+import base64
import re
+import urllib.parse
from .common import InfoExtractor
-from ..compat import compat_urlparse
from ..utils import (
+ ExtractorError,
clean_html,
extract_attributes,
- ExtractorError,
get_elements_by_class,
int_or_none,
js_to_json,
if attribute is None:
attribute = ''
else:
- attribute = r'\s+(?P<attribute>%s)' % re.escape(attribute)
+ attribute = rf'\s+(?P<attribute>{re.escape(attribute)})'
if value is None:
value = ''
else:
value = re.escape(value) if escape_value else value
- value = '=[\'"]?(?P<value>%s)[\'"]?' % value
+ value = f'=[\'"]?(?P<value>{value})[\'"]?'
retlist = []
- for m in re.finditer(r'''(?xs)
- <(?P<tag>%s)
+ for m in re.finditer(rf'''(?xs)
+ <(?P<tag>{tag})
(?:\s+[a-zA-Z0-9:._-]+(?:=[a-zA-Z0-9:._-]*|="[^"]*"|='[^']*'|))*?
- %s%s
+ {attribute}{value}
(?:\s+[a-zA-Z0-9:._-]+(?:=[a-zA-Z0-9:._-]*|="[^"]*"|='[^']*'|))*?
\s*>
(?P<content>.*?)
</\1>
- ''' % (tag, attribute, value), html):
+ ''', html):
retlist.append(m)
return retlist
class DubokuIE(InfoExtractor):
IE_NAME = 'duboku'
- IE_DESC = 'www.duboku.co'
+ IE_DESC = 'www.duboku.io'
- _VALID_URL = r'(?:https?://[^/]+\.duboku\.co/vodplay/)(?P<id>[0-9]+-[0-9-]+)\.html.*'
+ _VALID_URL = r'(?:https?://[^/]+\.duboku\.io/vodplay/)(?P<id>[0-9]+-[0-9-]+)\.html.*'
_TESTS = [{
- 'url': 'https://www.duboku.co/vodplay/1575-1-1.html',
+ 'url': 'https://w.duboku.io/vodplay/1575-1-1.html',
'info_dict': {
'id': '1575-1-1',
- 'ext': 'ts',
+ 'ext': 'mp4',
'series': '白色月光',
'title': 'contains:白色月光',
'season_number': 1,
'episode_number': 1,
+ 'season': 'Season 1',
+ 'episode_id': '1',
+ 'season_id': '1',
+ 'episode': 'Episode 1',
},
'params': {
'skip_download': 'm3u8 download',
},
}, {
- 'url': 'https://www.duboku.co/vodplay/1588-1-1.html',
+ 'url': 'https://w.duboku.io/vodplay/1588-1-1.html',
'info_dict': {
'id': '1588-1-1',
- 'ext': 'ts',
+ 'ext': 'mp4',
'series': '亲爱的自己',
- 'title': 'contains:预告片',
+ 'title': 'contains:第1集',
'season_number': 1,
'episode_number': 1,
+ 'episode': 'Episode 1',
+ 'season': 'Season 1',
+ 'episode_id': '1',
+ 'season_id': '1',
},
'params': {
'skip_download': 'm3u8 download',
season_id = temp[1]
episode_id = temp[2]
- webpage_url = 'https://www.duboku.co/vodplay/%s.html' % video_id
+ webpage_url = f'https://w.duboku.io/vodplay/{video_id}.html'
webpage_html = self._download_webpage(webpage_url, video_id)
# extract video url
data_url = player_data.get('url')
if not data_url:
raise ExtractorError('Cannot find url in player_data')
- data_from = player_data.get('from')
+ player_encrypt = player_data.get('encrypt')
+ if player_encrypt == 1:
+ data_url = urllib.parse.unquote(data_url)
+ elif player_encrypt == 2:
+ data_url = urllib.parse.unquote(base64.b64decode(data_url).decode('ascii'))
# if it is an embedded iframe, maybe it's an external source
- if data_from == 'iframe':
+ headers = {'Referer': webpage_url}
+ if player_data.get('from') == 'iframe':
# use _type url_transparent to retain the meaningful details
# of the video.
return {
'_type': 'url_transparent',
- 'url': smuggle_url(data_url, {'http_headers': {'Referer': webpage_url}}),
+ 'url': smuggle_url(data_url, {'referer': webpage_url}),
'id': video_id,
'title': title,
'series': series_title,
'episode_id': episode_id,
}
- formats = self._extract_m3u8_formats(data_url, video_id, 'mp4')
+ formats = self._extract_m3u8_formats(data_url, video_id, 'mp4', headers=headers)
return {
'id': video_id,
'episode_number': int_or_none(episode_id),
'episode_id': episode_id,
'formats': formats,
- 'http_headers': {'Referer': 'https://www.duboku.co/static/player/videojs.html'}
+ 'http_headers': headers,
}
class DubokuPlaylistIE(InfoExtractor):
IE_NAME = 'duboku:list'
- IE_DESC = 'www.duboku.co entire series'
+ IE_DESC = 'www.duboku.io entire series'
- _VALID_URL = r'(?:https?://[^/]+\.duboku\.co/voddetail/)(?P<id>[0-9]+)\.html.*'
+ _VALID_URL = r'(?:https?://[^/]+\.duboku\.io/voddetail/)(?P<id>[0-9]+)\.html.*'
_TESTS = [{
- 'url': 'https://www.duboku.co/voddetail/1575.html',
+ 'url': 'https://w.duboku.io/voddetail/1575.html',
'info_dict': {
'id': 'startswith:1575',
'title': '白色月光',
},
'playlist_count': 12,
}, {
- 'url': 'https://www.duboku.co/voddetail/1554.html',
+ 'url': 'https://w.duboku.io/voddetail/1554.html',
'info_dict': {
'id': 'startswith:1554',
'title': '以家人之名',
},
'playlist_mincount': 30,
- }, {
- 'url': 'https://www.duboku.co/voddetail/1554.html#playlist2',
- 'info_dict': {
- 'id': '1554#playlist2',
- 'title': '以家人之名',
- },
- 'playlist_mincount': 27,
}]
def _real_extract(self, url):
mobj = self._match_valid_url(url)
if mobj is None:
- raise ExtractorError('Invalid URL: %s' % url)
+ raise ExtractorError(f'Invalid URL: {url}')
series_id = mobj.group('id')
- fragment = compat_urlparse.urlparse(url).fragment
+ fragment = urllib.parse.urlparse(url).fragment
- webpage_url = 'https://www.duboku.co/voddetail/%s.html' % series_id
+ webpage_url = f'https://w.duboku.io/voddetail/{series_id}.html'
webpage_html = self._download_webpage(webpage_url, series_id)
# extract title
div.group('content'), 'a', 'href', value='[^\'"]+?', escape_value=False):
playlist.append({
'href': unescapeHTML(a.group('value')),
- 'title': unescapeHTML(a.group('content'))
+ 'title': unescapeHTML(a.group('content')),
})
playlists[playlist_id] = playlist
(playlist_id, playlist) = first
if not playlist:
raise ExtractorError(
- 'Cannot find %s' % fragment if fragment else 'Cannot extract playlist')
+ f'Cannot find {fragment}' if fragment else 'Cannot extract playlist')
# return url results
return self.playlist_result([
self.url_result(
- compat_urlparse.urljoin('https://www.duboku.co', x['href']),
+ urllib.parse.urljoin('https://w.duboku.io', x['href']),
ie=DubokuIE.ie_key(), video_title=x.get('title'))
for x in playlist], series_id + '#' + playlist_id, title)
projects / yt-dlp.git / blobdiff