1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
|
from __future__ import unicode_literals
import re
import json
from .common import InfoExtractor
from ..utils import (
determine_ext,
int_or_none,
qualities,
unescapeHTML,
)
class GiantBombIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?giantbomb\.com/videos/(?P<display_id>[^/]+)/(?P<id>\d+-\d+)'
_TEST = {
'url': 'http://www.giantbomb.com/videos/quick-look-destiny-the-dark-below/2300-9782/',
'md5': 'c8ea694254a59246a42831155dec57ac',
'info_dict': {
'id': '2300-9782',
'display_id': 'quick-look-destiny-the-dark-below',
'ext': 'mp4',
'title': 'Quick Look: Destiny: The Dark Below',
'description': 'md5:0aa3aaf2772a41b91d44c63f30dfad24',
'duration': 2399,
'thumbnail': r're:^https?://.*\.jpg$',
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
display_id = mobj.group('display_id')
webpage = self._download_webpage(url, display_id)
title = self._og_search_title(webpage)
description = self._og_search_description(webpage)
thumbnail = self._og_search_thumbnail(webpage)
video = json.loads(unescapeHTML(self._search_regex(
r'data-video="([^"]+)"', webpage, 'data-video')))
duration = int_or_none(video.get('lengthSeconds'))
quality = qualities([
'f4m_low', 'progressive_low', 'f4m_high',
'progressive_high', 'f4m_hd', 'progressive_hd'])
formats = []
for format_id, video_url in video['videoStreams'].items():
if format_id == 'f4m_stream':
continue
ext = determine_ext(video_url)
if ext == 'f4m':
f4m_formats = self._extract_f4m_formats(video_url + '?hdcore=3.3.1', display_id)
if f4m_formats:
f4m_formats[0]['quality'] = quality(format_id)
formats.extend(f4m_formats)
elif ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
video_url, display_id, ext='mp4', entry_protocol='m3u8_native',
m3u8_id='hls', fatal=False))
else:
formats.append({
'url': video_url,
'format_id': format_id,
'quality': quality(format_id),
})
if not formats:
youtube_id = video.get('youtubeID')
if youtube_id:
return self.url_result(youtube_id, 'Youtube')
self._sort_formats(formats)
return {
'id': video_id,
'display_id': display_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'duration': duration,
'formats': formats,
}
|
