]> Raphaël G. Git Repositories - youtubedl/blobdiff - youtube_dl/extractor/aenetworks.py
Rapsys Git / youtubedl / blobdiff
? search:
summary | shortlog | log | commit | commitdiff | tree
raw | inline | side by side
debian/README.source: Update steps used to create new release.
[youtubedl] / youtube_dl / extractor / aenetworks.py
diff --git a/youtube_dl/extractor/aenetworks.py b/youtube_dl/extractor/aenetworks.py
index 6018ae79a2a114451c79edc34af524898462004d..85ec6392daf807b18253b815c0165afc07badbc0 100644 (file)
--- a/youtube_dl/extractor/aenetworks.py
+++ b/youtube_dl/extractor/aenetworks.py
@@ -1,66 +1,241 @@
 from __future__ import unicode_literals
 
 from __future__ import unicode_literals
 
-from .common import InfoExtractor
-from ..utils import smuggle_url
+import re
 
 
+from .theplatform import ThePlatformIE
+from ..utils import (
+    smuggle_url,
+    update_url_query,
+    unescapeHTML,
+    extract_attributes,
+    get_element_by_attribute,
+)
+from ..compat import (
+    compat_urlparse,
+)
 
 
-class AENetworksIE(InfoExtractor):
-    IE_NAME = 'aenetworks'
-    IE_DESC = 'A+E Networks: A&E, Lifetime, History.com, FYI Network'
-    _VALID_URL = r'https?://(?:www\.)?(?:(?:history|aetv|mylifetime)\.com|fyi\.tv)/(?:[^/]+/)+(?P<id>[^/]+?)(?:$|[?#])'
 
 
+class AENetworksBaseIE(ThePlatformIE):
+    _THEPLATFORM_KEY = 'crazyjava'
+    _THEPLATFORM_SECRET = 's3cr3t'
+
+
+class AENetworksIE(AENetworksBaseIE):
+    IE_NAME = 'aenetworks'
+    IE_DESC = 'A+E Networks: A&E, Lifetime, History.com, FYI Network and History Vault'
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:www\.)?
+                        (?P<domain>
+                            (?:history(?:vault)?|aetv|mylifetime|lifetimemovieclub)\.com|
+                            fyi\.tv
+                        )/
+                        (?:
+                            shows/(?P<show_path>[^/]+(?:/[^/]+){0,2})|
+                            movies/(?P<movie_display_id>[^/]+)(?:/full-movie)?|
+                            specials/(?P<special_display_id>[^/]+)/full-special|
+                            collections/[^/]+/(?P<collection_display_id>[^/]+)
+                        )
+                    '''
     _TESTS = [{
     _TESTS = [{
-        'url': 'http://www.history.com/topics/valentines-day/history-of-valentines-day/videos/bet-you-didnt-know-valentines-day?m=528e394da93ae&s=undefined&f=1&free=false',
+        'url': 'http://www.history.com/shows/mountain-men/season-1/episode-1',
+        'md5': 'a97a65f7e823ae10e9244bc5433d5fe6',
         'info_dict': {
         'info_dict': {
-            'id': 'g12m5Gyt3fdR',
+            'id': '22253814',
             'ext': 'mp4',
             'ext': 'mp4',
-            'title': "Bet You Didn't Know: Valentine's Day",
-            'description': 'md5:7b57ea4829b391995b405fa60bd7b5f7',
-        },
-        'params': {
-            # m3u8 download
-            'skip_download': True,
+            'title': 'Winter Is Coming',
+            'description': 'md5:641f424b7a19d8e24f26dea22cf59d74',
+            'timestamp': 1338306241,
+            'upload_date': '20120529',
+            'uploader': 'AENE-NEW',
         },
         'add_ie': ['ThePlatform'],
         },
         'add_ie': ['ThePlatform'],
-        'expected_warnings': ['JSON-LD'],
     }, {
     }, {
-        'url': 'http://www.history.com/shows/mountain-men/season-1/episode-1',
+        'url': 'http://www.history.com/shows/ancient-aliens/season-1',
         'info_dict': {
         'info_dict': {
-            'id': 'eg47EERs_JsZ',
-            'ext': 'mp4',
-            'title': 'Winter Is Coming',
-            'description': 'md5:641f424b7a19d8e24f26dea22cf59d74',
+            'id': '71889446852',
         },
         },
-        'params': {
-            # m3u8 download
-            'skip_download': True,
+        'playlist_mincount': 5,
+    }, {
+        'url': 'http://www.mylifetime.com/shows/atlanta-plastic',
+        'info_dict': {
+            'id': 'SERIES4317',
+            'title': 'Atlanta Plastic',
         },
         },
-        'add_ie': ['ThePlatform'],
+        'playlist_mincount': 2,
+    }, {
+        'url': 'http://www.aetv.com/shows/duck-dynasty/season-9/episode-1',
+        'only_matching': True
+    }, {
+        'url': 'http://www.fyi.tv/shows/tiny-house-nation/season-1/episode-8',
+        'only_matching': True
+    }, {
+        'url': 'http://www.mylifetime.com/shows/project-runway-junior/season-1/episode-6',
+        'only_matching': True
     }, {
     }, {
-        'url': 'http://www.aetv.com/shows/duck-dynasty/video/inlawful-entry',
+        'url': 'http://www.mylifetime.com/movies/center-stage-on-pointe/full-movie',
         'only_matching': True
     }, {
         'only_matching': True
     }, {
-        'url': 'http://www.fyi.tv/shows/tiny-house-nation/videos/207-sq-ft-minnesota-prairie-cottage',
+        'url': 'https://www.lifetimemovieclub.com/movies/a-killer-among-us',
         'only_matching': True
     }, {
         'only_matching': True
     }, {
-        'url': 'http://www.mylifetime.com/shows/project-runway-junior/video/season-1/episode-6/superstar-clients',
+        'url': 'http://www.history.com/specials/sniper-into-the-kill-zone/full-special',
+        'only_matching': True
+    }, {
+        'url': 'https://www.historyvault.com/collections/america-the-story-of-us/westward',
         'only_matching': True
     }]
         'only_matching': True
     }]
+    _DOMAIN_TO_REQUESTOR_ID = {
+        'history.com': 'HISTORY',
+        'aetv.com': 'AETV',
+        'mylifetime.com': 'LIFETIME',
+        'lifetimemovieclub.com': 'LIFETIMEMOVIECLUB',
+        'fyi.tv': 'FYI',
+    }
 
     def _real_extract(self, url):
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
-
-        webpage = self._download_webpage(url, video_id)
-
-        video_url_re = [
-            r'data-href="[^"]*/%s"[^>]+data-release-url="([^"]+)"' % video_id,
-            r"media_url\s*=\s*'([^']+)'"
-        ]
-        video_url = self._search_regex(video_url_re, webpage, 'video url')
+        domain, show_path, movie_display_id, special_display_id, collection_display_id = re.match(self._VALID_URL, url).groups()
+        display_id = show_path or movie_display_id or special_display_id or collection_display_id
+        webpage = self._download_webpage(url, display_id, headers=self.geo_verification_headers())
+        if show_path:
+            url_parts = show_path.split('/')
+            url_parts_len = len(url_parts)
+            if url_parts_len == 1:
+                entries = []
+                for season_url_path in re.findall(r'(?s)<li[^>]+data-href="(/shows/%s/season-\d+)"' % url_parts[0], webpage):
+                    entries.append(self.url_result(
+                        compat_urlparse.urljoin(url, season_url_path), 'AENetworks'))
+                if entries:
+                    return self.playlist_result(
+                        entries, self._html_search_meta('aetn:SeriesId', webpage),
+                        self._html_search_meta('aetn:SeriesTitle', webpage))
+                else:
+                    # single season
+                    url_parts_len = 2
+            if url_parts_len == 2:
+                entries = []
+                for episode_item in re.findall(r'(?s)<[^>]+class="[^"]*(?:episode|program)-item[^"]*"[^>]*>', webpage):
+                    episode_attributes = extract_attributes(episode_item)
+                    episode_url = compat_urlparse.urljoin(
+                        url, episode_attributes['data-canonical'])
+                    entries.append(self.url_result(
+                        episode_url, 'AENetworks',
+                        episode_attributes.get('data-videoid') or episode_attributes.get('data-video-id')))
+                return self.playlist_result(
+                    entries, self._html_search_meta('aetn:SeasonId', webpage))
 
 
-        info = self._search_json_ld(webpage, video_id, fatal=False)
+        query = {
+            'mbr': 'true',
+            'assetTypes': 'high_video_ak',
+            'switch': 'hls_high_ak',
+        }
+        video_id = self._html_search_meta('aetn:VideoID', webpage)
+        media_url = self._search_regex(
+            [r"media_url\s*=\s*'(?P<url>[^']+)'",
+             r'data-media-url=(?P<url>(?:https?:)?//[^\s>]+)',
+             r'data-media-url=(["\'])(?P<url>(?:(?!\1).)+?)\1'],
+            webpage, 'video url', group='url')
+        theplatform_metadata = self._download_theplatform_metadata(self._search_regex(
+            r'https?://link\.theplatform\.com/s/([^?]+)', media_url, 'theplatform_path'), video_id)
+        info = self._parse_theplatform_metadata(theplatform_metadata)
+        if theplatform_metadata.get('AETN$isBehindWall'):
+            requestor_id = self._DOMAIN_TO_REQUESTOR_ID[domain]
+            resource = self._get_mvpd_resource(
+                requestor_id, theplatform_metadata['title'],
+                theplatform_metadata.get('AETN$PPL_pplProgramId') or theplatform_metadata.get('AETN$PPL_pplProgramId_OLD'),
+                theplatform_metadata['ratings'][0]['rating'])
+            query['auth'] = self._extract_mvpd_auth(
+                url, video_id, requestor_id, resource)
+        info.update(self._search_json_ld(webpage, video_id, fatal=False))
+        media_url = update_url_query(media_url, query)
+        media_url = self._sign_url(media_url, self._THEPLATFORM_KEY, self._THEPLATFORM_SECRET)
+        formats, subtitles = self._extract_theplatform_smil(media_url, video_id)
+        self._sort_formats(formats)
         info.update({
         info.update({
-            '_type': 'url_transparent',
-            'url': smuggle_url(video_url, {'sig': {'key': 'crazyjava', 'secret': 's3cr3t'}}),
+            'id': video_id,
+            'formats': formats,
+            'subtitles': subtitles,
         })
         return info
         })
         return info
+
+
+class HistoryTopicIE(AENetworksBaseIE):
+    IE_NAME = 'history:topic'
+    IE_DESC = 'History.com Topic'
+    _VALID_URL = r'https?://(?:www\.)?history\.com/topics/(?:[^/]+/)?(?P<topic_id>[^/]+)(?:/[^/]+(?:/(?P<video_display_id>[^/?#]+))?)?'
+    _TESTS = [{
+        'url': 'http://www.history.com/topics/valentines-day/history-of-valentines-day/videos/bet-you-didnt-know-valentines-day?m=528e394da93ae&s=undefined&f=1&free=false',
+        'info_dict': {
+            'id': '40700995724',
+            'ext': 'mp4',
+            'title': "Bet You Didn't Know: Valentine's Day",
+            'description': 'md5:7b57ea4829b391995b405fa60bd7b5f7',
+            'timestamp': 1375819729,
+            'upload_date': '20130806',
+            'uploader': 'AENE-NEW',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+        'add_ie': ['ThePlatform'],
+    }, {
+        'url': 'http://www.history.com/topics/world-war-i/world-war-i-history/videos',
+        'info_dict':
+        {
+            'id': 'world-war-i-history',
+            'title': 'World War I History',
+        },
+        'playlist_mincount': 23,
+    }, {
+        'url': 'http://www.history.com/topics/world-war-i-history/videos',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.history.com/topics/world-war-i/world-war-i-history',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.history.com/topics/world-war-i/world-war-i-history/speeches',
+        'only_matching': True,
+    }]
+
+    def theplatform_url_result(self, theplatform_url, video_id, query):
+        return {
+            '_type': 'url_transparent',
+            'id': video_id,
+            'url': smuggle_url(
+                update_url_query(theplatform_url, query),
+                {
+                    'sig': {
+                        'key': self._THEPLATFORM_KEY,
+                        'secret': self._THEPLATFORM_SECRET,
+                    },
+                    'force_smil_url': True
+                }),
+            'ie_key': 'ThePlatform',
+        }
+
+    def _real_extract(self, url):
+        topic_id, video_display_id = re.match(self._VALID_URL, url).groups()
+        if video_display_id:
+            webpage = self._download_webpage(url, video_display_id)
+            release_url, video_id = re.search(r"_videoPlayer.play\('([^']+)'\s*,\s*'[^']+'\s*,\s*'(\d+)'\)", webpage).groups()
+            release_url = unescapeHTML(release_url)
+
+            return self.theplatform_url_result(
+                release_url, video_id, {
+                    'mbr': 'true',
+                    'switch': 'hls',
+                    'assetTypes': 'high_video_ak',
+                })
+        else:
+            webpage = self._download_webpage(url, topic_id)
+            entries = []
+            for episode_item in re.findall(r'<a.+?data-release-url="[^"]+"[^>]*>', webpage):
+                video_attributes = extract_attributes(episode_item)
+                entries.append(self.theplatform_url_result(
+                    video_attributes['data-release-url'], video_attributes['data-id'], {
+                        'mbr': 'true',
+                        'switch': 'hls',
+                        'assetTypes': 'high_video_ak',
+                    }))
+            return self.playlist_result(entries, topic_id, get_element_by_attribute('class', 'show-title', webpage))
Backup clone of https://github.com/ytdl-org unavailable since RIAA fucking raid...