]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/gamespot.py
621257c9f72383a5c6133001953a7e51cc5df435
[youtubedl] / youtube_dl / extractor / gamespot.py
1 from __future__ import unicode_literals
2
3 import re
4
5 from .once import OnceIE
6 from ..compat import (
7 compat_urllib_parse_unquote,
8 )
9 from ..utils import (
10 unescapeHTML,
11 url_basename,
12 dict_get,
13 )
14
15
16 class GameSpotIE(OnceIE):
17 _VALID_URL = r'https?://(?:www\.)?gamespot\.com/.*-(?P<id>\d+)/?'
18 _TESTS = [{
19 'url': 'http://www.gamespot.com/videos/arma-3-community-guide-sitrep-i/2300-6410818/',
20 'md5': 'b2a30deaa8654fcccd43713a6b6a4825',
21 'info_dict': {
22 'id': 'gs-2300-6410818',
23 'ext': 'mp4',
24 'title': 'Arma 3 - Community Guide: SITREP I',
25 'description': 'Check out this video where some of the basics of Arma 3 is explained.',
26 },
27 }, {
28 'url': 'http://www.gamespot.com/videos/the-witcher-3-wild-hunt-xbox-one-now-playing/2300-6424837/',
29 'info_dict': {
30 'id': 'gs-2300-6424837',
31 'ext': 'flv',
32 'title': 'The Witcher 3: Wild Hunt [Xbox ONE] - Now Playing',
33 'description': 'Join us as we take a look at the early hours of The Witcher 3: Wild Hunt and more.',
34 },
35 }]
36
37 def _real_extract(self, url):
38 page_id = self._match_id(url)
39 webpage = self._download_webpage(url, page_id)
40 data_video_json = self._search_regex(
41 r'data-video=["\'](.*?)["\']', webpage, 'data video')
42 data_video = self._parse_json(unescapeHTML(data_video_json), page_id)
43 streams = data_video['videoStreams']
44
45 manifest_url = None
46 formats = []
47 f4m_url = streams.get('f4m_stream')
48 if f4m_url:
49 manifest_url = f4m_url
50 formats.extend(self._extract_f4m_formats(
51 f4m_url + '?hdcore=3.7.0', page_id, f4m_id='hds', fatal=False))
52 m3u8_url = streams.get('m3u8_stream')
53 if m3u8_url:
54 manifest_url = m3u8_url
55 m3u8_formats = self._extract_m3u8_formats(
56 m3u8_url, page_id, 'mp4', 'm3u8_native',
57 m3u8_id='hls', fatal=False)
58 formats.extend(m3u8_formats)
59 progressive_url = dict_get(
60 streams, ('progressive_hd', 'progressive_high', 'progressive_low'))
61 if progressive_url and manifest_url:
62 qualities_basename = self._search_regex(
63 '/([^/]+)\.csmil/',
64 manifest_url, 'qualities basename', default=None)
65 if qualities_basename:
66 QUALITIES_RE = r'((,\d+)+,?)'
67 qualities = self._search_regex(
68 QUALITIES_RE, qualities_basename,
69 'qualities', default=None)
70 if qualities:
71 qualities = list(map(lambda q: int(q), qualities.strip(',').split(',')))
72 qualities.sort()
73 http_template = re.sub(QUALITIES_RE, r'%d', qualities_basename)
74 http_url_basename = url_basename(progressive_url)
75 if m3u8_formats:
76 self._sort_formats(m3u8_formats)
77 m3u8_formats = list(filter(
78 lambda f: f.get('vcodec') != 'none' and f.get('resolution') != 'multiple',
79 m3u8_formats))
80 if len(qualities) == len(m3u8_formats):
81 for q, m3u8_format in zip(qualities, m3u8_formats):
82 f = m3u8_format.copy()
83 f.update({
84 'url': progressive_url.replace(
85 http_url_basename, http_template % q),
86 'format_id': f['format_id'].replace('hls', 'http'),
87 'protocol': 'http',
88 })
89 formats.append(f)
90 else:
91 for q in qualities:
92 formats.append({
93 'url': progressive_url.replace(
94 http_url_basename, http_template % q),
95 'ext': 'mp4',
96 'format_id': 'http-%d' % q,
97 'tbr': q,
98 })
99
100 onceux_json = self._search_regex(
101 r'data-onceux-options=["\'](.*?)["\']', webpage, 'data video', default=None)
102 if onceux_json:
103 onceux_url = self._parse_json(unescapeHTML(onceux_json), page_id).get('metadataUri')
104 if onceux_url:
105 formats.extend(self._extract_once_formats(re.sub(
106 r'https?://[^/]+', 'http://once.unicornmedia.com', onceux_url).replace('ads/vmap/', '')))
107
108 if not formats:
109 for quality in ['sd', 'hd']:
110 # It's actually a link to a flv file
111 flv_url = streams.get('f4m_{0}'.format(quality))
112 if flv_url is not None:
113 formats.append({
114 'url': flv_url,
115 'ext': 'flv',
116 'format_id': quality,
117 })
118 self._sort_formats(formats)
119
120 return {
121 'id': data_video['guid'],
122 'display_id': page_id,
123 'title': compat_urllib_parse_unquote(data_video['title']),
124 'formats': formats,
125 'description': self._html_search_meta('description', webpage),
126 'thumbnail': self._og_search_thumbnail(webpage),
127 }