]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/novamov.py
debian/changelog: Annotate bugs to close.
[youtubedl] / youtube_dl / extractor / novamov.py
1 from __future__ import unicode_literals
2
3 import re
4
5 from .common import InfoExtractor
6 from ..compat import (
7 compat_urlparse,
8 )
9 from ..utils import (
10 ExtractorError,
11 )
12
13
14 class NovaMovIE(InfoExtractor):
15 IE_NAME = 'novamov'
16 IE_DESC = 'NovaMov'
17
18 _VALID_URL_TEMPLATE = r'http://(?:(?:www\.)?%(host)s/(?:file|video)/|(?:(?:embed|www)\.)%(host)s/embed\.php\?(?:.*?&)?v=)(?P<id>[a-z\d]{13})'
19 _VALID_URL = _VALID_URL_TEMPLATE % {'host': 'novamov\.com'}
20
21 _HOST = 'www.novamov.com'
22
23 _FILE_DELETED_REGEX = r'This file no longer exists on our servers!</h2>'
24 _FILEKEY_REGEX = r'flashvars\.filekey="(?P<filekey>[^"]+)";'
25 _TITLE_REGEX = r'(?s)<div class="v_tab blockborder rounded5" id="v_tab1">\s*<h3>([^<]+)</h3>'
26 _DESCRIPTION_REGEX = r'(?s)<div class="v_tab blockborder rounded5" id="v_tab1">\s*<h3>[^<]+</h3><p>([^<]+)</p>'
27
28 _TEST = {
29 'url': 'http://www.novamov.com/video/4rurhn9x446jj',
30 'md5': '7205f346a52bbeba427603ba10d4b935',
31 'info_dict': {
32 'id': '4rurhn9x446jj',
33 'ext': 'flv',
34 'title': 'search engine optimization',
35 'description': 'search engine optimization is used to rank the web page in the google search engine'
36 },
37 'skip': '"Invalid token" errors abound (in web interface as well as youtube-dl, there is nothing we can do about it.)'
38 }
39
40 def _real_extract(self, url):
41 mobj = re.match(self._VALID_URL, url)
42 video_id = mobj.group('id')
43
44 page = self._download_webpage(
45 'http://%s/video/%s' % (self._HOST, video_id), video_id, 'Downloading video page')
46
47 if re.search(self._FILE_DELETED_REGEX, page) is not None:
48 raise ExtractorError('Video %s does not exist' % video_id, expected=True)
49
50 filekey = self._search_regex(self._FILEKEY_REGEX, page, 'filekey')
51
52 title = self._html_search_regex(self._TITLE_REGEX, page, 'title', fatal=False)
53 description = self._html_search_regex(self._DESCRIPTION_REGEX, page, 'description', default='', fatal=False)
54
55 api_response = self._download_webpage(
56 'http://%s/api/player.api.php?key=%s&file=%s' % (self._HOST, filekey, video_id), video_id,
57 'Downloading video api response')
58
59 response = compat_urlparse.parse_qs(api_response)
60
61 if 'error_msg' in response:
62 raise ExtractorError('%s returned error: %s' % (self.IE_NAME, response['error_msg'][0]), expected=True)
63
64 video_url = response['url'][0]
65
66 return {
67 'id': video_id,
68 'url': video_url,
69 'title': title,
70 'description': description
71 }