From 1547c8cc881b85f9f400f29c30b3a352eb679608 Mon Sep 17 00:00:00 2001 From: dst Date: Tue, 28 Jan 2014 06:56:09 +0700 Subject: [PATCH] [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 1e8556124..19ca5d6b4 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 e3e9bc07f..2001a83ef 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 -- 2.22.2