mirror of
https://github.com/ytdl-org/youtube-dl.git
synced 2024-11-10 11:31:19 +00:00
[twitter:card] Add extractor (#5239)
This commit is contained in:
parent
6c4d20cd6f
commit
23e7cba87f
2 changed files with 73 additions and 0 deletions
|
@ -621,6 +621,7 @@ from .twitch import (
|
||||||
TwitchBookmarksIE,
|
TwitchBookmarksIE,
|
||||||
TwitchStreamIE,
|
TwitchStreamIE,
|
||||||
)
|
)
|
||||||
|
from .twitter import TwitterCardIE
|
||||||
from .ubu import UbuIE
|
from .ubu import UbuIE
|
||||||
from .udemy import (
|
from .udemy import (
|
||||||
UdemyIE,
|
UdemyIE,
|
||||||
|
|
72
youtube_dl/extractor/twitter.py
Normal file
72
youtube_dl/extractor/twitter.py
Normal file
|
@ -0,0 +1,72 @@
|
||||||
|
from __future__ import unicode_literals
|
||||||
|
|
||||||
|
import re
|
||||||
|
|
||||||
|
from .common import InfoExtractor
|
||||||
|
from ..compat import compat_urllib_request
|
||||||
|
from ..utils import (
|
||||||
|
float_or_none,
|
||||||
|
unescapeHTML,
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
|
class TwitterCardIE(InfoExtractor):
|
||||||
|
_VALID_URL = r'https?://(?:www\.)?twitter\.com/i/cards/tfw/v1/(?P<id>\d+)'
|
||||||
|
_TEST = {
|
||||||
|
'url': 'https://twitter.com/i/cards/tfw/v1/560070183650213889',
|
||||||
|
'md5': 'a74f50b310c83170319ba16de6955192',
|
||||||
|
'info_dict': {
|
||||||
|
'id': '560070183650213889',
|
||||||
|
'ext': 'mp4',
|
||||||
|
'title': 'TwitterCard',
|
||||||
|
'thumbnail': 're:^https?://.*\.jpg$',
|
||||||
|
'duration': 30.033,
|
||||||
|
},
|
||||||
|
}
|
||||||
|
|
||||||
|
def _real_extract(self, url):
|
||||||
|
video_id = self._match_id(url)
|
||||||
|
|
||||||
|
# Different formats served for different User-Agents
|
||||||
|
USER_AGENTS = [
|
||||||
|
'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) Gecko/20150101 Firefox/20.0 (Chrome)', # mp4
|
||||||
|
'Mozilla/5.0 (Windows NT 5.2; WOW64; rv:38.0) Gecko/20100101 Firefox/38.0', # webm
|
||||||
|
]
|
||||||
|
|
||||||
|
config = None
|
||||||
|
formats = []
|
||||||
|
for user_agent in USER_AGENTS:
|
||||||
|
request = compat_urllib_request.Request(url)
|
||||||
|
request.add_header('User-Agent', user_agent)
|
||||||
|
webpage = self._download_webpage(request, video_id)
|
||||||
|
|
||||||
|
config = self._parse_json(
|
||||||
|
unescapeHTML(self._search_regex(
|
||||||
|
r'data-player-config="([^"]+)"', webpage, 'data player config')),
|
||||||
|
video_id)
|
||||||
|
|
||||||
|
video_url = config['playlist'][0]['source']
|
||||||
|
|
||||||
|
f = {
|
||||||
|
'url': video_url,
|
||||||
|
}
|
||||||
|
|
||||||
|
m = re.search(r'/(?P<width>\d+)x(?P<height>\d+)/', video_url)
|
||||||
|
if m:
|
||||||
|
f.update({
|
||||||
|
'width': int(m.group('width')),
|
||||||
|
'height': int(m.group('height')),
|
||||||
|
})
|
||||||
|
formats.append(f)
|
||||||
|
self._sort_formats(formats)
|
||||||
|
|
||||||
|
thumbnail = config.get('posterImageUrl')
|
||||||
|
duration = float_or_none(config.get('duration'))
|
||||||
|
|
||||||
|
return {
|
||||||
|
'id': video_id,
|
||||||
|
'title': 'TwitterCard',
|
||||||
|
'thumbnail': thumbnail,
|
||||||
|
'duration': duration,
|
||||||
|
'formats': formats,
|
||||||
|
}
|
Loading…
Reference in a new issue