]>
Commit | Line | Data |
---|---|---|
efc86777 PH |
1 | from __future__ import unicode_literals |
2 | ||
008af866 | 3 | from .common import InfoExtractor |
39fa4cc1 | 4 | from ..utils import int_or_none |
d55433bb | 5 | |
008af866 | 6 | |
f54aee02 | 7 | _translation_table = { |
b6d3a996 PH |
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 | '$': ':', '&': '.', '(': '=', '^': '&', '=': '/', | |
12 | } | |
008af866 P |
13 | |
14 | ||
f54aee02 PH |
15 | def _decode(s): |
16 | return ''.join(_translation_table.get(c, c) for c in s) | |
17 | ||
18 | ||
008af866 | 19 | class CliphunterIE(InfoExtractor): |
efc86777 | 20 | IE_NAME = 'cliphunter' |
008af866 | 21 | |
b6d3a996 PH |
22 | _VALID_URL = r'''(?x)http://(?:www\.)?cliphunter\.com/w/ |
23 | (?P<id>[0-9]+)/ | |
24 | (?P<seo>.+?)(?:$|[#\?]) | |
25 | ''' | |
26 | _TEST = { | |
efc86777 | 27 | 'url': 'http://www.cliphunter.com/w/1012420/Fun_Jynx_Maze_solo', |
3e055aa5 | 28 | 'md5': 'b7c9bbd4eb3a226ab91093714dcaa480', |
efc86777 | 29 | 'info_dict': { |
f54aee02 | 30 | 'id': '1012420', |
3e055aa5 | 31 | 'ext': 'flv', |
efc86777 | 32 | 'title': 'Fun Jynx Maze solo', |
f54aee02 PH |
33 | 'thumbnail': 're:^https?://.*\.jpg$', |
34 | 'age_limit': 18, | |
008af866 | 35 | } |
efc86777 | 36 | } |
008af866 P |
37 | |
38 | def _real_extract(self, url): | |
c9f08154 | 39 | video_id = self._match_id(url) |
008af866 P |
40 | webpage = self._download_webpage(url, video_id) |
41 | ||
f54aee02 PH |
42 | video_title = self._search_regex( |
43 | r'mediaTitle = "([^"]+)"', webpage, 'title') | |
44 | ||
39fa4cc1 S |
45 | gexo_files = self._parse_json( |
46 | self._search_regex( | |
47 | r'var\s+gexoFiles\s*=\s*({.+?});', webpage, 'gexo files'), | |
48 | video_id) | |
3e055aa5 NJ |
49 | |
50 | formats = [] | |
39fa4cc1 S |
51 | for format_id, f in gexo_files.items(): |
52 | video_url = f.get('url') | |
53 | if not video_url: | |
54 | continue | |
55 | fmt = f.get('fmt') | |
56 | height = f.get('h') | |
57 | format_id = '%s_%sp' % (fmt, height) if fmt and height else format_id | |
58 | formats.append({ | |
59 | 'url': _decode(video_url), | |
60 | 'format_id': format_id, | |
61 | 'width': int_or_none(f.get('w')), | |
62 | 'height': int_or_none(height), | |
63 | 'tbr': int_or_none(f.get('br')), | |
64 | }) | |
f54aee02 PH |
65 | self._sort_formats(formats) |
66 | ||
67 | thumbnail = self._search_regex( | |
68 | r"var\s+mov_thumb\s*=\s*'([^']+)';", | |
69 | webpage, 'thumbnail', fatal=False) | |
f54aee02 | 70 | |
008af866 P |
71 | return { |
72 | 'id': video_id, | |
73 | 'title': video_title, | |
74 | 'formats': formats, | |
f54aee02 PH |
75 | 'age_limit': self._rta_search(webpage), |
76 | 'thumbnail': thumbnail, | |
008af866 | 77 | } |