]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/ccc.py
New upstream version 2019.01.16
[youtubedl] / youtube_dl / extractor / ccc.py
1 from __future__ import unicode_literals
2
3 from .common import InfoExtractor
4 from ..utils import (
5 int_or_none,
6 parse_iso8601,
7 )
8
9
10 class CCCIE(InfoExtractor):
11 IE_NAME = 'media.ccc.de'
12 _VALID_URL = r'https?://(?:www\.)?media\.ccc\.de/v/(?P<id>[^/?#&]+)'
13
14 _TESTS = [{
15 'url': 'https://media.ccc.de/v/30C3_-_5443_-_en_-_saal_g_-_201312281830_-_introduction_to_processor_design_-_byterazor#video',
16 'md5': '3a1eda8f3a29515d27f5adb967d7e740',
17 'info_dict': {
18 'id': '1839',
19 'ext': 'mp4',
20 'title': 'Introduction to Processor Design',
21 'description': 'md5:df55f6d073d4ceae55aae6f2fd98a0ac',
22 'thumbnail': r're:^https?://.*\.jpg$',
23 'upload_date': '20131228',
24 'timestamp': 1388188800,
25 'duration': 3710,
26 }
27 }, {
28 'url': 'https://media.ccc.de/v/32c3-7368-shopshifting#download',
29 'only_matching': True,
30 }]
31
32 def _real_extract(self, url):
33 display_id = self._match_id(url)
34 webpage = self._download_webpage(url, display_id)
35 event_id = self._search_regex(r"data-id='(\d+)'", webpage, 'event id')
36 event_data = self._download_json('https://media.ccc.de/public/events/%s' % event_id, event_id)
37
38 formats = []
39 for recording in event_data.get('recordings', []):
40 recording_url = recording.get('recording_url')
41 if not recording_url:
42 continue
43 language = recording.get('language')
44 folder = recording.get('folder')
45 format_id = None
46 if language:
47 format_id = language
48 if folder:
49 if language:
50 format_id += '-' + folder
51 else:
52 format_id = folder
53 vcodec = 'h264' if 'h264' in folder else (
54 'none' if folder in ('mp3', 'opus') else None
55 )
56 formats.append({
57 'format_id': format_id,
58 'url': recording_url,
59 'width': int_or_none(recording.get('width')),
60 'height': int_or_none(recording.get('height')),
61 'filesize': int_or_none(recording.get('size'), invscale=1024 * 1024),
62 'language': language,
63 'vcodec': vcodec,
64 })
65 self._sort_formats(formats)
66
67 return {
68 'id': event_id,
69 'display_id': display_id,
70 'title': event_data['title'],
71 'description': event_data.get('description'),
72 'thumbnail': event_data.get('thumb_url'),
73 'timestamp': parse_iso8601(event_data.get('date')),
74 'duration': int_or_none(event_data.get('length')),
75 'tags': event_data.get('tags'),
76 'formats': formats,
77 }