aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/thisav.py
diff options
context:
space:
mode:
Diffstat (limited to 'youtube_dl/extractor/thisav.py')
-rw-r--r--youtube_dl/extractor/thisav.py39
1 files changed, 28 insertions, 11 deletions
diff --git a/youtube_dl/extractor/thisav.py b/youtube_dl/extractor/thisav.py
index 7f323c938..027a8e907 100644
--- a/youtube_dl/extractor/thisav.py
+++ b/youtube_dl/extractor/thisav.py
@@ -3,13 +3,12 @@ from __future__ import unicode_literals
import re
-from .common import InfoExtractor
-from ..utils import determine_ext
+from .jwplatform import JWPlatformBaseIE
-class ThisAVIE(InfoExtractor):
+class ThisAVIE(JWPlatformBaseIE):
_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',
'md5': '0480f1ef3932d901f0e0e719f188f19b',
'info_dict': {
@@ -19,7 +18,17 @@ class ThisAVIE(InfoExtractor):
'uploader': '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):
mobj = re.match(self._VALID_URL, url)
@@ -28,20 +37,28 @@ class ThisAVIE(InfoExtractor):
webpage = self._download_webpage(url, video_id)
title = self._html_search_regex(r'<h1>([^<]*)</h1>', webpage, 'title')
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(
r': <a href="http://www.thisav.com/user/[0-9]+/(?:[^"]+)">([^<]+)</a>',
webpage, 'uploader name', fatal=False)
uploader_id = self._html_search_regex(
r': <a href="http://www.thisav.com/user/[0-9]+/([^"]+)">(?:[^<]+)</a>',
webpage, 'uploader id', fatal=False)
- ext = determine_ext(video_url)
- return {
+ info_dict.update({
'id': video_id,
- 'url': video_url,
'uploader': uploader,
'uploader_id': uploader_id,
'title': title,
- 'ext': ext,
- }
+ })
+
+ return info_dict