mirror of https://github.com/yt-dlp/yt-dlp.git
[extractor/generic] Extract wistia embed code into separate method
This commit is contained in:
parent
7ad4362357
commit
58bb440283
|
@ -88,6 +88,7 @@ from .rutube import RutubeIE
|
||||||
from .limelight import LimelightBaseIE
|
from .limelight import LimelightBaseIE
|
||||||
from .anvato import AnvatoIE
|
from .anvato import AnvatoIE
|
||||||
from .washingtonpost import WashingtonPostIE
|
from .washingtonpost import WashingtonPostIE
|
||||||
|
from .wistia import WistiaIE
|
||||||
|
|
||||||
|
|
||||||
class GenericIE(InfoExtractor):
|
class GenericIE(InfoExtractor):
|
||||||
|
@ -2111,36 +2112,15 @@ class GenericIE(InfoExtractor):
|
||||||
playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
|
playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
|
||||||
|
|
||||||
# Look for embedded Wistia player
|
# Look for embedded Wistia player
|
||||||
match = re.search(
|
wistia_url = WistiaIE._extract_url(webpage)
|
||||||
r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
|
if wistia_url:
|
||||||
if match:
|
|
||||||
embed_url = self._proto_relative_url(
|
|
||||||
unescapeHTML(match.group('url')))
|
|
||||||
return {
|
return {
|
||||||
'_type': 'url_transparent',
|
'_type': 'url_transparent',
|
||||||
'url': embed_url,
|
'url': self._proto_relative_url(wistia_url),
|
||||||
'ie_key': 'Wistia',
|
'ie_key': WistiaIE.ie_key(),
|
||||||
'uploader': video_uploader,
|
'uploader': video_uploader,
|
||||||
}
|
}
|
||||||
|
|
||||||
match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
|
|
||||||
if match:
|
|
||||||
return {
|
|
||||||
'_type': 'url_transparent',
|
|
||||||
'url': 'wistia:%s' % match.group('id'),
|
|
||||||
'ie_key': 'Wistia',
|
|
||||||
'uploader': video_uploader,
|
|
||||||
}
|
|
||||||
|
|
||||||
match = re.search(
|
|
||||||
r'''(?sx)
|
|
||||||
<script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
|
|
||||||
<div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
|
|
||||||
''', webpage)
|
|
||||||
if match:
|
|
||||||
return self.url_result(self._proto_relative_url(
|
|
||||||
'wistia:%s' % match.group('id')), 'Wistia')
|
|
||||||
|
|
||||||
# Look for SVT player
|
# Look for SVT player
|
||||||
svt_url = SVTIE._extract_url(webpage)
|
svt_url = SVTIE._extract_url(webpage)
|
||||||
if svt_url:
|
if svt_url:
|
||||||
|
|
|
@ -1,10 +1,13 @@
|
||||||
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 (
|
||||||
ExtractorError,
|
ExtractorError,
|
||||||
int_or_none,
|
int_or_none,
|
||||||
float_or_none,
|
float_or_none,
|
||||||
|
unescapeHTML,
|
||||||
)
|
)
|
||||||
|
|
||||||
|
|
||||||
|
@ -34,6 +37,25 @@ class WistiaIE(InfoExtractor):
|
||||||
'only_matching': True,
|
'only_matching': True,
|
||||||
}]
|
}]
|
||||||
|
|
||||||
|
@staticmethod
|
||||||
|
def _extract_url(webpage):
|
||||||
|
match = re.search(
|
||||||
|
r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
|
||||||
|
if match:
|
||||||
|
return unescapeHTML(match.group('url'))
|
||||||
|
|
||||||
|
match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
|
||||||
|
if match:
|
||||||
|
return 'wistia:%s' % match.group('id')
|
||||||
|
|
||||||
|
match = re.search(
|
||||||
|
r'''(?sx)
|
||||||
|
<script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
|
||||||
|
<div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
|
||||||
|
''', webpage)
|
||||||
|
if match:
|
||||||
|
return 'wistia:%s' % match.group('id')
|
||||||
|
|
||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
video_id = self._match_id(url)
|
video_id = self._match_id(url)
|
||||||
|
|
||||||
|
|
Loading…
Reference in New Issue