summaryrefslogtreecommitdiffhomepage
diff options
context:
space:
mode:
authorPhilipp Hagemeister <[email protected]>2013-07-17 11:16:53 +0200
committerPhilipp Hagemeister <[email protected]>2013-07-17 11:16:53 +0200
commit466de6880121d55de082975f0274cfab71b6c2ab (patch)
treeb6ba3e2ba69f984152e8e6b3c02811005ef85531
parent88d4111cfa2f88a323de5ae0a8e75942530fa67d (diff)
downloadyoutube-dl-466de6880121d55de082975f0274cfab71b6c2ab.tar.gz
youtube-dl-466de6880121d55de082975f0274cfab71b6c2ab.zip
[thisav] Add IE (Fixes #1056)
-rw-r--r--youtube_dl/extractor/__init__.py1
-rw-r--r--youtube_dl/extractor/thisav.py46
2 files changed, 47 insertions, 0 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index fea7513f9..6738c4168 100644
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -58,6 +58,7 @@ from .steam import SteamIE
from .teamcoco import TeamcocoIE
from .ted import TEDIE
from .tf1 import TF1IE
+from .thisav import ThisAVIE
from .traileraddict import TrailerAddictIE
from .tudou import TudouIE
from .tumblr import TumblrIE
diff --git a/youtube_dl/extractor/thisav.py b/youtube_dl/extractor/thisav.py
new file mode 100644
index 000000000..35b7379b6
--- /dev/null
+++ b/youtube_dl/extractor/thisav.py
@@ -0,0 +1,46 @@
+#coding: utf-8
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+ determine_ext,
+)
+
+class ThisAVIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:www\.)?thisav\.com/video/(?P<id>[0-9]+)/.*'
+ _TEST = {
+ u"url": u"http://www.thisav.com/video/47734/%98%26sup1%3B%83%9E%83%82---just-fit.html",
+ u"file": u"47734.flv",
+ u"info_dict": {
+ u"title": u"高樹マリア - Just fit",
+ u"uploader": u"dj7970",
+ u"uploader_id": u"dj7970"
+ }
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+
+ video_id = mobj.group('id')
+ webpage = self._download_webpage(url, video_id)
+ title = self._html_search_regex(r'<h1>([^<]*)</h1>', webpage, u'title')
+ video_url = self._html_search_regex(
+ r"addVariable\('file','([^']+)'\);", webpage, u'video url')
+ uploader = self._html_search_regex(
+ r': <a href="http://www.thisav.com/user/[0-9]+/(?:[^"]+)">([^<]+)</a>',
+ webpage, u'uploader name', fatal=False)
+ uploader_id = self._html_search_regex(
+ r': <a href="http://www.thisav.com/user/[0-9]+/([^"]+)">(?:[^<]+)</a>',
+ webpage, u'uploader id', fatal=False)
+ ext = determine_ext(video_url)
+
+ return {
+ '_type': 'video',
+ 'id': video_id,
+ 'url': video_url,
+ 'uploader': uploader,
+ 'uploader_id': uploader_id,
+ 'title': title,
+ 'ext': ext,
+ }