mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-11-30 15:00:40 -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
70 lines
2.2 KiB
Python
70 lines
2.2 KiB
Python
import re
|
|
|
|
from .common import InfoExtractor
|
|
from ..utils import parse_duration
|
|
|
|
|
|
class Canalc2IE(InfoExtractor):
|
|
IE_NAME = 'canalc2.tv'
|
|
_VALID_URL = r'https?://(?:(?:www\.)?canalc2\.tv/video/|archives-canalc2\.u-strasbg\.fr/video\.asp\?.*\bidVideo=)(?P<id>\d+)'
|
|
|
|
_TESTS = [{
|
|
'url': 'http://www.canalc2.tv/video/12163',
|
|
'md5': '060158428b650f896c542dfbb3d6487f',
|
|
'info_dict': {
|
|
'id': '12163',
|
|
'ext': 'mp4',
|
|
'title': 'Terrasses du Numérique',
|
|
'duration': 122,
|
|
},
|
|
}, {
|
|
'url': 'http://archives-canalc2.u-strasbg.fr/video.asp?idVideo=11427&voir=oui',
|
|
'only_matching': True,
|
|
}]
|
|
|
|
def _real_extract(self, url):
|
|
video_id = self._match_id(url)
|
|
|
|
webpage = self._download_webpage(
|
|
'http://www.canalc2.tv/video/%s' % video_id, video_id)
|
|
|
|
title = self._html_search_regex(
|
|
r'(?s)class="[^"]*col_description[^"]*">.*?<h3>(.+?)</h3>',
|
|
webpage, 'title')
|
|
|
|
formats = []
|
|
for _, video_url in re.findall(r'file\s*=\s*(["\'])(.+?)\1', webpage):
|
|
if video_url.startswith('rtmp://'):
|
|
rtmp = re.search(
|
|
r'^(?P<url>rtmp://[^/]+/(?P<app>.+/))(?P<play_path>mp4:.+)$', video_url)
|
|
formats.append({
|
|
'url': rtmp.group('url'),
|
|
'format_id': 'rtmp',
|
|
'ext': 'flv',
|
|
'app': rtmp.group('app'),
|
|
'play_path': rtmp.group('play_path'),
|
|
'page_url': url,
|
|
})
|
|
else:
|
|
formats.append({
|
|
'url': video_url,
|
|
'format_id': 'http',
|
|
})
|
|
|
|
if formats:
|
|
info = {
|
|
'formats': formats,
|
|
}
|
|
else:
|
|
info = self._parse_html5_media_entries(url, webpage, url)[0]
|
|
|
|
self._sort_formats(info['formats'])
|
|
|
|
info.update({
|
|
'id': video_id,
|
|
'title': title,
|
|
'duration': parse_duration(self._search_regex(
|
|
r'id=["\']video_duree["\'][^>]*>([^<]+)',
|
|
webpage, 'duration', fatal=False)),
|
|
})
|
|
return info
|