mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-11-30 12:01:28 +00:00
parent
a54ffb8aa7
commit
f0bc5a8609
|
@ -4,6 +4,7 @@ Core
|
||||||
+ Improved support for HTML5 subtitles
|
+ Improved support for HTML5 subtitles
|
||||||
|
|
||||||
Extractors
|
Extractors
|
||||||
|
+ [twitter] Support Periscope embeds (#10737)
|
||||||
+ [openload] Support subtitles (#10625)
|
+ [openload] Support subtitles (#10625)
|
||||||
|
|
||||||
|
|
||||||
|
|
|
@ -1,6 +1,8 @@
|
||||||
# coding: utf-8
|
# coding: utf-8
|
||||||
from __future__ import unicode_literals
|
from __future__ import unicode_literals
|
||||||
|
|
||||||
|
import re
|
||||||
|
|
||||||
from .common import InfoExtractor
|
from .common import InfoExtractor
|
||||||
from ..utils import (
|
from ..utils import (
|
||||||
parse_iso8601,
|
parse_iso8601,
|
||||||
|
@ -41,6 +43,13 @@ class PeriscopeIE(PeriscopeBaseIE):
|
||||||
'only_matching': True,
|
'only_matching': True,
|
||||||
}]
|
}]
|
||||||
|
|
||||||
|
@staticmethod
|
||||||
|
def _extract_url(webpage):
|
||||||
|
mobj = re.search(
|
||||||
|
r'<iframe[^>]+src=([\'"])(?P<url>(?:https?:)?//(?:www\.)?periscope\.tv/(?:(?!\1).)+)\1', webpage)
|
||||||
|
if mobj:
|
||||||
|
return mobj.group('url')
|
||||||
|
|
||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
token = self._match_id(url)
|
token = self._match_id(url)
|
||||||
|
|
||||||
|
|
|
@ -4,6 +4,7 @@
|
||||||
import re
|
import re
|
||||||
|
|
||||||
from .common import InfoExtractor
|
from .common import InfoExtractor
|
||||||
|
from ..compat import compat_urlparse
|
||||||
from ..utils import (
|
from ..utils import (
|
||||||
determine_ext,
|
determine_ext,
|
||||||
float_or_none,
|
float_or_none,
|
||||||
|
@ -13,6 +14,8 @@
|
||||||
ExtractorError,
|
ExtractorError,
|
||||||
)
|
)
|
||||||
|
|
||||||
|
from .periscope import PeriscopeIE
|
||||||
|
|
||||||
|
|
||||||
class TwitterBaseIE(InfoExtractor):
|
class TwitterBaseIE(InfoExtractor):
|
||||||
def _get_vmap_video_url(self, vmap_url, video_id):
|
def _get_vmap_video_url(self, vmap_url, video_id):
|
||||||
|
@ -48,12 +51,12 @@ class TwitterCardIE(TwitterBaseIE):
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
'url': 'https://twitter.com/i/cards/tfw/v1/654001591733886977',
|
'url': 'https://twitter.com/i/cards/tfw/v1/654001591733886977',
|
||||||
'md5': 'd4724ffe6d2437886d004fa5de1043b3',
|
'md5': 'b6d9683dd3f48e340ded81c0e917ad46',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': 'dq4Oj5quskI',
|
'id': 'dq4Oj5quskI',
|
||||||
'ext': 'mp4',
|
'ext': 'mp4',
|
||||||
'title': 'Ubuntu 11.10 Overview',
|
'title': 'Ubuntu 11.10 Overview',
|
||||||
'description': 'Take a quick peek at what\'s new and improved in Ubuntu 11.10.\n\nOnce installed take a look at 10 Things to Do After Installing: http://www.omgubuntu.co.uk/2011/10/10...',
|
'description': 'md5:a831e97fa384863d6e26ce48d1c43376',
|
||||||
'upload_date': '20111013',
|
'upload_date': '20111013',
|
||||||
'uploader': 'OMG! Ubuntu!',
|
'uploader': 'OMG! Ubuntu!',
|
||||||
'uploader_id': 'omgubuntu',
|
'uploader_id': 'omgubuntu',
|
||||||
|
@ -100,12 +103,17 @@ def _real_extract(self, url):
|
||||||
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', default='{}'),
|
||||||
video_id)
|
video_id)
|
||||||
|
|
||||||
if config.get('source_type') == 'vine':
|
if config.get('source_type') == 'vine':
|
||||||
return self.url_result(config['player_url'], 'Vine')
|
return self.url_result(config['player_url'], 'Vine')
|
||||||
|
|
||||||
|
periscope_url = PeriscopeIE._extract_url(webpage)
|
||||||
|
if periscope_url:
|
||||||
|
return self.url_result(periscope_url, PeriscopeIE.ie_key())
|
||||||
|
|
||||||
def _search_dimensions_in_video_url(a_format, video_url):
|
def _search_dimensions_in_video_url(a_format, video_url):
|
||||||
m = re.search(r'/(?P<width>\d+)x(?P<height>\d+)/', video_url)
|
m = re.search(r'/(?P<width>\d+)x(?P<height>\d+)/', video_url)
|
||||||
if m:
|
if m:
|
||||||
|
@ -244,10 +252,10 @@ class TwitterIE(InfoExtractor):
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': '700207533655363584',
|
'id': '700207533655363584',
|
||||||
'ext': 'mp4',
|
'ext': 'mp4',
|
||||||
'title': 'Donte The Dumbass - BEAT PROD: @suhmeduh #Damndaniel',
|
'title': 'JG - BEAT PROD: @suhmeduh #Damndaniel',
|
||||||
'description': 'Donte The Dumbass on Twitter: "BEAT PROD: @suhmeduh https://t.co/HBrQ4AfpvZ #Damndaniel https://t.co/byBooq2ejZ"',
|
'description': 'JG on Twitter: "BEAT PROD: @suhmeduh https://t.co/HBrQ4AfpvZ #Damndaniel https://t.co/byBooq2ejZ"',
|
||||||
'thumbnail': 're:^https?://.*\.jpg',
|
'thumbnail': 're:^https?://.*\.jpg',
|
||||||
'uploader': 'Donte The Dumbass',
|
'uploader': 'JG',
|
||||||
'uploader_id': 'jaydingeer',
|
'uploader_id': 'jaydingeer',
|
||||||
},
|
},
|
||||||
'params': {
|
'params': {
|
||||||
|
@ -278,6 +286,18 @@ class TwitterIE(InfoExtractor):
|
||||||
'params': {
|
'params': {
|
||||||
'skip_download': True, # requires ffmpeg
|
'skip_download': True, # requires ffmpeg
|
||||||
},
|
},
|
||||||
|
}, {
|
||||||
|
'url': 'https://twitter.com/OPP_HSD/status/779210622571536384',
|
||||||
|
'info_dict': {
|
||||||
|
'id': '1zqKVVlkqLaKB',
|
||||||
|
'ext': 'mp4',
|
||||||
|
'title': 'Sgt Kerry Schmidt - Ontario Provincial Police - Road rage, mischief, assault, rollover and fire in one occurrence',
|
||||||
|
'upload_date': '20160923',
|
||||||
|
'uploader_id': 'OPP_HSD',
|
||||||
|
'uploader': 'Sgt Kerry Schmidt - Ontario Provincial Police',
|
||||||
|
'timestamp': 1474613214,
|
||||||
|
},
|
||||||
|
'add_ie': ['Periscope'],
|
||||||
}]
|
}]
|
||||||
|
|
||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
|
@ -328,13 +348,22 @@ def _real_extract(self, url):
|
||||||
})
|
})
|
||||||
return info
|
return info
|
||||||
|
|
||||||
|
twitter_card_url = None
|
||||||
if 'class="PlayableMedia' in webpage:
|
if 'class="PlayableMedia' in webpage:
|
||||||
|
twitter_card_url = '%s//twitter.com/i/videos/tweet/%s' % (self.http_scheme(), twid)
|
||||||
|
else:
|
||||||
|
twitter_card_iframe_url = self._search_regex(
|
||||||
|
r'data-full-card-iframe-url=([\'"])(?P<url>(?:(?!\1).)+)\1',
|
||||||
|
webpage, 'Twitter card iframe URL', default=None, group='url')
|
||||||
|
if twitter_card_iframe_url:
|
||||||
|
twitter_card_url = compat_urlparse.urljoin(url, twitter_card_iframe_url)
|
||||||
|
|
||||||
|
if twitter_card_url:
|
||||||
info.update({
|
info.update({
|
||||||
'_type': 'url_transparent',
|
'_type': 'url_transparent',
|
||||||
'ie_key': 'TwitterCard',
|
'ie_key': 'TwitterCard',
|
||||||
'url': '%s//twitter.com/i/videos/tweet/%s' % (self.http_scheme(), twid),
|
'url': twitter_card_url,
|
||||||
})
|
})
|
||||||
|
|
||||||
return info
|
return info
|
||||||
|
|
||||||
raise ExtractorError('There\'s no video in this tweet.')
|
raise ExtractorError('There\'s no video in this tweet.')
|
||||||
|
|
Loading…
Reference in a new issue