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

[thisav] Recognize jwplayers (closes #10447)

Browse source
This commit is contained in:
Yen Chi Hsuan 2016-09-17 18:46:43 +08:00
parent e14c82bd6b
commit 584d6f3457
No known key found for this signature in database
GPG key ID: 3FDDD575826C5C30
2 changed files with 29 additions and 11 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

1
ChangeLog
View file

@ -1,6 +1,7 @@
version <unreleased> version <unreleased>
Extractors Extractors
+ [thisav] Recognize HTML5 videos (#10447)
* [jwplatform] Improve JWPlayer detection * [jwplatform] Improve JWPlayer detection

39
youtube_dl/extractor/thisav.py
View file

@ -3,13 +3,12 @@ from __future__ import unicode_literals
import re import re
from .common import InfoExtractor from .jwplatform import JWPlatformBaseIE
from ..utils import determine_ext
class ThisAVIE(InfoExtractor): class ThisAVIE(JWPlatformBaseIE):
_VALID_URL = r'https?://(?:www\.)?thisav\.com/video/(?P<id>[0-9]+)/.*' _VALID_URL = r'https?://(?:www\.)?thisav\.com/video/(?P<id>[0-9]+)/.*'
_TEST = { _TESTS = [{
'url': 'http://www.thisav.com/video/47734/%98%26sup1%3B%83%9E%83%82---just-fit.html', 'url': 'http://www.thisav.com/video/47734/%98%26sup1%3B%83%9E%83%82---just-fit.html',
'md5': '0480f1ef3932d901f0e0e719f188f19b', 'md5': '0480f1ef3932d901f0e0e719f188f19b',
'info_dict': { 'info_dict': {
@ -19,7 +18,17 @@ class ThisAVIE(InfoExtractor):
'uploader': 'dj7970', 'uploader': 'dj7970',
'uploader_id': 'dj7970' 'uploader_id': 'dj7970'
} }
} }, {
'url': 'http://www.thisav.com/video/242352/nerdy-18yo-big-ass-tattoos-and-glasses.html',
'md5': 'ba90c076bd0f80203679e5b60bf523ee',
'info_dict': {
'id': '242352',
'ext': 'mp4',
'title': 'Nerdy 18yo Big Ass Tattoos and Glasses',
'uploader': 'cybersluts',
'uploader_id': 'cybersluts',
},
}]
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
@ -28,20 +37,28 @@ class ThisAVIE(InfoExtractor):
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
title = self._html_search_regex(r'<h1>([^<]*)</h1>', webpage, 'title') title = self._html_search_regex(r'<h1>([^<]*)</h1>', webpage, 'title')
video_url = self._html_search_regex( video_url = self._html_search_regex(
r"addVariable\('file','([^']+)'\);", webpage, 'video url') r"addVariable\('file','([^']+)'\);", webpage, 'video url', default=None)
if video_url:
info_dict = {
'formats': [{
'url': video_url,
}],
}
else:
info_dict = self._extract_jwplayer_data(
webpage, video_id, require_title=False)
uploader = self._html_search_regex( uploader = self._html_search_regex(
r': <a href="http://www.thisav.com/user/[0-9]+/(?:[^"]+)">([^<]+)</a>', r': <a href="http://www.thisav.com/user/[0-9]+/(?:[^"]+)">([^<]+)</a>',
webpage, 'uploader name', fatal=False) webpage, 'uploader name', fatal=False)
uploader_id = self._html_search_regex( uploader_id = self._html_search_regex(
r': <a href="http://www.thisav.com/user/[0-9]+/([^"]+)">(?:[^<]+)</a>', r': <a href="http://www.thisav.com/user/[0-9]+/([^"]+)">(?:[^<]+)</a>',
webpage, 'uploader id', fatal=False) webpage, 'uploader id', fatal=False)
ext = determine_ext(video_url)
return { info_dict.update({
'id': video_id, 'id': video_id,
'url': video_url,
'uploader': uploader, 'uploader': uploader,
'uploader_id': uploader_id, 'uploader_id': uploader_id,
'title': title, 'title': title,
'ext': ext, })
}
return info_dict