aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/toypics.py
diff options
context:
space:
mode:
authorPhilipp Hagemeister <phihag@phihag.de>2014-03-22 14:24:44 +0100
committerPhilipp Hagemeister <phihag@phihag.de>2014-03-22 14:24:44 +0100
commit55442a7812d3df6b888fa2f61446f711ed3e92b4 (patch)
treeeb0dc448c53e6b2380015a6fbc2681d5a7cb6b47 /youtube_dl/extractor/toypics.py
parent43b81eb98afb8958b9a31220bf710a97751df5be (diff)
parent74af99fc2fd5fd971dd04224e90cb799b6b4bb29 (diff)
Merge remote-tracking branch 'fiocfun/toypics-support'
Diffstat (limited to 'youtube_dl/extractor/toypics.py')
-rw-r--r--youtube_dl/extractor/toypics.py55
1 files changed, 55 insertions, 0 deletions
diff --git a/youtube_dl/extractor/toypics.py b/youtube_dl/extractor/toypics.py
new file mode 100644
index 000000000..3cbfe2e7e
--- /dev/null
+++ b/youtube_dl/extractor/toypics.py
@@ -0,0 +1,55 @@
+from .common import InfoExtractor
+from math import ceil
+import re
+
+class ToypicsIE(InfoExtractor):
+ _VALID_URL = r'(?:http://)?videos\.toypics\.net/.*'
+ _TEST = {
+ 'url': 'http://videos.toypics.net/view/514/chancebulged,-2-1/',
+ #'md5': '8a8b546956bbd0e769dbe28f6e80abb3', == $head -c10K 12929646011616163504.mp4 |md5sum //no idea why it fails
+ 'info_dict': {
+ 'id': '514',
+ 'ext': 'mp4',
+ 'title': 'Chance-Bulge\'d, 2',
+ 'age_limit': 18
+ }
+ }
+ PAGINATED=8
+
+ def _real_extract(self, url):
+ mobj = re.match(r'(http://)?videos\.toypics\.net/(?P<username>[^/?]+)$', url)
+ if not mobj:
+ return self.extract_one(url)
+ return [self.extract_one(u) for u in self.process_paginated(url,
+ r'public/">Public Videos \((?P<videos_count>[0-9]+)\)</a></li>',
+ r'<p class="video-entry-title">\n\s*<a href="(http://videos.toypics.net/view/[^"]+)">'
+ )]
+
+ def process_paginated(self, profile_url, re_total, re_video_page):
+ profile_page = self._download_webpage(profile_url, 'profile' , 'getting profile page: '+profile_url)
+ videos_count = self._html_search_regex(re_total, profile_page, 'videos count')
+ lst = []
+ for n in xrange(1,int(ceil(float(videos_count)/self.PAGINATED)) +1):
+ lpage_url = profile_url +'/public/%d'%n
+ lpage = self._download_webpage(lpage_url, 'page %d'%n)
+ lst.extend(re.findall(re_video_page, lpage))
+ return lst
+
+ def extract_one(self,url):
+ mobj = re.match(r'(http://)?videos\.toypics\.net/view/(?P<videoid>[0-9]+)/.*', url)
+ video_id = mobj.group('videoid')
+ page = self._download_webpage(url, video_id, 'getting page: '+url)
+ video_url = self._html_search_regex(
+ r'src:\s+"(http://static[0-9]+\.toypics\.net/flvideo/[^"]+)"', page, 'video URL')
+ title = self._html_search_regex(
+ r'<title>Toypics - ([^<]+)</title>', page, 'title')
+ username = self._html_search_regex(
+ r'toypics.net/([^/"]+)" class="user-name">', page, 'username')
+ return {
+ 'id': video_id,
+ 'url': video_url,
+ 'ext': video_url[-3:],
+ 'title': title,
+ 'uploader': username,
+ 'age_limit': 18
+ }