]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/videopress.py
Fix extraction from youtube.
[youtubedl] / youtube_dl / extractor / videopress.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 import re
5
6 from .common import InfoExtractor
7 from ..compat import compat_str
8 from ..utils import (
9 determine_ext,
10 float_or_none,
11 parse_age_limit,
12 qualities,
13 random_birthday,
14 try_get,
15 unified_timestamp,
16 urljoin,
17 )
18
19
20 class VideoPressIE(InfoExtractor):
21 _VALID_URL = r'https?://videopress\.com/embed/(?P<id>[\da-zA-Z]+)'
22 _TESTS = [{
23 'url': 'https://videopress.com/embed/kUJmAcSf',
24 'md5': '706956a6c875873d51010921310e4bc6',
25 'info_dict': {
26 'id': 'kUJmAcSf',
27 'ext': 'mp4',
28 'title': 'VideoPress Demo',
29 'thumbnail': r're:^https?://.*\.jpg',
30 'duration': 634.6,
31 'timestamp': 1434983935,
32 'upload_date': '20150622',
33 'age_limit': 0,
34 },
35 }, {
36 # 17+, requires birth_* params
37 'url': 'https://videopress.com/embed/iH3gstfZ',
38 'only_matching': True,
39 }]
40
41 @staticmethod
42 def _extract_urls(webpage):
43 return re.findall(
44 r'<iframe[^>]+src=["\']((?:https?://)?videopress\.com/embed/[\da-zA-Z]+)',
45 webpage)
46
47 def _real_extract(self, url):
48 video_id = self._match_id(url)
49
50 query = random_birthday('birth_year', 'birth_month', 'birth_day')
51 video = self._download_json(
52 'https://public-api.wordpress.com/rest/v1.1/videos/%s' % video_id,
53 video_id, query=query)
54
55 title = video['title']
56
57 def base_url(scheme):
58 return try_get(
59 video, lambda x: x['file_url_base'][scheme], compat_str)
60
61 base_url = base_url('https') or base_url('http')
62
63 QUALITIES = ('std', 'dvd', 'hd')
64 quality = qualities(QUALITIES)
65
66 formats = []
67 for format_id, f in video['files'].items():
68 if not isinstance(f, dict):
69 continue
70 for ext, path in f.items():
71 if ext in ('mp4', 'ogg'):
72 formats.append({
73 'url': urljoin(base_url, path),
74 'format_id': '%s-%s' % (format_id, ext),
75 'ext': determine_ext(path, ext),
76 'quality': quality(format_id),
77 })
78 original_url = try_get(video, lambda x: x['original'], compat_str)
79 if original_url:
80 formats.append({
81 'url': original_url,
82 'format_id': 'original',
83 'quality': len(QUALITIES),
84 })
85 self._sort_formats(formats)
86
87 return {
88 'id': video_id,
89 'title': title,
90 'description': video.get('description'),
91 'thumbnail': video.get('poster'),
92 'duration': float_or_none(video.get('duration'), 1000),
93 'timestamp': unified_timestamp(video.get('upload_date')),
94 'age_limit': parse_age_limit(video.get('rating')),
95 'formats': formats,
96 }