/extractor/__init__.py | 6 ++- youtube_dl/extractor/rutube.py | 74 +++++++++++++++++++++++++++----- 2 files changed, 69 insertions(+), 11 deletions(-) diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 1e8556124a..19ca5d6b4b 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -161,7 +161,11 @@ 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 +) from .servingsys import ServingSysIE from .sina import SinaIE from .slashdot import SlashdotIE diff --git a/youtube_dl/extractor/rutube.py b/youtube_dl/extractor/rutube.py index e3e9bc07ff..2001a83ef7 100644 --- a/youtube_dl/extractor/rutube.py +++ b/youtube_dl/extractor/rutube.py @@ -1,6 +1,9 @@ # encoding: utf-8 +from __future__ import unicode_literals + import re import json +import itertools from .common import InfoExtractor from ..utils import ( @@ -11,26 +14,28 @@ from ..utils import ( class RutubeIE(InfoExtractor): + IE_NAME = 'rutube' + IE_DESC = 'Rutube videos' _VALID_URL = r'https?://rutube\.ru/video/(?P\w+)' _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', + 'uploader': 'NTDRussian', + 'uploader_id': '29790', }, - 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) + 'Downloading %s json' % subpath) return json.loads(response_json) def _real_extract(self, url): @@ -45,7 +50,7 @@ class RutubeIE(InfoExtractor): 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'], @@ -56,3 +61,52 @@ class RutubeIE(InfoExtractor): 'uploader': author.get('name'), 'uploader_id': compat_str(author['id']) if author else None, } + + +class RutubeChannelIE(InfoExtractor): + IE_NAME = 'rutube:channel' + IE_DESC = 'Rutube channels' + _VALID_URL = r'http://rutube\.ru/tags/video/(?P\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): + response_json = self._download_webpage(self._PAGE_TEMPLATE % (channel_id, pagenum), + channel_id, 'Downloading page %s' % pagenum) + page = json.loads(response_json) + if 'detail' in page and page['detail'] == 'Not found': + raise ExtractorError('Channel %s does not exist' % channel_id, expected=True) + results = page['results'] + if len(results) == 0: + break; + entries.extend(self.url_result(v['video_url'], 'Rutube') for v in results) + if page['has_next'] is False: + 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\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') + movie_json = self._download_webpage(self._MOVIE_TEMPLATE % movie_id, movie_id, + 'Downloading movie JSON') + movie = json.loads(movie_json) + if 'detail' in movie and movie['detail'] == 'Not found': + raise ExtractorError('Movie %s does not exist' % movie_id, expected=True) + movie_name = movie['name'] + return self._extract_videos(movie_id, movie_name) \ No newline at end of file From a2fb2a213452f0f8b4e9fea9518ad148e1b1e6d4 Mon Sep 17 00:00:00 2001 From: dst Date: Tue, 28 Jan 2014 08:19:45 +0700 Subject: [PATCH 2/4] [rutube] Improve video extractor --- youtube_dl/extractor/rutube.py | 47 +++++++++++++++++----------------- 1 file changed, 23 insertions(+), 24 deletions(-) diff --git a/youtube_dl/extractor/rutube.py b/youtube_dl/extractor/rutube.py index 2001a83ef7..6075296ffe 100644 --- a/youtube_dl/extractor/rutube.py +++ b/youtube_dl/extractor/rutube.py @@ -7,8 +7,8 @@ import itertools from .common import InfoExtractor from ..utils import ( - compat_urlparse, compat_str, + unified_strdate, ExtractorError, ) @@ -32,20 +32,18 @@ class RutubeIE(InfoExtractor): }, } - 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, - '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') + + api_response = self._download_webpage('http://rutube.ru/api/video/%s/?format=json' % long_id, + long_id, 'Downloading video JSON') + video = json.loads(api_response) + + api_response = self._download_webpage('http://rutube.ru/api/play/trackinfo/%s/?format=json' % long_id, + long_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') @@ -53,13 +51,18 @@ class RutubeIE(InfoExtractor): 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, } @@ -73,15 +76,13 @@ class RutubeChannelIE(InfoExtractor): def _extract_videos(self, channel_id, channel_title=None): entries = [] for pagenum in itertools.count(1): - response_json = self._download_webpage(self._PAGE_TEMPLATE % (channel_id, pagenum), + api_response = self._download_webpage(self._PAGE_TEMPLATE % (channel_id, pagenum), channel_id, 'Downloading page %s' % pagenum) - page = json.loads(response_json) - if 'detail' in page and page['detail'] == 'Not found': - raise ExtractorError('Channel %s does not exist' % channel_id, expected=True) + page = json.loads(api_response) results = page['results'] if len(results) == 0: break; - entries.extend(self.url_result(v['video_url'], 'Rutube') for v in results) + entries.extend(self.url_result(result['video_url'], 'Rutube') for result in results) if page['has_next'] is False: break; return self.playlist_result(entries, channel_id, channel_title) @@ -103,10 +104,8 @@ class RutubeMovieIE(RutubeChannelIE): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) movie_id = mobj.group('id') - movie_json = self._download_webpage(self._MOVIE_TEMPLATE % movie_id, movie_id, + api_response = self._download_webpage(self._MOVIE_TEMPLATE % movie_id, movie_id, 'Downloading movie JSON') - movie = json.loads(movie_json) - if 'detail' in movie and movie['detail'] == 'Not found': - raise ExtractorError('Movie %s does not exist' % movie_id, expected=True) + movie = json.loads(api_response) movie_name = movie['name'] return self._extract_videos(movie_id, movie_name) \ No newline at end of file From 87fac3238d09a4298d6cfa66f8753c734b81e5b7 Mon Sep 17 00:00:00 2001 From: dst Date: Tue, 28 Jan 2014 08:25:56 +0700 Subject: [PATCH 3/4] [rutube] Add channel test --- test/test_playlists.py | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/test/test_playlists.py b/test/test_playlists.py index 5eeba091ee..3861224b02 100644 --- a/test/test_playlists.py +++ b/test/test_playlists.py @@ -33,6 +33,7 @@ from youtube_dl.extractor import ( ImdbListIE, KhanAcademyIE, EveryonesMixtapeIE, + RutubeChannelIE, ) @@ -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__': From e3a9f32f52bbd9be8b38d70a529808f123126ce7 Mon Sep 17 00:00:00 2001 From: dst Date: Tue, 28 Jan 2014 08:47:17 +0700 Subject: [PATCH 4/4] [rutube] Add support for user videos --- youtube_dl/extractor/__init__.py | 3 ++- youtube_dl/extractor/rutube.py | 22 +++++++++++++++------- 2 files changed, 17 insertions(+), 8 deletions(-) diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 19ca5d6b4b..e89b5cf9de 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -164,7 +164,8 @@ from .rtlnow import RTLnowIE from .rutube import ( RutubeIE, RutubeChannelIE, - RutubeMovieIE + RutubeMovieIE, + RutubePersonIE, ) from .servingsys import ServingSysIE from .sina import SinaIE diff --git a/youtube_dl/extractor/rutube.py b/youtube_dl/extractor/rutube.py index 6075296ffe..9a20facfd8 100644 --- a/youtube_dl/extractor/rutube.py +++ b/youtube_dl/extractor/rutube.py @@ -16,7 +16,7 @@ from ..utils import ( class RutubeIE(InfoExtractor): IE_NAME = 'rutube' IE_DESC = 'Rutube videos' - _VALID_URL = r'https?://rutube\.ru/video/(?P\w+)' + _VALID_URL = r'https?://rutube\.ru/video/(?P[\da-z]{32})' _TEST = { 'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/', @@ -34,14 +34,14 @@ class RutubeIE(InfoExtractor): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - long_id = mobj.group('long_id') + video_id = mobj.group('id') - api_response = self._download_webpage('http://rutube.ru/api/video/%s/?format=json' % long_id, - long_id, 'Downloading video JSON') + 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' % long_id, - long_id, 'Downloading trackinfo JSON') + 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 @@ -108,4 +108,12 @@ class RutubeMovieIE(RutubeChannelIE): 'Downloading movie JSON') movie = json.loads(api_response) movie_name = movie['name'] - return self._extract_videos(movie_id, movie_name) \ No newline at end of file + 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\d+)' + + _PAGE_TEMPLATE = 'http://rutube.ru/api/video/person/%s/?page=%s&format=json' \ No newline at end of file