aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/veehd.py
diff options
context:
space:
mode:
authorJaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com>2013-09-02 11:54:09 +0200
committerJaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com>2013-09-02 11:54:09 +0200
commit8e4e89f1c236e1bec38c5363c1c341930056211e (patch)
tree70a69d7e9bad6a9f2d131b908d0a13b416fed704 /youtube_dl/extractor/veehd.py
parent6c758d79de48956b90d9e78aec695ee0b10b00d2 (diff)
Add an extractor for VeeHD (closes #1359)
Diffstat (limited to 'youtube_dl/extractor/veehd.py')
-rw-r--r--youtube_dl/extractor/veehd.py56
1 files changed, 56 insertions, 0 deletions
diff --git a/youtube_dl/extractor/veehd.py b/youtube_dl/extractor/veehd.py
new file mode 100644
index 000000000..3a99a29c6
--- /dev/null
+++ b/youtube_dl/extractor/veehd.py
@@ -0,0 +1,56 @@
+import re
+import json
+
+from .common import InfoExtractor
+from ..utils import (
+ compat_urlparse,
+ get_element_by_id,
+ clean_html,
+)
+
+class VeeHDIE(InfoExtractor):
+ _VALID_URL = r'https?://veehd.com/video/(?P<id>\d+)'
+
+ _TEST = {
+ u'url': u'http://veehd.com/video/4686958',
+ u'file': u'4686958.mp4',
+ u'info_dict': {
+ u'title': u'Time Lapse View from Space ( ISS)',
+ u'uploader_id': u'spotted',
+ u'description': u'md5:f0094c4cf3a72e22bc4e4239ef767ad7',
+ },
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('id')
+
+ webpage = self._download_webpage(url, video_id)
+ player_path = self._search_regex(r'\$\("#playeriframe"\).attr\({src : "(.+?)"',
+ webpage, u'player path')
+ player_url = compat_urlparse.urljoin(url, player_path)
+ player_page = self._download_webpage(player_url, video_id,
+ u'Downloading player page')
+ config_json = self._search_regex(r'value=\'config=({.+?})\'',
+ player_page, u'config json')
+ config = json.loads(config_json)
+
+ video_url = compat_urlparse.unquote(config['clip']['url'])
+ title = clean_html(get_element_by_id('videoName', webpage).rpartition('|')[0])
+ uploader_id = self._html_search_regex(r'<a href="/profile/\d+">(.+?)</a>',
+ webpage, u'uploader')
+ thumbnail = self._search_regex(r'<img id="veehdpreview" src="(.+?)"',
+ webpage, u'thumbnail')
+ description = self._html_search_regex(r'<td class="infodropdown".*?<div>(.*?)<ul',
+ webpage, u'description', flags=re.DOTALL)
+
+ return {
+ '_type': 'video',
+ 'id': video_id,
+ 'title': title,
+ 'url': video_url,
+ 'ext': 'mp4',
+ 'uploader_id': uploader_id,
+ 'thumbnail': thumbnail,
+ 'description': description,
+ }