mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-11-05 01:37:24 -05:00
86e5f3ed2e
Using https://github.com/asottile/pyupgrade 1. `__future__` imports and `coding: utf-8` were removed 2. Files were rewritten with `pyupgrade --py36-plus --keep-percent-format` 3. f-strings were cherry-picked from `pyupgrade --py36-plus` Extractors are left untouched (except removing header) to avoid unnecessary merge conflicts
69 lines
2.2 KiB
Python
69 lines
2.2 KiB
Python
import re
|
|
|
|
from .common import InfoExtractor
|
|
from ..compat import (
|
|
compat_urllib_parse_urlparse,
|
|
)
|
|
from ..utils import (
|
|
ExtractorError,
|
|
parse_duration,
|
|
remove_end,
|
|
)
|
|
|
|
|
|
class VuClipIE(InfoExtractor):
|
|
_VALID_URL = r'https?://(?:m\.)?vuclip\.com/w\?.*?cid=(?P<id>[0-9]+)'
|
|
|
|
_TEST = {
|
|
'url': 'http://m.vuclip.com/w?cid=1129900602&bu=8589892792&frm=w&z=34801&op=0&oc=843169247§ion=recommend',
|
|
'info_dict': {
|
|
'id': '1129900602',
|
|
'ext': '3gp',
|
|
'title': 'Top 10 TV Convicts',
|
|
'duration': 733,
|
|
}
|
|
}
|
|
|
|
def _real_extract(self, url):
|
|
video_id = self._match_id(url)
|
|
webpage = self._download_webpage(url, video_id)
|
|
|
|
ad_m = re.search(
|
|
r'''value="No.*?" onClick="location.href='([^"']+)'"''', webpage)
|
|
if ad_m:
|
|
urlr = compat_urllib_parse_urlparse(url)
|
|
adfree_url = urlr.scheme + '://' + urlr.netloc + ad_m.group(1)
|
|
webpage = self._download_webpage(
|
|
adfree_url, video_id, note='Download post-ad page')
|
|
|
|
error_msg = self._html_search_regex(
|
|
r'<p class="message">(.*?)</p>', webpage, 'error message',
|
|
default=None)
|
|
if error_msg:
|
|
raise ExtractorError(
|
|
'%s said: %s' % (self.IE_NAME, error_msg), expected=True)
|
|
|
|
# These clowns alternate between two page types
|
|
video_url = self._search_regex(
|
|
r'<a[^>]+href="([^"]+)"[^>]*><img[^>]+src="[^"]*/play\.gif',
|
|
webpage, 'video URL', default=None)
|
|
if video_url:
|
|
formats = [{
|
|
'url': video_url,
|
|
}]
|
|
else:
|
|
formats = self._parse_html5_media_entries(url, webpage, video_id)[0]['formats']
|
|
|
|
title = remove_end(self._html_search_regex(
|
|
r'<title>(.*?)-\s*Vuclip</title>', webpage, 'title').strip(), ' - Video')
|
|
|
|
duration = parse_duration(self._html_search_regex(
|
|
r'[(>]([0-9]+:[0-9]+)(?:<span|\))', webpage, 'duration', fatal=False))
|
|
|
|
return {
|
|
'id': video_id,
|
|
'formats': formats,
|
|
'title': title,
|
|
'duration': duration,
|
|
}
|