1
0
Fork 0
mirror of https://gitlab.com/dstftw/youtube-dl.git synced 2020-11-16 09:42:26 +00:00

[twitter] Support twitter.com/i/videos/tweet/ URLS

Closes #8737
This commit is contained in:
Yen Chi Hsuan 2016-03-03 13:39:04 +08:00
parent 4459bef203
commit 0ae937a798

View file

@ -22,7 +22,7 @@ class TwitterBaseIE(InfoExtractor):
class TwitterCardIE(TwitterBaseIE): class TwitterCardIE(TwitterBaseIE):
IE_NAME = 'twitter:card' IE_NAME = 'twitter:card'
_VALID_URL = r'https?://(?:www\.)?twitter\.com/i/cards/tfw/v1/(?P<id>\d+)' _VALID_URL = r'https?://(?:www\.)?twitter\.com/i/(?:cards/tfw/v1|videos/tweet)/(?P<id>\d+)'
_TESTS = [ _TESTS = [
{ {
'url': 'https://twitter.com/i/cards/tfw/v1/560070183650213889', 'url': 'https://twitter.com/i/cards/tfw/v1/560070183650213889',
@ -30,7 +30,7 @@ class TwitterCardIE(TwitterBaseIE):
'info_dict': { 'info_dict': {
'id': '560070183650213889', 'id': '560070183650213889',
'ext': 'mp4', 'ext': 'mp4',
'title': 'TwitterCard', 'title': 'Twitter Card',
'thumbnail': 're:^https?://.*\.jpg$', 'thumbnail': 're:^https?://.*\.jpg$',
'duration': 30.033, 'duration': 30.033,
} }
@ -41,7 +41,7 @@ class TwitterCardIE(TwitterBaseIE):
'info_dict': { 'info_dict': {
'id': '623160978427936768', 'id': '623160978427936768',
'ext': 'mp4', 'ext': 'mp4',
'title': 'TwitterCard', 'title': 'Twitter Card',
'thumbnail': 're:^https?://.*\.jpg', 'thumbnail': 're:^https?://.*\.jpg',
'duration': 80.155, 'duration': 80.155,
}, },
@ -72,7 +72,16 @@ class TwitterCardIE(TwitterBaseIE):
'title': 'Vine by ArsenalTerje', 'title': 'Vine by ArsenalTerje',
}, },
'add_ie': ['Vine'], 'add_ie': ['Vine'],
} }, {
'url': 'https://twitter.com/i/videos/tweet/705235433198714880',
'md5': '3846d0a07109b5ab622425449b59049d',
'info_dict': {
'id': '705235433198714880',
'ext': 'mp4',
'title': 'Twitter web player',
'thumbnail': 're:^https?://.*\.jpg',
},
},
] ]
def _real_extract(self, url): def _real_extract(self, url):
@ -98,12 +107,13 @@ class TwitterCardIE(TwitterBaseIE):
return self.url_result(iframe_url) return self.url_result(iframe_url)
config = self._parse_json(self._html_search_regex( config = self._parse_json(self._html_search_regex(
r'data-player-config="([^"]+)"', webpage, 'data player config'), r'data-(?:player-)?config="([^"]+)"', webpage, 'data player config'),
video_id) video_id)
if 'playlist' not in config: if 'playlist' not in config:
if 'vmapUrl' in config: vmap_url = config.get('vmapUrl') or config.get('vmap_url')
if vmap_url:
formats.append({ formats.append({
'url': self._get_vmap_video_url(config['vmapUrl'], video_id), 'url': self._get_vmap_video_url(vmap_url, video_id),
}) })
break # same video regardless of UA break # same video regardless of UA
continue continue
@ -123,12 +133,13 @@ class TwitterCardIE(TwitterBaseIE):
formats.append(f) formats.append(f)
self._sort_formats(formats) self._sort_formats(formats)
thumbnail = config.get('posterImageUrl') 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')) duration = float_or_none(config.get('duration'))
return { return {
'id': video_id, 'id': video_id,
'title': 'TwitterCard', 'title': title,
'thumbnail': thumbnail, 'thumbnail': thumbnail,
'duration': duration, 'duration': duration,
'formats': formats, 'formats': formats,
@ -177,6 +188,21 @@ class TwitterIE(InfoExtractor):
'uploader_id': 'starwars', 'uploader_id': 'starwars',
'uploader': 'Star Wars', 'uploader': 'Star Wars',
}, },
}, {
'url': 'https://twitter.com/BTNBrentYarina/status/705235433198714880',
'info_dict': {
'id': '705235433198714880',
'ext': 'mp4',
'title': 'Brent Yarina - Khalil Iverson\'s missed highlight dunk. And made highlight dunk. In one highlight.',
'description': 'Brent Yarina on Twitter: "Khalil Iverson\'s missed highlight dunk. And made highlight dunk. In one highlight."',
'uploader_id': 'BTNBrentYarina',
'uploader': 'Brent Yarina',
},
'params': {
# The same video as https://twitter.com/i/videos/tweet/705235433198714880
# Test case of TwitterCardIE
'skip_download': True,
},
}] }]
def _real_extract(self, url): def _real_extract(self, url):
@ -234,6 +260,15 @@ class TwitterIE(InfoExtractor):
}) })
return info return info
if 'class="PlayableMedia' in webpage:
info.update({
'_type': 'url_transparent',
'ie_key': 'TwitterCard',
'url': '%s//twitter.com/i/videos/tweet/%s' % (self.http_scheme(), twid),
})
return info
raise ExtractorError('There\'s no video in this tweet.') raise ExtractorError('There\'s no video in this tweet.')