mirror of
https://github.com/ytdl-org/youtube-dl
synced 2024-08-27 20:38:50 +09:00
![Sergey M?](/assets/img/avatar_default.png)
compat_urllib_request.Request [downloader/dash] Use sanitized_Request [downloader/http] Use sanitized_Request [atresplayer] Use sanitized_Request [bambuser] Use sanitized_Request [bliptv] Use sanitized_Request [brightcove] Use sanitized_Request [cbs] Use sanitized_Request [ceskatelevize] Use sanitized_Request [collegerama] Use sanitized_Request [extractor/common] Use sanitized_Request [crunchyroll] Use sanitized_Request [dailymotion] Use sanitized_Request [dcn] Use sanitized_Request [dramafever] Use sanitized_Request [dumpert] Use sanitized_Request [eitb] Use sanitized_Request [escapist] Use sanitized_Request [everyonesmixtape] Use sanitized_Request [extremetube] Use sanitized_Request [facebook] Use sanitized_Request [fc2] Use sanitized_Request [flickr] Use sanitized_Request [4tube] Use sanitized_Request [gdcvault] Use sanitized_Request [extractor/generic] Use sanitized_Request [hearthisat] Use sanitized_Request [hotnewhiphop] Use sanitized_Request [hypem] Use sanitized_Request [iprima] Use sanitized_Request [ivi] Use sanitized_Request [keezmovies] Use sanitized_Request [letv] Use sanitized_Request [lynda] Use sanitized_Request [metacafe] Use sanitized_Request [minhateca] Use sanitized_Request [miomio] Use sanitized_Request [meovideo] Use sanitized_Request [mofosex] Use sanitized_Request [moniker] Use sanitized_Request [mooshare] Use sanitized_Request [movieclips] Use sanitized_Request [mtv] Use sanitized_Request [myvideo] Use sanitized_Request [neteasemusic] Use sanitized_Request [nfb] Use sanitized_Request [niconico] Use sanitized_Request [noco] Use sanitized_Request [nosvideo] Use sanitized_Request [novamov] Use sanitized_Request [nowness] Use sanitized_Request [nuvid] Use sanitized_Request [played] Use sanitized_Request [pluralsight] Use sanitized_Request [pornhub] Use sanitized_Request [pornotube] Use sanitized_Request [primesharetv] Use sanitized_Request [promptfile] Use sanitized_Request [qqmusic] Use sanitized_Request [rtve] Use sanitized_Request [safari] Use sanitized_Request [sandia] Use sanitized_Request [shared] Use sanitized_Request [sharesix] Use sanitized_Request [sina] Use sanitized_Request [smotri] Use sanitized_Request [sohu] Use sanitized_Request [spankwire] Use sanitized_Request [sportdeutschland] Use sanitized_Request [streamcloud] Use sanitized_Request [streamcz] Use sanitized_Request [tapely] Use sanitized_Request [tube8] Use sanitized_Request [tubitv] Use sanitized_Request [twitch] Use sanitized_Request [twitter] Use sanitized_Request [udemy] Use sanitized_Request [vbox7] Use sanitized_Request [veoh] Use sanitized_Request [vessel] Use sanitized_Request [vevo] Use sanitized_Request [viddler] Use sanitized_Request [videomega] Use sanitized_Request [viewvster] Use sanitized_Request [viki] Use sanitized_Request [vk] Use sanitized_Request [vodlocker] Use sanitized_Request [voicerepublic] Use sanitized_Request [wistia] Use sanitized_Request [xfileshare] Use sanitized_Request [xtube] Use sanitized_Request [xvideos] Use sanitized_Request [yandexmusic] Use sanitized_Request [youku] Use sanitized_Request [youporn] Use sanitized_Request [youtube] Use sanitized_Request [patreon] Use sanitized_Request [extractor/common] Remove unused import [nfb] PEP 8
193 lines
6.8 KiB
Python
193 lines
6.8 KiB
Python
# -*- coding: utf-8 -*-
|
|
from __future__ import unicode_literals
|
|
|
|
import re
|
|
|
|
from .common import InfoExtractor
|
|
from ..compat import (
|
|
compat_urllib_parse,
|
|
compat_urllib_parse_unquote,
|
|
compat_urllib_parse_urlparse,
|
|
)
|
|
from ..utils import (
|
|
ExtractorError,
|
|
float_or_none,
|
|
sanitized_Request,
|
|
)
|
|
|
|
|
|
class CeskaTelevizeIE(InfoExtractor):
|
|
_VALID_URL = r'https?://www\.ceskatelevize\.cz/(porady|ivysilani)/(?:[^/]+/)*(?P<id>[^/#?]+)/*(?:[#?].*)?$'
|
|
_TESTS = [{
|
|
'url': 'http://www.ceskatelevize.cz/ivysilani/ivysilani/10441294653-hyde-park-civilizace/214411058091220',
|
|
'info_dict': {
|
|
'id': '61924494876951776',
|
|
'ext': 'mp4',
|
|
'title': 'Hyde Park Civilizace',
|
|
'description': 'md5:fe93f6eda372d150759d11644ebbfb4a',
|
|
'thumbnail': 're:^https?://.*\.jpg',
|
|
'duration': 3350,
|
|
},
|
|
'params': {
|
|
# m3u8 download
|
|
'skip_download': True,
|
|
},
|
|
}, {
|
|
'url': 'http://www.ceskatelevize.cz/ivysilani/10532695142-prvni-republika/bonus/14716-zpevacka-z-duparny-bobina',
|
|
'info_dict': {
|
|
'id': '61924494876844374',
|
|
'ext': 'mp4',
|
|
'title': 'První republika: Zpěvačka z Dupárny Bobina',
|
|
'description': 'Sága mapující atmosféru první republiky od r. 1918 do r. 1945.',
|
|
'thumbnail': 're:^https?://.*\.jpg',
|
|
'duration': 88.4,
|
|
},
|
|
'params': {
|
|
# m3u8 download
|
|
'skip_download': True,
|
|
},
|
|
}, {
|
|
# video with 18+ caution trailer
|
|
'url': 'http://www.ceskatelevize.cz/porady/10520528904-queer/215562210900007-bogotart/',
|
|
'info_dict': {
|
|
'id': '215562210900007-bogotart',
|
|
'title': 'Queer: Bogotart',
|
|
'description': 'Alternativní průvodce současným queer světem',
|
|
},
|
|
'playlist': [{
|
|
'info_dict': {
|
|
'id': '61924494876844842',
|
|
'ext': 'mp4',
|
|
'title': 'Queer: Bogotart (Varování 18+)',
|
|
'duration': 10.2,
|
|
},
|
|
}, {
|
|
'info_dict': {
|
|
'id': '61924494877068022',
|
|
'ext': 'mp4',
|
|
'title': 'Queer: Bogotart (Queer)',
|
|
'thumbnail': 're:^https?://.*\.jpg',
|
|
'duration': 1558.3,
|
|
},
|
|
}],
|
|
'params': {
|
|
# m3u8 download
|
|
'skip_download': True,
|
|
},
|
|
}]
|
|
|
|
def _real_extract(self, url):
|
|
url = url.replace('/porady/', '/ivysilani/').replace('/video/', '')
|
|
|
|
mobj = re.match(self._VALID_URL, url)
|
|
playlist_id = mobj.group('id')
|
|
|
|
webpage = self._download_webpage(url, playlist_id)
|
|
|
|
NOT_AVAILABLE_STRING = 'This content is not available at your territory due to limited copyright.'
|
|
if '%s</p>' % NOT_AVAILABLE_STRING in webpage:
|
|
raise ExtractorError(NOT_AVAILABLE_STRING, expected=True)
|
|
|
|
typ = self._html_search_regex(
|
|
r'getPlaylistUrl\(\[\{"type":"(.+?)","id":".+?"\}\],', webpage, 'type')
|
|
episode_id = self._html_search_regex(
|
|
r'getPlaylistUrl\(\[\{"type":".+?","id":"(.+?)"\}\],', webpage, 'episode_id')
|
|
|
|
data = {
|
|
'playlist[0][type]': typ,
|
|
'playlist[0][id]': episode_id,
|
|
'requestUrl': compat_urllib_parse_urlparse(url).path,
|
|
'requestSource': 'iVysilani',
|
|
}
|
|
|
|
req = sanitized_Request(
|
|
'http://www.ceskatelevize.cz/ivysilani/ajax/get-client-playlist',
|
|
data=compat_urllib_parse.urlencode(data))
|
|
|
|
req.add_header('Content-type', 'application/x-www-form-urlencoded')
|
|
req.add_header('x-addr', '127.0.0.1')
|
|
req.add_header('X-Requested-With', 'XMLHttpRequest')
|
|
req.add_header('Referer', url)
|
|
|
|
playlistpage = self._download_json(req, playlist_id)
|
|
|
|
playlist_url = playlistpage['url']
|
|
if playlist_url == 'error_region':
|
|
raise ExtractorError(NOT_AVAILABLE_STRING, expected=True)
|
|
|
|
req = sanitized_Request(compat_urllib_parse_unquote(playlist_url))
|
|
req.add_header('Referer', url)
|
|
|
|
playlist_title = self._og_search_title(webpage)
|
|
playlist_description = self._og_search_description(webpage)
|
|
|
|
playlist = self._download_json(req, playlist_id)['playlist']
|
|
playlist_len = len(playlist)
|
|
|
|
entries = []
|
|
for item in playlist:
|
|
formats = []
|
|
for format_id, stream_url in item['streamUrls'].items():
|
|
formats.extend(self._extract_m3u8_formats(
|
|
stream_url, playlist_id, 'mp4', entry_protocol='m3u8_native'))
|
|
self._sort_formats(formats)
|
|
|
|
item_id = item.get('id') or item['assetId']
|
|
title = item['title']
|
|
|
|
duration = float_or_none(item.get('duration'))
|
|
thumbnail = item.get('previewImageUrl')
|
|
|
|
subtitles = {}
|
|
if item.get('type') == 'VOD':
|
|
subs = item.get('subtitles')
|
|
if subs:
|
|
subtitles = self.extract_subtitles(episode_id, subs)
|
|
|
|
entries.append({
|
|
'id': item_id,
|
|
'title': playlist_title if playlist_len == 1 else '%s (%s)' % (playlist_title, title),
|
|
'description': playlist_description if playlist_len == 1 else None,
|
|
'thumbnail': thumbnail,
|
|
'duration': duration,
|
|
'formats': formats,
|
|
'subtitles': subtitles,
|
|
})
|
|
|
|
return self.playlist_result(entries, playlist_id, playlist_title, playlist_description)
|
|
|
|
def _get_subtitles(self, episode_id, subs):
|
|
original_subtitles = self._download_webpage(
|
|
subs[0]['url'], episode_id, 'Downloading subtitles')
|
|
srt_subs = self._fix_subtitles(original_subtitles)
|
|
return {
|
|
'cs': [{
|
|
'ext': 'srt',
|
|
'data': srt_subs,
|
|
}]
|
|
}
|
|
|
|
@staticmethod
|
|
def _fix_subtitles(subtitles):
|
|
""" Convert millisecond-based subtitles to SRT """
|
|
|
|
def _msectotimecode(msec):
|
|
""" Helper utility to convert milliseconds to timecode """
|
|
components = []
|
|
for divider in [1000, 60, 60, 100]:
|
|
components.append(msec % divider)
|
|
msec //= divider
|
|
return "{3:02}:{2:02}:{1:02},{0:03}".format(*components)
|
|
|
|
def _fix_subtitle(subtitle):
|
|
for line in subtitle.splitlines():
|
|
m = re.match(r"^\s*([0-9]+);\s*([0-9]+)\s+([0-9]+)\s*$", line)
|
|
if m:
|
|
yield m.group(1)
|
|
start, stop = (_msectotimecode(int(t)) for t in m.groups()[1:])
|
|
yield "{0} --> {1}".format(start, stop)
|
|
else:
|
|
yield line
|
|
|
|
return "\r\n".join(_fix_subtitle(subtitles))
|