Fix some regexes

[youtube-dl] / youtube_dl / extractor / twitter.py

diff --git a/youtube_dl/extractor/twitter.py b/youtube_dl/extractor/twitter.py
index 2ff55412b13773a34b27b86dd627c08491a60279..1b0b9637160f3c096b4baf07f6146bc9d84a31c8 100644 (file)
--- a/youtube_dl/extractor/twitter.py
+++ b/youtube_dl/extractor/twitter.py
@@ -54,7 +54,8 @@ class TwitterCardIE(TwitterBaseIE):
                 'title': 'Twitter Card',
                 'thumbnail': r're:^https?://.*\.jpg$',
                 'duration': 30.033,
-            }
+            },
+            'skip': 'Video gone',
         },
         {
             'url': 'https://twitter.com/i/cards/tfw/v1/623160978427936768',
@@ -66,6 +67,7 @@ class TwitterCardIE(TwitterBaseIE):
                 'thumbnail': r're:^https?://.*\.jpg',
                 'duration': 80.155,
             },
+            'skip': 'Video gone',
         },
         {
             'url': 'https://twitter.com/i/cards/tfw/v1/654001591733886977',
@@ -83,7 +85,7 @@ class TwitterCardIE(TwitterBaseIE):
         },
         {
             'url': 'https://twitter.com/i/cards/tfw/v1/665289828897005568',
-            'md5': 'ab2745d0b0ce53319a534fccaa986439',
+            'md5': '6dabeaca9e68cbb71c99c322a4b42a11',
             'info_dict': {
                 'id': 'iBb2x00UVlv',
                 'ext': 'mp4',
@@ -96,12 +98,12 @@ class TwitterCardIE(TwitterBaseIE):
             'add_ie': ['Vine'],
         }, {
             'url': 'https://twitter.com/i/videos/tweet/705235433198714880',
-            'md5': '3846d0a07109b5ab622425449b59049d',
+            'md5': '884812a2adc8aaf6fe52b15ccbfa3b88',
             'info_dict': {
                 'id': '705235433198714880',
                 'ext': 'mp4',
                 'title': 'Twitter web player',
-                'thumbnail': r're:^https?://.*\.jpg',
+                'thumbnail': r're:^https?://.*',
             },
         }, {
             'url': 'https://twitter.com/i/videos/752274308186120192',
@@ -172,7 +174,7 @@ class TwitterCardIE(TwitterBaseIE):
         webpage = self._download_webpage(url, video_id)
 
         iframe_url = self._html_search_regex(
-            r'<iframe[^>]+src="((?:https?:)?//(?:www.youtube.com/embed/[^"]+|(?:www\.)?vine\.co/v/\w+/card))"',
+            r'<iframe[^>]+src="((?:https?:)?//(?:www\.youtube\.com/embed/[^"]+|(?:www\.)?vine\.co/v/\w+/card))"',
             webpage, 'video iframe', default=None)
         if iframe_url:
             return self.url_result(iframe_url)
@@ -227,7 +229,7 @@ class TwitterCardIE(TwitterBaseIE):
 
         title = self._search_regex(r'<title>([^<]+)</title>', webpage, 'title')
         thumbnail = config.get('posterImageUrl') or config.get('image_src')
-        duration = float_or_none(config.get('duration')) or duration
+        duration = float_or_none(config.get('duration'), scale=1000) or duration
 
         return {
             'id': video_id,
@@ -240,8 +242,9 @@ class TwitterCardIE(TwitterBaseIE):
 
 class TwitterIE(InfoExtractor):
     IE_NAME = 'twitter'
-    _VALID_URL = r'https?://(?:www\.|m\.|mobile\.)?twitter\.com/(?P<user_id>[^/]+)/status/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.|m\.|mobile\.)?twitter\.com/(?:i/web|(?P<user_id>[^/]+))/status/(?P<id>\d+)'
     _TEMPLATE_URL = 'https://twitter.com/%s/status/%s'
+    _TEMPLATE_STATUSES_URL = 'https://twitter.com/statuses/%s'
 
     _TESTS = [{
         'url': 'https://twitter.com/freethenipple/status/643211948184596480',
@@ -253,6 +256,7 @@ class TwitterIE(InfoExtractor):
             'description': 'FREE THE NIPPLE on Twitter: "FTN supporters on Hollywood Blvd today! http://t.co/c7jHH749xJ"',
             'uploader': 'FREE THE NIPPLE',
             'uploader_id': 'freethenipple',
+            'duration': 12.922,
         },
         'params': {
             'skip_download': True,  # requires ffmpeg
@@ -303,11 +307,12 @@ class TwitterIE(InfoExtractor):
         'info_dict': {
             'id': '700207533655363584',
             'ext': 'mp4',
-            'title': 'JG - BEAT PROD: @suhmeduh #Damndaniel',
-            'description': 'JG on Twitter: "BEAT PROD: @suhmeduh  https://t.co/HBrQ4AfpvZ #Damndaniel https://t.co/byBooq2ejZ"',
+            'title': 'あかさ - BEAT PROD: @suhmeduh #Damndaniel',
+            'description': 'あかさ on Twitter: "BEAT PROD: @suhmeduh  https://t.co/HBrQ4AfpvZ #Damndaniel https://t.co/byBooq2ejZ"',
             'thumbnail': r're:^https?://.*\.jpg',
-            'uploader': 'JG',
+            'uploader': 'あかさ',
             'uploader_id': 'jaydingeer',
+            'duration': 30.0,
         },
         'params': {
             'skip_download': True,  # requires ffmpeg
@@ -318,9 +323,11 @@ class TwitterIE(InfoExtractor):
         'info_dict': {
             'id': 'MIOxnrUteUd',
             'ext': 'mp4',
-            'title': 'Dr.Pepperの飲み方 #japanese #バカ #ドクペ #電動ガン',
-            'uploader': 'TAKUMA',
-            'uploader_id': '1004126642786242560',
+            'title': 'Vince Mancini - Vine of the day',
+            'description': 'Vince Mancini on Twitter: "Vine of the day https://t.co/xmTvRdqxWf"',
+            'uploader': 'Vince Mancini',
+            'uploader_id': 'Filmdrunk',
+            'timestamp': 1402826626,
             'upload_date': '20140615',
         },
         'add_ie': ['Vine'],
@@ -333,6 +340,7 @@ class TwitterIE(InfoExtractor):
             'description': 'Captain America on Twitter: "@King0fNerd Are you sure you made the right choice? Find out in theaters. https://t.co/GpgYi9xMJI"',
             'uploader_id': 'captainamerica',
             'uploader': 'Captain America',
+            'duration': 3.17,
         },
         'params': {
             'skip_download': True,  # requires ffmpeg
@@ -360,10 +368,26 @@ class TwitterIE(InfoExtractor):
             'description': 'عالم الأخبار on Twitter: "كلمة تاريخية بجلسة الجناسي التاريخية.. النائب خالد مؤنس العتيبي للمعارضين : اتقوا الله .. الظلم ظلمات يوم القيامة   https://t.co/xg6OhpyKfN"',
             'uploader': 'عالم الأخبار',
             'uploader_id': 'news_al3alm',
+            'duration': 277.4,
         },
         'params': {
             'format': 'best[format_id^=http-]',
         },
+    }, {
+        'url': 'https://twitter.com/i/web/status/910031516746514432',
+        'info_dict': {
+            'id': '910031516746514432',
+            'ext': 'mp4',
+            'title': 'Préfet de Guadeloupe - [Direct] #Maria Le centre se trouve actuellement au sud de Basse-Terre. Restez confinés. Réfugiez-vous dans la pièce la + sûre.',
+            'thumbnail': r're:^https?://.*\.jpg',
+            'description': 'Préfet de Guadeloupe on Twitter: "[Direct] #Maria Le centre se trouve actuellement au sud de Basse-Terre. Restez confinés. Réfugiez-vous dans la pièce la + sûre. https://t.co/mwx01Rs4lo"',
+            'uploader': 'Préfet de Guadeloupe',
+            'uploader_id': 'Prefet971',
+            'duration': 47.48,
+        },
+        'params': {
+            'skip_download': True,  # requires ffmpeg
+        },
     }]
 
     def _real_extract(self, url):
@@ -372,11 +396,15 @@ class TwitterIE(InfoExtractor):
         twid = mobj.group('id')
 
         webpage, urlh = self._download_webpage_handle(
-            self._TEMPLATE_URL % (user_id, twid), twid)
+            self._TEMPLATE_STATUSES_URL % twid, twid)
 
         if 'twitter.com/account/suspended' in urlh.geturl():
             raise ExtractorError('Account suspended by Twitter.', expected=True)
 
+        if user_id is None:
+            mobj = re.match(self._VALID_URL, urlh.geturl())
+            user_id = mobj.group('user_id')
+
         username = remove_end(self._og_search_title(webpage), ' on Twitter')
 
         title = description = self._og_search_description(webpage).strip('').replace('\n', ' ').strip('“”')