jcgruenhage/youtube-dl
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

[promptfile] Fix extraction (Closes #10634)

Browse source
This commit is contained in:
Ondřej Bárta 2016-09-25 12:44:46 +02:00 committed by Sergey M․
parent fffb9cff94
commit d3dbb46330
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
1 changed files with 11 additions and 5 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

16
youtube_dl/extractor/promptfile.py
View file

@ -15,12 +15,12 @@ from ..utils import (
class PromptFileIE(InfoExtractor): class PromptFileIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?promptfile\.com/l/(?P<id>[0-9A-Z\-]+)' _VALID_URL = r'https?://(?:www\.)?promptfile\.com/l/(?P<id>[0-9A-Z\-]+)'
_TEST = { _TEST = {
'url': 'http://www.promptfile.com/l/D21B4746E9-F01462F0FF', 'url': 'http://www.promptfile.com/l/86D1CE8462-576CAAE416',
'md5': 'd1451b6302da7215485837aaea882c4c', 'md5': '5a7e285a26e0d66d9a263fae91bc92ce',
'info_dict': { 'info_dict': {
'id': 'D21B4746E9-F01462F0FF', 'id': '86D1CE8462-576CAAE416',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Birds.mp4', 'title': 'oceans.mp4',
'thumbnail': 're:^https?://.*\.jpg$', 'thumbnail': 're:^https?://.*\.jpg$',
} }
} }
@ -33,14 +33,20 @@ class PromptFileIE(InfoExtractor):
raise ExtractorError('Video %s does not exist' % video_id, raise ExtractorError('Video %s does not exist' % video_id,
expected=True) expected=True)
chash_pattern = r'\$\("#chash"\)\.val\("(.+)"\+\$\("#chash"\)'
chash = self._html_search_regex(chash_pattern, webpage, "chash")
fields = self._hidden_inputs(webpage) fields = self._hidden_inputs(webpage)
k = list(fields)[0]
fields[k] = chash + fields[k]
post = urlencode_postdata(fields) post = urlencode_postdata(fields)
req = sanitized_Request(url, post) req = sanitized_Request(url, post)
req.add_header('Content-type', 'application/x-www-form-urlencoded') req.add_header('Content-type', 'application/x-www-form-urlencoded')
webpage = self._download_webpage( webpage = self._download_webpage(
req, video_id, 'Downloading video page') req, video_id, 'Downloading video page')
url = self._html_search_regex(r'url:\s*\'([^\']+)\'', webpage, 'URL') url_pattern = r'<a href="(http://www\.promptfile\.com/file/[^"]+)'
url = self._html_search_regex(url_pattern, webpage, 'URL')
title = self._html_search_regex( title = self._html_search_regex(
r'<span.+title="([^"]+)">', webpage, 'title') r'<span.+title="([^"]+)">', webpage, 'title')
thumbnail = self._html_search_regex( thumbnail = self._html_search_regex(