X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/0865c28fb29a6481cd837cf8c1ef0cd134c6ef8e..a57dac80d518b579d7a7da90aa74ce401f138d0f:/youtube_dl/extractor/ccc.py diff --git a/youtube_dl/extractor/ccc.py b/youtube_dl/extractor/ccc.py index 2a5d4be..36e6dff 100644 --- a/youtube_dl/extractor/ccc.py +++ b/youtube_dl/extractor/ccc.py @@ -1,99 +1,111 @@ +# coding: utf-8 from __future__ import unicode_literals -import re - from .common import InfoExtractor from ..utils import ( int_or_none, - qualities, - unified_strdate, + parse_iso8601, + try_get, + url_or_none, ) class CCCIE(InfoExtractor): IE_NAME = 'media.ccc.de' - _VALID_URL = r'https?://(?:www\.)?media\.ccc\.de/[^?#]+/[^?#/]*?_(?P[0-9]{8,})._[^?#/]*\.html' + _VALID_URL = r'https?://(?:www\.)?media\.ccc\.de/v/(?P[^/?#&]+)' - _TEST = { - 'url': 'http://media.ccc.de/browse/congress/2013/30C3_-_5443_-_en_-_saal_g_-_201312281830_-_introduction_to_processor_design_-_byterazor.html#video', - 'md5': '205a365d0d57c0b1e43a12c9ffe8f9be', + _TESTS = [{ + 'url': 'https://media.ccc.de/v/30C3_-_5443_-_en_-_saal_g_-_201312281830_-_introduction_to_processor_design_-_byterazor#video', + 'md5': '3a1eda8f3a29515d27f5adb967d7e740', 'info_dict': { - 'id': '20131228183', + 'id': '1839', 'ext': 'mp4', 'title': 'Introduction to Processor Design', - 'description': 'md5:5ddbf8c734800267f2cee4eab187bc1b', - 'thumbnail': 're:^https?://.*\.jpg$', - 'view_count': int, - 'upload_date': '20131229', + 'creator': 'byterazor', + 'description': 'md5:df55f6d073d4ceae55aae6f2fd98a0ac', + 'thumbnail': r're:^https?://.*\.jpg$', + 'upload_date': '20131228', + 'timestamp': 1388188800, + 'duration': 3710, + 'tags': list, } - } + }, { + 'url': 'https://media.ccc.de/v/32c3-7368-shopshifting#download', + 'only_matching': True, + }] def _real_extract(self, url): - video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - - if self._downloader.params.get('prefer_free_formats'): - preference = qualities(['mp3', 'opus', 'mp4-lq', 'webm-lq', 'h264-sd', 'mp4-sd', 'webm-sd', 'mp4', 'webm', 'mp4-hd', 'h264-hd', 'webm-hd']) - else: - preference = qualities(['opus', 'mp3', 'webm-lq', 'mp4-lq', 'webm-sd', 'h264-sd', 'mp4-sd', 'webm', 'mp4', 'webm-hd', 'mp4-hd', 'h264-hd']) + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + event_id = self._search_regex(r"data-id='(\d+)'", webpage, 'event id') + event_data = self._download_json('https://media.ccc.de/public/events/%s' % event_id, event_id) - title = self._html_search_regex( - r'(?s)

(.*?)

', webpage, 'title') - description = self._html_search_regex( - r"(?s)

(.*?)

", - webpage, 'description', fatal=False) - upload_date = unified_strdate(self._html_search_regex( - r"(?s)(.*?)", - webpage, 'upload date', fatal=False)) - view_count = int_or_none(self._html_search_regex( - r"(?s)(.*?)", - webpage, 'view count', fatal=False)) - - matches = re.finditer(r'''(?xs) - <(?:span|div)\s+class='label\s+filetype'>(?P.*?)\s* - [^']+)'>\s* - (?: - .*? - [^']+\.torrent)' - )?''', webpage) formats = [] - for m in matches: - format = m.group('format') - format_id = self._search_regex( - r'.*/([a-z0-9_-]+)/[^/]*$', - m.group('http_url'), 'format id', default=None) - vcodec = 'h264' if 'h264' in format_id else ( - 'none' if format_id in ('mp3', 'opus') else None + for recording in event_data.get('recordings', []): + recording_url = recording.get('recording_url') + if not recording_url: + continue + language = recording.get('language') + folder = recording.get('folder') + format_id = None + if language: + format_id = language + if folder: + if language: + format_id += '-' + folder + else: + format_id = folder + vcodec = 'h264' if 'h264' in folder else ( + 'none' if folder in ('mp3', 'opus') else None ) formats.append({ 'format_id': format_id, - 'format': format, - 'url': m.group('http_url'), + 'url': recording_url, + 'width': int_or_none(recording.get('width')), + 'height': int_or_none(recording.get('height')), + 'filesize': int_or_none(recording.get('size'), invscale=1024 * 1024), + 'language': language, 'vcodec': vcodec, - 'preference': preference(format_id), }) - - if m.group('torrent_url'): - formats.append({ - 'format_id': 'torrent-%s' % (format if format_id is None else format_id), - 'format': '%s (torrent)' % format, - 'proto': 'torrent', - 'format_note': '(unsupported; will just download the .torrent file)', - 'vcodec': vcodec, - 'preference': -100 + preference(format_id), - 'url': m.group('torrent_url'), - }) self._sort_formats(formats) - thumbnail = self._html_search_regex( - r"[^/?#&]+)' + _TESTS = [{ + 'url': 'https://media.ccc.de/c/30c3', + 'info_dict': { + 'title': '30C3', + 'id': '30c3', + }, + 'playlist_count': 135, + }] + + def _real_extract(self, url): + playlist_id = self._match_id(url).lower() + + conf = self._download_json( + 'https://media.ccc.de/public/conferences/' + playlist_id, + playlist_id) + + entries = [] + for e in conf['events']: + event_url = url_or_none(e.get('frontend_link')) + if event_url: + entries.append(self.url_result(event_url, ie=CCCIE.ie_key())) + + return self.playlist_result(entries, playlist_id, conf.get('title'))