mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-11-17 21:59:17 +00:00
137 lines
5.2 KiB
Python
Executable file
137 lines
5.2 KiB
Python
Executable file
# coding: utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
import codecs
|
|
import re
|
|
|
|
from .common import InfoExtractor
|
|
from ..utils import (
|
|
ExtractorError,
|
|
float_or_none,
|
|
int_or_none,
|
|
parse_duration,
|
|
)
|
|
|
|
|
|
class CDAIE(InfoExtractor):
|
|
_VALID_URL = r'https?://(?:(?:www\.)?cda\.pl/video|ebd\.cda\.pl/[0-9]+x[0-9]+)/(?P<id>[0-9a-z]+)'
|
|
_BASE_URL = 'http://www.cda.pl/'
|
|
_TESTS = [{
|
|
'url': 'http://www.cda.pl/video/5749950c',
|
|
'md5': '6f844bf51b15f31fae165365707ae970',
|
|
'info_dict': {
|
|
'id': '5749950c',
|
|
'ext': 'mp4',
|
|
'height': 720,
|
|
'title': 'Oto dlaczego przed zakrętem należy zwolnić.',
|
|
'description': 'md5:269ccd135d550da90d1662651fcb9772',
|
|
'thumbnail': r're:^https?://.*\.jpg$',
|
|
'average_rating': float,
|
|
'duration': 39
|
|
}
|
|
}, {
|
|
'url': 'http://www.cda.pl/video/57413289',
|
|
'md5': 'a88828770a8310fc00be6c95faf7f4d5',
|
|
'info_dict': {
|
|
'id': '57413289',
|
|
'ext': 'mp4',
|
|
'title': 'Lądowanie na lotnisku na Maderze',
|
|
'description': 'md5:60d76b71186dcce4e0ba6d4bbdb13e1a',
|
|
'thumbnail': r're:^https?://.*\.jpg$',
|
|
'uploader': 'crash404',
|
|
'view_count': int,
|
|
'average_rating': float,
|
|
'duration': 137
|
|
}
|
|
}, {
|
|
'url': 'http://ebd.cda.pl/0x0/5749950c',
|
|
'only_matching': True,
|
|
}]
|
|
|
|
def _real_extract(self, url):
|
|
video_id = self._match_id(url)
|
|
self._set_cookie('cda.pl', 'cda.player', 'html5')
|
|
webpage = self._download_webpage(
|
|
self._BASE_URL + '/video/' + video_id, video_id)
|
|
|
|
if 'Ten film jest dostępny dla użytkowników premium' in webpage:
|
|
raise ExtractorError('This video is only available for premium users.', expected=True)
|
|
|
|
formats = []
|
|
|
|
uploader = self._search_regex(r'''(?x)
|
|
<(span|meta)[^>]+itemprop=(["\'])author\2[^>]*>
|
|
(?:<\1[^>]*>[^<]*</\1>|(?!</\1>)(?:.|\n))*?
|
|
<(span|meta)[^>]+itemprop=(["\'])name\4[^>]*>(?P<uploader>[^<]+)</\3>
|
|
''', webpage, 'uploader', default=None, group='uploader')
|
|
view_count = self._search_regex(
|
|
r'Odsłony:(?:\s| )*([0-9]+)', webpage,
|
|
'view_count', default=None)
|
|
average_rating = self._search_regex(
|
|
r'<(?:span|meta)[^>]+itemprop=(["\'])ratingValue\1[^>]*>(?P<rating_value>[0-9.]+)',
|
|
webpage, 'rating', fatal=False, group='rating_value')
|
|
|
|
info_dict = {
|
|
'id': video_id,
|
|
'title': self._og_search_title(webpage),
|
|
'description': self._og_search_description(webpage),
|
|
'uploader': uploader,
|
|
'view_count': int_or_none(view_count),
|
|
'average_rating': float_or_none(average_rating),
|
|
'thumbnail': self._og_search_thumbnail(webpage),
|
|
'formats': formats,
|
|
'duration': None,
|
|
}
|
|
|
|
def extract_format(page, version):
|
|
json_str = self._search_regex(
|
|
r'player_data=(\\?["\'])(?P<player_data>.+?)\1', page,
|
|
'%s player_json' % version, fatal=False, group='player_data')
|
|
if not json_str:
|
|
return
|
|
player_data = self._parse_json(
|
|
json_str, '%s player_data' % version, fatal=False)
|
|
if not player_data:
|
|
return
|
|
video = player_data.get('video')
|
|
if not video or 'file' not in video:
|
|
self.report_warning('Unable to extract %s version information' % version)
|
|
return
|
|
if video['file'].startswith('uggc'):
|
|
video['file'] = codecs.decode(video['file'], 'rot_13')
|
|
if video['file'].endswith('adc.mp4'):
|
|
video['file'] = video['file'].replace('adc.mp4', '.mp4')
|
|
f = {
|
|
'url': video['file'],
|
|
}
|
|
m = re.search(
|
|
r'<a[^>]+data-quality="(?P<format_id>[^"]+)"[^>]+href="[^"]+"[^>]+class="[^"]*quality-btn-active[^"]*">(?P<height>[0-9]+)p',
|
|
page)
|
|
if m:
|
|
f.update({
|
|
'format_id': m.group('format_id'),
|
|
'height': int(m.group('height')),
|
|
})
|
|
info_dict['formats'].append(f)
|
|
if not info_dict['duration']:
|
|
info_dict['duration'] = parse_duration(video.get('duration'))
|
|
|
|
extract_format(webpage, 'default')
|
|
|
|
for href, resolution in re.findall(
|
|
r'<a[^>]+data-quality="[^"]+"[^>]+href="([^"]+)"[^>]+class="quality-btn"[^>]*>([0-9]+p)',
|
|
webpage):
|
|
webpage = self._download_webpage(
|
|
self._BASE_URL + href, video_id,
|
|
'Downloading %s version information' % resolution, fatal=False)
|
|
if not webpage:
|
|
# Manually report warning because empty page is returned when
|
|
# invalid version is requested.
|
|
self.report_warning('Unable to download %s version information' % resolution)
|
|
continue
|
|
extract_format(webpage, resolution)
|
|
|
|
self._sort_formats(formats)
|
|
|
|
return info_dict
|