1
0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-11-15 11:33:30 +01:00

[twitter:amplify] Add TwitterAmplifyIE for handling Twitter smart URLs

Closes #8075
This commit is contained in:
Yen Chi Hsuan 2016-02-21 16:41:24 +08:00
parent 92c5e11b40
commit 445d72b8b5
2 changed files with 42 additions and 5 deletions

View File

@ -798,7 +798,11 @@ from .twitch import (
TwitchBookmarksIE,
TwitchStreamIE,
)
from .twitter import TwitterCardIE, TwitterIE
from .twitter import (
TwitterCardIE,
TwitterIE,
TwitterAmplifyIE,
)
from .ubu import UbuIE
from .udemy import (
UdemyIE,

View File

@ -14,7 +14,13 @@ from ..utils import (
)
class TwitterCardIE(InfoExtractor):
class TwitterBaseIE(InfoExtractor):
def _get_vmap_video_url(self, vmap_url, video_id):
vmap_data = self._download_xml(vmap_url, video_id)
return xpath_text(vmap_data, './/MediaFile').strip()
class TwitterCardIE(TwitterBaseIE):
IE_NAME = 'twitter:card'
_VALID_URL = r'https?://(?:www\.)?twitter\.com/i/cards/tfw/v1/(?P<id>\d+)'
_TESTS = [
@ -96,10 +102,8 @@ class TwitterCardIE(InfoExtractor):
video_id)
if 'playlist' not in config:
if 'vmapUrl' in config:
vmap_data = self._download_xml(config['vmapUrl'], video_id)
video_url = xpath_text(vmap_data, './/MediaFile').strip()
formats.append({
'url': video_url,
'url': self._get_vmap_video_url(config['vmapUrl'], video_id),
})
break # same video regardless of UA
continue
@ -226,3 +230,32 @@ class TwitterIE(InfoExtractor):
return info
raise ExtractorError('There\'s not video in this tweet.')
class TwitterAmplifyIE(TwitterBaseIE):
IE_NAME = 'twitter:amplify'
_VALID_URL = 'https?://amp\.twimg\.com/v/(?P<id>[0-9a-f\-]{36})'
_TEST = {
'url': 'https://amp.twimg.com/v/0ba0c3c7-0af3-4c0a-bed5-7efd1ffa2951',
'md5': '7df102d0b9fd7066b86f3159f8e81bf6',
'info_dict': {
'id': '0ba0c3c7-0af3-4c0a-bed5-7efd1ffa2951',
'ext': 'mp4',
'title': 'Twitter Video',
},
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
vmap_url = self._html_search_meta(
'twitter:amplify:vmap', webpage, 'vmap url')
video_url = self._get_vmap_video_url(vmap_url, video_id)
return {
'id': video_id,
'title': 'Twitter Video',
'url': video_url,
}