Merge pull request #1 from e7appew/python3

[youtubedl] / youtube_dl / extractor / comedycentral.py

diff --git a/youtube_dl/extractor/comedycentral.py b/youtube_dl/extractor/comedycentral.py
index b2453898199ed72da7df13fa90714572fad22133..88346dde7754a124e2b1d88d5ab8291dca4ca632 100644 (file)
--- a/youtube_dl/extractor/comedycentral.py
+++ b/youtube_dl/extractor/comedycentral.py
@@ -1,271 +1,118 @@
 from __future__ import unicode_literals
 
 from __future__ import unicode_literals
 

-import re
-

 from .mtv import MTVServicesInfoExtractor
 from .mtv import MTVServicesInfoExtractor

-from ..compat import (
-    compat_str,
-    compat_urllib_parse,
-)
-from ..utils import (
-    ExtractorError,
-    float_or_none,
-    unified_strdate,
-)
+from .common import InfoExtractor

 
 
 class ComedyCentralIE(MTVServicesInfoExtractor):
     _VALID_URL = r'''(?x)https?://(?:www\.)?cc\.com/
 
 
 class ComedyCentralIE(MTVServicesInfoExtractor):
     _VALID_URL = r'''(?x)https?://(?:www\.)?cc\.com/

-        (video-clips|episodes|cc-studios|video-collections|full-episodes)
+        (video-clips|episodes|cc-studios|video-collections|full-episodes|shows)

         /(?P<title>.*)'''
     _FEED_URL = 'http://comedycentral.com/feeds/mrss/'
 
         /(?P<title>.*)'''
     _FEED_URL = 'http://comedycentral.com/feeds/mrss/'
 

-    _TEST = {
+    _TESTS = [{

         'url': 'http://www.cc.com/video-clips/kllhuv/stand-up-greg-fitzsimmons--uncensored---too-good-of-a-mother',
         'md5': 'c4f48e9eda1b16dd10add0744344b6d8',
         'info_dict': {
             'id': 'cef0cbb3-e776-4bc9-b62e-8016deccb354',
             'ext': 'mp4',
         'url': 'http://www.cc.com/video-clips/kllhuv/stand-up-greg-fitzsimmons--uncensored---too-good-of-a-mother',
         'md5': 'c4f48e9eda1b16dd10add0744344b6d8',
         'info_dict': {
             'id': 'cef0cbb3-e776-4bc9-b62e-8016deccb354',
             'ext': 'mp4',

-            'title': 'CC:Stand-Up|Greg Fitzsimmons: Life on Stage|Uncensored - Too Good of a Mother',
+            'title': 'CC:Stand-Up|August 18, 2013|1|0101|Uncensored - Too Good of a Mother',

             'description': 'After a certain point, breastfeeding becomes c**kblocking.',
             'description': 'After a certain point, breastfeeding becomes c**kblocking.',

+            'timestamp': 1376798400,
+            'upload_date': '20130818',

         },
         },

-    }
+    }, {
+        'url': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/interviews/6yx39d/exclusive-rand-paul-extended-interview',
+        'only_matching': True,
+    }]
+

 
 

+class ToshIE(MTVServicesInfoExtractor):
+    IE_DESC = 'Tosh.0'
+    _VALID_URL = r'^https?://tosh\.cc\.com/video-(?:clips|collections)/[^/]+/(?P<videotitle>[^/?#]+)'
+    _FEED_URL = 'http://tosh.cc.com/feeds/mrss'

 
 

-class ComedyCentralShowsIE(MTVServicesInfoExtractor):
-    IE_DESC = 'The Daily Show / The Colbert Report'
-    # urls can be abbreviations like :thedailyshow
-    # urls for episodes like:
-    # or urls for clips like: http://www.thedailyshow.com/watch/mon-december-10-2012/any-given-gun-day
-    #                     or: http://www.colbertnation.com/the-colbert-report-videos/421667/november-29-2012/moon-shattering-news
-    #                     or: http://www.colbertnation.com/the-colbert-report-collections/422008/festival-of-lights/79524
-    _VALID_URL = r'''(?x)^(:(?P<shortname>tds|thedailyshow)
-                      |https?://(:www\.)?
-                          (?P<showname>thedailyshow|thecolbertreport)\.(?:cc\.)?com/
-                         ((?:full-)?episodes/(?:[0-9a-z]{6}/)?(?P<episode>.*)|
-                          (?P<clip>
-                              (?:(?:guests/[^/]+|videos|video-playlists|special-editions|news-team/[^/]+)/[^/]+/(?P<videotitle>[^/?#]+))
-                              |(the-colbert-report-(videos|collections)/(?P<clipID>[0-9]+)/[^/]*/(?P<cntitle>.*?))
-                              |(watch/(?P<date>[^/]*)/(?P<tdstitle>.*))
-                          )|
-                          (?P<interview>
-                              extended-interviews/(?P<interID>[0-9a-z]+)/
-                              (?:playlist_tds_extended_)?(?P<interview_title>[^/?#]*?)
-                              (?:/[^/?#]?|[?#]|$))))
-                     '''

     _TESTS = [{
     _TESTS = [{

-        'url': 'http://thedailyshow.cc.com/watch/thu-december-13-2012/kristen-stewart',
-        'md5': '4e2f5cb088a83cd8cdb7756132f9739d',
-        'info_dict': {
-            'id': 'ab9ab3e7-5a98-4dbe-8b21-551dc0523d55',
-            'ext': 'mp4',
-            'upload_date': '20121213',
-            'description': 'Kristen Stewart learns to let loose in "On the Road."',
-            'uploader': 'thedailyshow',
-            'title': 'thedailyshow kristen-stewart part 1',
-        }
-    }, {
-        'url': 'http://thedailyshow.cc.com/extended-interviews/b6364d/sarah-chayes-extended-interview',
+        'url': 'http://tosh.cc.com/video-clips/68g93d/twitter-users-share-summer-plans',

         'info_dict': {
         'info_dict': {

-            'id': 'sarah-chayes-extended-interview',
-            'description': 'Carnegie Endowment Senior Associate Sarah Chayes discusses how corrupt institutions function throughout the world in her book "Thieves of State: Why Corruption Threatens Global Security."',
-            'title': 'thedailyshow Sarah Chayes Extended Interview',
+            'description': 'Tosh asked fans to share their summer plans.',
+            'title': 'Twitter Users Share Summer Plans',

         },
         },

-        'playlist': [
-            {
-                'info_dict': {
-                    'id': '0baad492-cbec-4ec1-9e50-ad91c291127f',
-                    'ext': 'mp4',
-                    'upload_date': '20150129',
-                    'description': 'Carnegie Endowment Senior Associate Sarah Chayes discusses how corrupt institutions function throughout the world in her book "Thieves of State: Why Corruption Threatens Global Security."',
-                    'uploader': 'thedailyshow',
-                    'title': 'thedailyshow sarah-chayes-extended-interview part 1',
+        'playlist': [{
+            'md5': 'f269e88114c1805bb6d7653fecea9e06',
+            'info_dict': {
+                'id': '90498ec2-ed00-11e0-aca6-0026b9414f30',
+                'ext': 'mp4',
+                'title': 'Tosh.0|June 9, 2077|2|211|Twitter Users Share Summer Plans',
+                'description': 'Tosh asked fans to share their summer plans.',
+                'thumbnail': 're:^https?://.*\.jpg',
+                # It's really reported to be published on year 2077
+                'upload_date': '20770610',
+                'timestamp': 3390510600,
+                'subtitles': {
+                    'en': 'mincount:3',

                 },
             },
                 },
             },

-            {
-                'info_dict': {
-                    'id': '1e4fb91b-8ce7-4277-bd7c-98c9f1bbd283',
-                    'ext': 'mp4',
-                    'upload_date': '20150129',
-                    'description': 'Carnegie Endowment Senior Associate Sarah Chayes discusses how corrupt institutions function throughout the world in her book "Thieves of State: Why Corruption Threatens Global Security."',
-                    'uploader': 'thedailyshow',
-                    'title': 'thedailyshow sarah-chayes-extended-interview part 2',
-                },
-            },
-        ],
+        }]
+    }, {
+        'url': 'http://tosh.cc.com/video-collections/x2iz7k/just-plain-foul/m5q4fp',
+        'only_matching': True,
+    }]
+
+    @classmethod
+    def _transform_rtmp_url(cls, rtmp_video_url):
+        new_urls = super(ToshIE, cls)._transform_rtmp_url(rtmp_video_url)
+        new_urls['rtmp'] = rtmp_video_url.replace('viacomccstrm', 'viacommtvstrm')
+        return new_urls
+
+
+class ComedyCentralTVIE(MTVServicesInfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?comedycentral\.tv/(?:staffeln|shows)/(?P<id>[^/?#&]+)'
+    _TESTS = [{
+        'url': 'http://www.comedycentral.tv/staffeln/7436-the-mindy-project-staffel-4',
+        'info_dict': {
+            'id': 'local_playlist-f99b626bdfe13568579a',
+            'ext': 'flv',
+            'title': 'Episode_the-mindy-project_shows_season-4_episode-3_full-episode_part1',
+        },

         'params': {
         'params': {

+            # rtmp download

             'skip_download': True,
         },
     }, {
             'skip_download': True,
         },
     }, {

-        'url': 'http://thedailyshow.cc.com/extended-interviews/xm3fnq/andrew-napolitano-extended-interview',
-        'only_matching': True,
-    }, {
-        'url': 'http://thecolbertreport.cc.com/videos/29w6fx/-realhumanpraise-for-fox-news',
-        'only_matching': True,
-    }, {
-        'url': 'http://thecolbertreport.cc.com/videos/gh6urb/neil-degrasse-tyson-pt--1?xrs=eml_col_031114',
-        'only_matching': True,
-    }, {
-        'url': 'http://thedailyshow.cc.com/guests/michael-lewis/3efna8/exclusive---michael-lewis-extended-interview-pt--3',
+        'url': 'http://www.comedycentral.tv/shows/1074-workaholics',

         'only_matching': True,
     }, {
         'only_matching': True,
     }, {

-        'url': 'http://thedailyshow.cc.com/episodes/sy7yv0/april-8--2014---denis-leary',
-        'only_matching': True,
-    }, {
-        'url': 'http://thecolbertreport.cc.com/episodes/8ase07/april-8--2014---jane-goodall',
-        'only_matching': True,
-    }, {
-        'url': 'http://thedailyshow.cc.com/video-playlists/npde3s/the-daily-show-19088-highlights',
-        'only_matching': True,
-    }, {
-        'url': 'http://thedailyshow.cc.com/video-playlists/t6d9sg/the-daily-show-20038-highlights/be3cwo',
-        'only_matching': True,
-    }, {
-        'url': 'http://thedailyshow.cc.com/special-editions/2l8fdb/special-edition---a-look-back-at-food',
-        'only_matching': True,
-    }, {
-        'url': 'http://thedailyshow.cc.com/news-team/michael-che/7wnfel/we-need-to-talk-about-israel',
+        'url': 'http://www.comedycentral.tv/shows/1727-the-mindy-project/bonus',

         'only_matching': True,
     }]
 
         'only_matching': True,
     }]
 

-    _available_formats = ['3500', '2200', '1700', '1200', '750', '400']
-
-    _video_extensions = {
-        '3500': 'mp4',
-        '2200': 'mp4',
-        '1700': 'mp4',
-        '1200': 'mp4',
-        '750': 'mp4',
-        '400': 'mp4',
-    }
-    _video_dimensions = {
-        '3500': (1280, 720),
-        '2200': (960, 540),
-        '1700': (768, 432),
-        '1200': (640, 360),
-        '750': (512, 288),
-        '400': (384, 216),
-    }
-

     def _real_extract(self, url):
     def _real_extract(self, url):

-        mobj = re.match(self._VALID_URL, url)
-
-        if mobj.group('shortname'):
-            if mobj.group('shortname') in ('tds', 'thedailyshow'):
-                url = 'http://thedailyshow.cc.com/full-episodes/'
-            else:
-                url = 'http://thecolbertreport.cc.com/full-episodes/'
-            mobj = re.match(self._VALID_URL, url, re.VERBOSE)
-            assert mobj is not None
-
-        if mobj.group('clip'):
-            if mobj.group('videotitle'):
-                epTitle = mobj.group('videotitle')
-            elif mobj.group('showname') == 'thedailyshow':
-                epTitle = mobj.group('tdstitle')
-            else:
-                epTitle = mobj.group('cntitle')
-            dlNewest = False
-        elif mobj.group('interview'):
-            epTitle = mobj.group('interview_title')
-            dlNewest = False
-        else:
-            dlNewest = not mobj.group('episode')
-            if dlNewest:
-                epTitle = mobj.group('showname')
-            else:
-                epTitle = mobj.group('episode')
-        show_name = mobj.group('showname')
+        video_id = self._match_id(url)

 
 

-        webpage, htmlHandle = self._download_webpage_handle(url, epTitle)
-        if dlNewest:
-            url = htmlHandle.geturl()
-            mobj = re.match(self._VALID_URL, url, re.VERBOSE)
-            if mobj is None:
-                raise ExtractorError('Invalid redirected URL: ' + url)
-            if mobj.group('episode') == '':
-                raise ExtractorError('Redirected URL is still not specific: ' + url)
-            epTitle = (mobj.group('episode') or mobj.group('videotitle')).rpartition('/')[-1]
+        webpage = self._download_webpage(url, video_id)

 
 

-        mMovieParams = re.findall('(?:<param name="movie" value="|var url = ")(http://media.mtvnservices.com/([^"]*(?:episode|video).*?:.*?))"', webpage)
-        if len(mMovieParams) == 0:
-            # The Colbert Report embeds the information in a without
-            # a URL prefix; so extract the alternate reference
-            # and then add the URL prefix manually.
+        mrss_url = self._search_regex(
+            r'data-mrss=(["\'])(?P<url>(?:(?!\1).)+)\1',
+            webpage, 'mrss url', group='url')

 
 

-            altMovieParams = re.findall('data-mgid="([^"]*(?:episode|video|playlist).*?:.*?)"', webpage)
-            if len(altMovieParams) == 0:
-                raise ExtractorError('unable to find Flash URL in webpage ' + url)
-            else:
-                mMovieParams = [("http://media.mtvnservices.com/" + altMovieParams[0], altMovieParams[0])]
+        return self._get_videos_info_from_url(mrss_url, video_id)

 
 

-        uri = mMovieParams[0][1]
-        # Correct cc.com in uri
-        uri = re.sub(r'(episode:[^.]+)(\.cc)?\.com', r'\1.cc.com', uri)

 
 

-        index_url = 'http://%s.cc.com/feeds/mrss?%s' % (show_name, compat_urllib_parse.urlencode({'uri': uri}))
-        idoc = self._download_xml(
-            index_url, epTitle,
-            'Downloading show index', 'Unable to download episode index')
-
-        title = idoc.find('./channel/title').text
-        description = idoc.find('./channel/description').text
-
-        entries = []
-        item_els = idoc.findall('.//item')
-        for part_num, itemEl in enumerate(item_els):
-            upload_date = unified_strdate(itemEl.findall('./pubDate')[0].text)
-            thumbnail = itemEl.find('.//{http://search.yahoo.com/mrss/}thumbnail').attrib.get('url')
-
-            content = itemEl.find('.//{http://search.yahoo.com/mrss/}content')
-            duration = float_or_none(content.attrib.get('duration'))
-            mediagen_url = content.attrib['url']
-            guid = itemEl.find('./guid').text.rpartition(':')[-1]
-
-            cdoc = self._download_xml(
-                mediagen_url, epTitle,
-                'Downloading configuration for segment %d / %d' % (part_num + 1, len(item_els)))
-
-            turls = []
-            for rendition in cdoc.findall('.//rendition'):
-                finfo = (rendition.attrib['bitrate'], rendition.findall('./src')[0].text)
-                turls.append(finfo)
-
-            formats = []
-            for format, rtmp_video_url in turls:
-                w, h = self._video_dimensions.get(format, (None, None))
-                formats.append({
-                    'format_id': 'vhttp-%s' % format,
-                    'url': self._transform_rtmp_url(rtmp_video_url),
-                    'ext': self._video_extensions.get(format, 'mp4'),
-                    'height': h,
-                    'width': w,
-                })
-                formats.append({
-                    'format_id': 'rtmp-%s' % format,
-                    'url': rtmp_video_url.replace('viacomccstrm', 'viacommtvstrm'),
-                    'ext': self._video_extensions.get(format, 'mp4'),
-                    'height': h,
-                    'width': w,
-                })
-                self._sort_formats(formats)
-
-            virtual_id = show_name + ' ' + epTitle + ' part ' + compat_str(part_num + 1)
-            entries.append({
-                'id': guid,
-                'title': virtual_id,
-                'formats': formats,
-                'uploader': show_name,
-                'upload_date': upload_date,
-                'duration': duration,
-                'thumbnail': thumbnail,
-                'description': description,
-            })
+class ComedyCentralShortnameIE(InfoExtractor):
+    _VALID_URL = r'^:(?P<id>tds|thedailyshow)$'
+    _TESTS = [{
+        'url': ':tds',
+        'only_matching': True,
+    }, {
+        'url': ':thedailyshow',
+        'only_matching': True,
+    }]

 
 

-        return {
-            '_type': 'playlist',
-            'id': epTitle,
-            'entries': entries,
-            'title': show_name + ' ' + title,
-            'description': description,
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        shortcut_map = {
+            'tds': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/full-episodes',
+            'thedailyshow': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/full-episodes',

         }
         }

+        return self.url_result(shortcut_map[video_id])