release 2014.08.24.5

youtube_dl/extractor/__init__.py

@@ -88,6 +88,7 @@ from .engadget import EngadgetIE
 from .escapist import EscapistIE
 from .everyonesmixtape import EveryonesMixtapeIE
 from .exfm import ExfmIE
+from .expotv import ExpoTVIE
 from .extremetube import ExtremeTubeIE
 from .facebook import FacebookIE
 from .faz import FazIE

youtube_dl/extractor/expotv.py

@@ -0,0 +1,73 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    unified_strdate,
+)
+
+
+class ExpoTVIE(InfoExtractor):
+    _VALID_URL = r'https?://www\.expotv\.com/videos/[^?#]*/(?P<id>[0-9]+)($|[?#])'
+    _TEST = {
+        'url': 'http://www.expotv.com/videos/reviews/1/24/LinneCardscom/17561',
+        'md5': '2985e6d7a392b2f7a05e0ca350fe41d0',
+        'info_dict': {
+            'id': '17561',
+            'ext': 'mp4',
+            'upload_date': '20060212',
+            'title': 'My Favorite Online Scrapbook Store',
+            'view_count': int,
+            'description': 'You\'ll find most everything you need at this virtual store front.',
+            'uploader': 'Anna T.',
+            'thumbnail': 're:^https?://.*\.jpg$',
+        }
+    }
+
+    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_key = self._search_regex(
+            r'<param name="playerKey" value="([^"]+)"', webpage, 'player key')
+        config_url = 'http://client.expotv.com/video/config/%s/%s' % (
+            video_id, player_key)
+        config = self._download_json(
+            config_url, video_id,
+            note='Downloading video configuration')
+
+        formats = [{
+            'url': fcfg['file'],
+            'height': int_or_none(fcfg.get('height')),
+            'format_note': fcfg.get('label'),
+            'ext': self._search_regex(
+                r'filename=.*\.([a-z0-9_A-Z]+)&', fcfg['file'],
+                'file extension', default=None),
+        } for fcfg in config['sources']]
+        self._sort_formats(formats)
+
+        title = self._og_search_title(webpage)
+        description = self._og_search_description(webpage)
+        thumbnail = config.get('image')
+        view_count = int_or_none(self._search_regex(
+            r'<h5>Plays: ([0-9]+)</h5>', webpage, 'view counts'))
+        uploader = self._search_regex(
+            r'<div class="reviewer">\s*<img alt="([^"]+)"', webpage, 'uploader',
+            fatal=False)
+        upload_date = unified_strdate(self._search_regex(
+            r'<h5>Reviewed on ([0-9/.]+)</h5>', webpage, 'upload date',
+            fatal=False))
+
+        return {
+            'id': video_id,
+            'formats': formats,
+            'title': title,
+            'description': description,
+            'view_count': view_count,
+            'thumbnail': thumbnail,
+            'uploader': uploader,
+            'upload_date': upload_date,
+        }

youtube_dl/extractor/generic.py

@@ -331,6 +331,18 @@ class GenericIE(InfoExtractor):
             'info_dict': {
                 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
             }
+        },
+        # Flowplayer
+        {
+            'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
+            'md5': '9d65602bf31c6e20014319c7d07fba27',
+            'info_dict': {
+                'id': '5123ea6d5e5a7',
+                'ext': 'mp4',
+                'age_limit': 18,
+                'uploader': 'www.handjobhub.com',
+                'title': 'Busty Blonde Siri Tit Fuck While Wank at Handjob Hub',
+            }
         }
     ]
 
@@ -344,58 +356,6 @@ class GenericIE(InfoExtractor):
         """Report information extraction."""
         self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
 
-    def _send_head(self, url):
-        """Check if it is a redirect, like url shorteners, in case return the new url."""
-
-        class HEADRedirectHandler(compat_urllib_request.HTTPRedirectHandler):
-            """
-            Subclass the HTTPRedirectHandler to make it use our
-            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"))
-                    try:
-                        # This function was deprecated in python 3.3 and removed in 3.4
-                        origin_req_host = req.get_origin_req_host()
-                    except AttributeError:
-                        origin_req_host = req.origin_req_host
-                    return HEADRequest(newurl,
-                                       headers=newheaders,
-                                       origin_req_host=origin_req_host,
-                                       unverifiable=True)
-                else:
-                    raise compat_urllib_error.HTTPError(req.get_full_url(), code, msg, headers, fp)
-
-        class HTTPMethodFallback(compat_urllib_request.BaseHandler):
-            """
-            Fallback to GET if HEAD is not allowed (405 HTTP error)
-            """
-            def http_error_405(self, req, fp, code, msg, headers):
-                fp.read()
-                fp.close()
-
-                newheaders = dict((k,v) for k,v in req.headers.items()
-                                  if k.lower() not in ("content-length", "content-type"))
-                return self.parent.open(compat_urllib_request.Request(req.get_full_url(),
-                                                 headers=newheaders,
-                                                 origin_req_host=req.get_origin_req_host(),
-                                                 unverifiable=True))
-
-        # Build our opener
-        opener = compat_urllib_request.OpenerDirector()
-        for handler in [compat_urllib_request.HTTPHandler, compat_urllib_request.HTTPDefaultErrorHandler,
-                        HTTPMethodFallback, HEADRedirectHandler,
-                        compat_urllib_request.HTTPErrorProcessor, compat_urllib_request.HTTPSHandler]:
-            opener.add_handler(handler())
-
-        response = opener.open(HEADRequest(url))
-        if response is None:
-            raise ExtractorError('Invalid URL protocol')
-        return response
-
     def _extract_rss(self, url, video_id, doc):
         playlist_title = doc.find('./channel/title').text
         playlist_desc_el = doc.find('./channel/description')
@@ -499,9 +459,13 @@ class GenericIE(InfoExtractor):
 
         self.to_screen('%s: Requesting header' % video_id)
 
-        try:
-            response = self._send_head(url)
+        head_req = HEADRequest(url)
+        response = self._request_webpage(
+            head_req, video_id,
+            note=False, errnote='Could not send HEAD request to %s' % url,
+            fatal=False)
 
+        if response is not False:
             # Check for redirect
             new_url = response.geturl()
             if url != new_url:
@@ -529,10 +493,6 @@ class GenericIE(InfoExtractor):
                     'upload_date': upload_date,
                 }
 
-        except compat_urllib_error.HTTPError:
-            # This may be a stupid server that doesn't like HEAD, our UA, or so
-            pass
-
         try:
             webpage = self._download_webpage(url, video_id)
         except ValueError:
@@ -570,6 +530,16 @@ class GenericIE(InfoExtractor):
             r'(?s)<title>(.*?)</title>', webpage, 'video title',
             default='video')
 
+        # Try to detect age limit automatically
+        age_limit = self._rta_search(webpage)
+        # And then there are the jokers who advertise that they use RTA,
+        # but actually don't.
+        AGE_LIMIT_MARKERS = [
+            r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
+        ]
+        if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
+            age_limit = 18
+
         # video uploader is domain name
         video_uploader = self._search_regex(
             r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
@@ -833,6 +803,15 @@ class GenericIE(InfoExtractor):
         if not found:
             # Broaden the findall a little bit: JWPlayer JS loader
             found = re.findall(r'[^A-Za-z0-9]?file["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage)
+        if not found:
+            # Flow player
+            found = re.findall(r'''(?xs)
+                flowplayer\("[^"]+",\s*
+                    \{[^}]+?\}\s*,
+                    \s*{[^}]+? ["']?clip["']?\s*:\s*\{\s*
+                        ["']?url["']?\s*:\s*["']([^"']+)["']
+            ''', webpage)
+            assert found
         if not found:
             # Try to find twitter cards info
             found = re.findall(r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage)
@@ -884,6 +863,7 @@ class GenericIE(InfoExtractor):
                 'url': video_url,
                 'uploader': video_uploader,
                 'title': video_title,
+                'age_limit': age_limit,
             })
 
         if len(entries) == 1:

youtube_dl/extractor/pornotube.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
@@ -9,15 +11,16 @@ from ..utils import (
 
 
 class PornotubeIE(InfoExtractor):
-    _VALID_URL = r'^(?:https?://)?(?:\w+\.)?pornotube\.com(/c/(?P<channel>[0-9]+))?(/m/(?P<videoid>[0-9]+))(/(?P<title>.+))$'
+    _VALID_URL = r'https?://(?:\w+\.)?pornotube\.com(/c/(?P<channel>[0-9]+))?(/m/(?P<videoid>[0-9]+))(/(?P<title>.+))$'
     _TEST = {
-        u'url': u'http://pornotube.com/c/173/m/1689755/Marilyn-Monroe-Bathing',
-        u'file': u'1689755.flv',
-        u'md5': u'374dd6dcedd24234453b295209aa69b6',
-        u'info_dict': {
-            u"upload_date": u"20090708", 
-            u"title": u"Marilyn-Monroe-Bathing",
-            u"age_limit": 18
+        'url': 'http://pornotube.com/c/173/m/1689755/Marilyn-Monroe-Bathing',
+        'md5': '374dd6dcedd24234453b295209aa69b6',
+        'info_dict': {
+            'id': '1689755',
+            'ext': 'flv',
+            'upload_date': '20090708',
+            'title': 'Marilyn-Monroe-Bathing',
+            'age_limit': 18
         }
     }
 
@@ -32,22 +35,22 @@ class PornotubeIE(InfoExtractor):
 
         # Get the video URL
         VIDEO_URL_RE = r'url: "(?P<url>http://video[0-9].pornotube.com/.+\.flv)",'
-        video_url = self._search_regex(VIDEO_URL_RE, webpage, u'video url')
+        video_url = self._search_regex(VIDEO_URL_RE, webpage, 'video url')
         video_url = compat_urllib_parse.unquote(video_url)
 
         #Get the uploaded date
         VIDEO_UPLOADED_RE = r'<div class="video_added_by">Added (?P<date>[0-9\/]+) by'
-        upload_date = self._html_search_regex(VIDEO_UPLOADED_RE, webpage, u'upload date', fatal=False)
-        if upload_date: upload_date = unified_strdate(upload_date)
+        upload_date = self._html_search_regex(VIDEO_UPLOADED_RE, webpage, 'upload date', fatal=False)
+        if upload_date:
+            upload_date = unified_strdate(upload_date)
         age_limit = self._rta_search(webpage)
 
-        info = {'id': video_id,
-                'url': video_url,
-                'uploader': None,
-                'upload_date': upload_date,
-                'title': video_title,
-                'ext': 'flv',
-                'format': 'flv',
-                'age_limit': age_limit}
-
-        return [info]
+        return {
+            'id': video_id,
+            'url': video_url,
+            'upload_date': upload_date,
+            'title': video_title,
+            'ext': 'flv',
+            'format': 'flv',
+            'age_limit': age_limit,
+        }

youtube_dl/utils.py

@@ -855,6 +855,7 @@ def unified_strdate(date_str):
         '%Y/%m/%d',
         '%d.%m.%Y',
         '%d/%m/%Y',
+        '%d/%m/%y',
         '%Y/%m/%d %H:%M:%S',
         '%Y-%m-%d %H:%M:%S',
         '%d.%m.%Y %H:%M',

youtube_dl/version.py

@@ -1,2 +1,2 @@
 
-__version__ = '2014.08.24.2'
+__version__ = '2014.08.24.5'