lopar/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-12-23 16:36:48 +00:00
Code Releases Activity

[novamov] Follow continue-to-the-video button if any (Closes #7330)

Browse Source
This commit is contained in:
Sergey M․ 2015-11-11 21:02:05 +06:00
parent 2eb99a4b98
commit 82393e2bb2
1 changed files with 32 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

38
youtube_dl/extractor/novamov.py
View File

@ -4,10 +4,14 @@ import re
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import ( from ..compat import (
compat_urllib_request,
compat_urlparse, compat_urlparse,
) )
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
NO_DEFAULT,
encode_dict,
urlencode_postdata,
) )
@ -41,16 +45,38 @@ class NovaMovIE(InfoExtractor):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id') video_id = mobj.group('id')
page = self._download_webpage( url = 'http://%s/video/%s' % (self._HOST, video_id)
'http://%s/video/%s' % (self._HOST, video_id), video_id, 'Downloading video page')
if re.search(self._FILE_DELETED_REGEX, page) is not None: webpage = self._download_webpage(
url, video_id, 'Downloading video page')
if re.search(self._FILE_DELETED_REGEX, webpage) is not None:
raise ExtractorError('Video %s does not exist' % video_id, expected=True) raise ExtractorError('Video %s does not exist' % video_id, expected=True)
filekey = self._search_regex(self._FILEKEY_REGEX, page, 'filekey') def extract_filekey(default=NO_DEFAULT):
return self._search_regex(
self._FILEKEY_REGEX, webpage, 'filekey', default=default)
title = self._html_search_regex(self._TITLE_REGEX, page, 'title', fatal=False) filekey = extract_filekey(default=None)
description = self._html_search_regex(self._DESCRIPTION_REGEX, page, 'description', default='', fatal=False)
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 = compat_urllib_request.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( api_response = self._download_webpage(
'http://%s/api/player.api.php?key=%s&file=%s' % (self._HOST, filekey, video_id), video_id, 'http://%s/api/player.api.php?key=%s&file=%s' % (self._HOST, filekey, video_id), video_id,