diff options
author | remitamine <remitamine@gmail.com> | 2015-12-03 20:05:11 +0100 |
---|---|---|
committer | remitamine <remitamine@gmail.com> | 2015-12-03 20:05:11 +0100 |
commit | 640bb54e73779f4a941eae1f17e4be049ca575db (patch) | |
tree | ba0c50db3ad5bb0932a56cda66d4f386b145bb22 /youtube_dl/extractor/novamov.py | |
parent | 497f5fd93fe1efd0df8dc58d518c328ed1409457 (diff) | |
parent | e0977d7686e5df524b1a024484e7a4bb9cfa261d (diff) | |
download | youtube-dl-640bb54e73779f4a941eae1f17e4be049ca575db.tar.xz |
Merge branch 'master' of https://github.com/rg3/youtube-dl into bilibili
Diffstat (limited to 'youtube_dl/extractor/novamov.py')
-rw-r--r-- | youtube_dl/extractor/novamov.py | 47 |
1 files changed, 35 insertions, 12 deletions
diff --git a/youtube_dl/extractor/novamov.py b/youtube_dl/extractor/novamov.py index 04d779890..6163e8855 100644 --- a/youtube_dl/extractor/novamov.py +++ b/youtube_dl/extractor/novamov.py @@ -3,11 +3,13 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import ( - compat_urlparse, -) +from ..compat import compat_urlparse from ..utils import ( ExtractorError, + NO_DEFAULT, + encode_dict, + sanitized_Request, + urlencode_postdata, ) @@ -38,19 +40,40 @@ class NovaMovIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) - page = self._download_webpage( - 'http://%s/video/%s' % (self._HOST, video_id), video_id, 'Downloading video page') + url = 'http://%s/video/%s' % (self._HOST, video_id) - if re.search(self._FILE_DELETED_REGEX, page) is not None: - raise ExtractorError('Video %s does not exist' % video_id, expected=True) + webpage = self._download_webpage( + url, video_id, 'Downloading video page') - filekey = self._search_regex(self._FILEKEY_REGEX, page, 'filekey') + if re.search(self._FILE_DELETED_REGEX, webpage) is not None: + raise ExtractorError('Video %s does not exist' % video_id, expected=True) - title = self._html_search_regex(self._TITLE_REGEX, page, 'title', fatal=False) - description = self._html_search_regex(self._DESCRIPTION_REGEX, page, 'description', default='', fatal=False) + def extract_filekey(default=NO_DEFAULT): + return self._search_regex( + self._FILEKEY_REGEX, webpage, 'filekey', default=default) + + filekey = extract_filekey(default=None) + + if not filekey: + fields = self._hidden_inputs(webpage) + post_url = self._search_regex( + r'<form[^>]+action=(["\'])(?P<url>.+?)\1', webpage, + 'post url', default=url, group='url') + if not post_url.startswith('http'): + post_url = compat_urlparse.urljoin(url, post_url) + request = sanitized_Request( + post_url, urlencode_postdata(encode_dict(fields))) + request.add_header('Content-Type', 'application/x-www-form-urlencoded') + request.add_header('Referer', post_url) + webpage = self._download_webpage( + request, video_id, 'Downloading continue to the video page') + + filekey = extract_filekey() + + title = self._html_search_regex(self._TITLE_REGEX, webpage, 'title', fatal=False) + description = self._html_search_regex(self._DESCRIPTION_REGEX, webpage, 'description', default='', fatal=False) api_response = self._download_webpage( 'http://%s/api/player.api.php?key=%s&file=%s' % (self._HOST, filekey, video_id), video_id, |