commit aa94a6d3159af8333b56d16f3ed0bc3a164a882a
parent 768df745385a283f4df3a38ee4734feec518ec87
Author: Philipp Hagemeister <phihag@phihag.de>
Date: Fri, 20 Dec 2013 17:05:28 +0100
[aparat] Add support (Fixes #2012)
Diffstat:
5 files changed, 73 insertions(+), 6 deletions(-)
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
@@ -1,6 +1,7 @@
from .academicearth import AcademicEarthCourseIE
from .addanime import AddAnimeIE
from .anitube import AnitubeIE
+from .aparat import AparatIE
from .appletrailers import AppleTrailersIE
from .archiveorg import ArchiveOrgIE
from .ard import ARDIE
diff --git a/youtube_dl/extractor/aparat.py b/youtube_dl/extractor/aparat.py
@@ -0,0 +1,56 @@
+#coding: utf-8
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+ ExtractorError,
+ HEADRequest,
+)
+
+
+class AparatIE(InfoExtractor):
+ _VALID_URL = r'^https?://(?:www\.)?aparat\.com/(?:v/|video/video/embed/videohash/)(?P<id>[a-zA-Z0-9]+)'
+
+ _TEST = {
+ u'url': u'http://www.aparat.com/v/wP8On',
+ u'file': u'wP8On.mp4',
+ u'md5': u'6714e0af7e0d875c5a39c4dc4ab46ad1',
+ u'info_dict': {
+ u"title": u"تیم گلکسی 11 - زومیت",
+ },
+ #u'skip': u'Extremely unreliable',
+ }
+
+ def _real_extract(self, url):
+ m = re.match(self._VALID_URL, url)
+ video_id = m.group('id')
+
+ # Note: There is an easier-to-parse configuration at
+ # http://www.aparat.com/video/video/config/videohash/%video_id
+ # but the URL in there does not work
+ embed_url = (u'http://www.aparat.com/video/video/embed/videohash/' +
+ video_id + u'/vt/frame')
+ webpage = self._download_webpage(embed_url, video_id)
+
+ video_urls = re.findall(r'fileList\[[0-9]+\]\s*=\s*"([^"]+)"', webpage)
+ for i, video_url in enumerate(video_urls):
+ req = HEADRequest(video_url)
+ res = self._request_webpage(
+ req, video_id, note=u'Testing video URL %d' % i, errnote=False)
+ if res:
+ break
+ else:
+ raise ExtractorError(u'No working video URLs found')
+
+ title = self._search_regex(r'\s+title:\s*"([^"]+)"', webpage, u'title')
+ thumbnail = self._search_regex(
+ r'\s+image:\s*"([^"]+)"', webpage, u'thumbnail', fatal=False)
+
+ return {
+ 'id': video_id,
+ 'title': title,
+ 'url': video_url,
+ 'ext': 'mp4',
+ 'thumbnail': thumbnail,
+ }
diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py
@@ -170,6 +170,8 @@ class InfoExtractor(object):
try:
return self._downloader.urlopen(url_or_request)
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
+ if errnote is False:
+ return False
if errnote is None:
errnote = u'Unable to download webpage'
errmsg = u'%s: %s' % (errnote, compat_str(err))
diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
@@ -11,6 +11,7 @@ from ..utils import (
compat_urlparse,
ExtractorError,
+ HEADRequest,
smuggle_url,
unescapeHTML,
unified_strdate,
@@ -109,21 +110,18 @@ class GenericIE(InfoExtractor):
def _send_head(self, url):
"""Check if it is a redirect, like url shorteners, in case return the new url."""
- class HeadRequest(compat_urllib_request.Request):
- def get_method(self):
- return "HEAD"
class HEADRedirectHandler(compat_urllib_request.HTTPRedirectHandler):
"""
Subclass the HTTPRedirectHandler to make it use our
- HeadRequest also on the redirected URL
+ HEADRequest also on the redirected URL
"""
def redirect_request(self, req, fp, code, msg, headers, newurl):
if code in (301, 302, 303, 307):
newurl = newurl.replace(' ', '%20')
newheaders = dict((k,v) for k,v in req.headers.items()
if k.lower() not in ("content-length", "content-type"))
- return HeadRequest(newurl,
+ return HEADRequest(newurl,
headers=newheaders,
origin_req_host=req.get_origin_req_host(),
unverifiable=True)
@@ -152,7 +150,7 @@ class GenericIE(InfoExtractor):
compat_urllib_request.HTTPErrorProcessor, compat_urllib_request.HTTPSHandler]:
opener.add_handler(handler())
- response = opener.open(HeadRequest(url))
+ response = opener.open(HEADRequest(url))
if response is None:
raise ExtractorError(u'Invalid URL protocol')
return response
@@ -296,6 +294,11 @@ class GenericIE(InfoExtractor):
if mobj is not None:
return OoyalaIE._build_url_result(mobj.group(1))
+ # Look for Aparat videos
+ mobj = re.search(r'<iframe src="(http://www.aparat.com/video/[^"]+)"', webpage)
+ if mobj is not None:
+ return self.url_result(mobj.group(1), 'Aparat')
+
# Start with something easy: JW Player in SWFObject
mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)
if mobj is None:
diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py
@@ -1093,3 +1093,8 @@ def remove_start(s, start):
def url_basename(url):
path = compat_urlparse.urlparse(url).path
return path.strip(u'/').split(u'/')[-1]
+
+
+class HEADRequest(compat_urllib_request.Request):
+ def get_method(self):
+ return "HEAD"
