]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/cliphunter.py
debian/changelog: Annotate bugs to close.
[youtubedl] / youtube_dl / extractor / cliphunter.py
1 from __future__ import unicode_literals
2
3 from .common import InfoExtractor
4 from ..utils import determine_ext
5
6
7 _translation_table = {
8 'a': 'h', 'd': 'e', 'e': 'v', 'f': 'o', 'g': 'f', 'i': 'd', 'l': 'n',
9 'm': 'a', 'n': 'm', 'p': 'u', 'q': 't', 'r': 's', 'v': 'p', 'x': 'r',
10 'y': 'l', 'z': 'i',
11 '$': ':', '&': '.', '(': '=', '^': '&', '=': '/',
12 }
13
14
15 def _decode(s):
16 return ''.join(_translation_table.get(c, c) for c in s)
17
18
19 class CliphunterIE(InfoExtractor):
20 IE_NAME = 'cliphunter'
21
22 _VALID_URL = r'''(?x)http://(?:www\.)?cliphunter\.com/w/
23 (?P<id>[0-9]+)/
24 (?P<seo>.+?)(?:$|[#\?])
25 '''
26 _TEST = {
27 'url': 'http://www.cliphunter.com/w/1012420/Fun_Jynx_Maze_solo',
28 'md5': 'b7c9bbd4eb3a226ab91093714dcaa480',
29 'info_dict': {
30 'id': '1012420',
31 'ext': 'flv',
32 'title': 'Fun Jynx Maze solo',
33 'thumbnail': 're:^https?://.*\.jpg$',
34 'age_limit': 18,
35 }
36 }
37
38 def _real_extract(self, url):
39 video_id = self._match_id(url)
40 webpage = self._download_webpage(url, video_id)
41
42 video_title = self._search_regex(
43 r'mediaTitle = "([^"]+)"', webpage, 'title')
44
45 fmts = {}
46 for fmt in ('mp4', 'flv'):
47 fmt_list = self._parse_json(self._search_regex(
48 r'var %sjson\s*=\s*(\[.*?\]);' % fmt, webpage, '%s formats' % fmt), video_id)
49 for f in fmt_list:
50 fmts[f['fname']] = _decode(f['sUrl'])
51
52 qualities = self._parse_json(self._search_regex(
53 r'var player_btns\s*=\s*(.*?);\n', webpage, 'quality info'), video_id)
54
55 formats = []
56 for fname, url in fmts.items():
57 f = {
58 'url': url,
59 }
60 if fname in qualities:
61 qual = qualities[fname]
62 f.update({
63 'format_id': '%s_%sp' % (determine_ext(url), qual['h']),
64 'width': qual['w'],
65 'height': qual['h'],
66 'tbr': qual['br'],
67 })
68 formats.append(f)
69
70 self._sort_formats(formats)
71
72 thumbnail = self._search_regex(
73 r"var\s+mov_thumb\s*=\s*'([^']+)';",
74 webpage, 'thumbnail', fatal=False)
75
76 return {
77 'id': video_id,
78 'title': video_title,
79 'formats': formats,
80 'age_limit': self._rta_search(webpage),
81 'thumbnail': thumbnail,
82 }