X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fcommon.py;h=ef02b68966e88d8d1cbc2f9d628e5a79fe8ce3c3;hb=7c360e3a04f09b912f51034c7778eb2297872e86;hp=02a82dc57cf5b0d07586d39614ae9f03acd81b5e;hpb=50317b111dadccba73bcdd828d9997d1da78a5f1;p=youtube-dl

diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py
index 02a82dc57..ef02b6896 100644
--- a/youtube_dl/extractor/common.py
+++ b/youtube_dl/extractor/common.py
@@ -66,14 +66,15 @@ class InfoExtractor(object):
                     * asr        Audio sampling rate in Hertz
                     * vbr        Average video bitrate in KBit/s
                     * vcodec     Name of the video codec in use
+                    * container  Name of the container format
                     * filesize   The number of bytes, if known in advance
                     * player_url SWF Player URL (used for rtmpdump).
                     * protocol   The protocol that will be used for the actual
                                  download, lower-case.
-                                 "http", "https", "rtsp", "rtmp" or so.
+                                 "http", "https", "rtsp", "rtmp", "m3u8" or so.
                     * preference Order number of this format. If this field is
                                  present and not None, the formats get sorted
-                                 by this field.
+                                 by this field, regardless of all other values.
                                  -1 for default (order by other properties),
                                  -2 or smaller for less than default.
                     * quality    Order number of the video quality of this
@@ -87,12 +88,18 @@ class InfoExtractor(object):
 
     The following fields are optional:
 
+    display_id      An alternative identifier for the video, not necessarily
+                    unique, but available before title. Typically, id is
+                    something like "4234987", title "Dancing naked mole rats",
+                    and display_id "dancing-naked-mole-rats"
     thumbnails:     A list of dictionaries (with the entries "resolution" and
                     "url") for the varying thumbnails
     thumbnail:      Full URL to a video thumbnail image.
     description:    One-line video description.
     uploader:       Full name of the video uploader.
+    timestamp:      UNIX timestamp of the moment the video became available.
     upload_date:    Video upload date (YYYYMMDD).
+                    If not explicitly set, calculated from timestamp.
     uploader_id:    Nickname or id of the video uploader.
     location:       Physical location of the video.
     subtitles:      The subtitle file contents as a dictionary in the format
@@ -113,9 +120,6 @@ class InfoExtractor(object):
     _real_extract() methods and define a _VALID_URL regexp.
     Probably, they should also be added to the list of extractors.
 
-    _real_extract() must return a *list* of information dictionaries as
-    described above.
-
     Finally, the _WORKING attribute should be set to False for broken IEs
     in order to warn the users and skip the tests.
     """
@@ -239,7 +243,7 @@ class InfoExtractor(object):
             except AttributeError:
                 url = url_or_request
             if len(url) > 200:
-                h = u'___' + hashlib.md5(url).hexdigest()
+                h = u'___' + hashlib.md5(url.encode('utf-8')).hexdigest()
                 url = url[:200 - len(h)] + h
             raw_filename = ('%s_%s.dump' % (video_id, url))
             filename = sanitize_filename(raw_filename, restricted=True)
@@ -247,7 +251,21 @@ class InfoExtractor(object):
             with open(filename, 'wb') as outf:
                 outf.write(webpage_bytes)
 
-        content = webpage_bytes.decode(encoding, 'replace')
+        try:
+            content = webpage_bytes.decode(encoding, 'replace')
+        except LookupError:
+            content = webpage_bytes.decode('utf-8', 'replace')
+
+        if (u'<title>Access to this site is blocked</title>' in content and
+                u'Websense' in content[:512]):
+            msg = u'Access to this webpage has been blocked by Websense filtering software in your network.'
+            blocked_iframe = self._html_search_regex(
+                r'<iframe src="([^"]+)"', content,
+                u'Websense information URL', default=None)
+            if blocked_iframe:
+                msg += u' Visit %s for more details' % blocked_iframe
+            raise ExtractorError(msg, expected=True)
+
         return (content, urlh)
 
     def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True):
@@ -261,17 +279,23 @@ class InfoExtractor(object):
 
     def _download_xml(self, url_or_request, video_id,
                       note=u'Downloading XML', errnote=u'Unable to download XML',
-                      transform_source=None):
+                      transform_source=None, fatal=True):
         """Return the xml as an xml.etree.ElementTree.Element"""
-        xml_string = self._download_webpage(url_or_request, video_id, note, errnote)
+        xml_string = self._download_webpage(
+            url_or_request, video_id, note, errnote, fatal=fatal)
+        if xml_string is False:
+            return xml_string
         if transform_source:
             xml_string = transform_source(xml_string)
         return xml.etree.ElementTree.fromstring(xml_string.encode('utf-8'))
 
     def _download_json(self, url_or_request, video_id,
                        note=u'Downloading JSON metadata',
-                       errnote=u'Unable to download JSON metadata'):
+                       errnote=u'Unable to download JSON metadata',
+                       transform_source=None):
         json_string = self._download_webpage(url_or_request, video_id, note, errnote)
+        if transform_source:
+            json_string = transform_source(json_string)
         try:
             return json.loads(json_string)
         except ValueError as ve:
@@ -398,7 +422,7 @@ class InfoExtractor(object):
     # Helper functions for extracting OpenGraph info
     @staticmethod
     def _og_regexes(prop):
-        content_re = r'content=(?:"([^>]+?)"|\'(.+?)\')'
+        content_re = r'content=(?:"([^>]+?)"|\'([^>]+?)\')'
         property_re = r'(?:name|property)=[\'"]og:%s[\'"]' % re.escape(prop)
         template = r'<meta[^>]+?%s[^>]+?%s'
         return [
@@ -428,14 +452,14 @@ class InfoExtractor(object):
         if secure: regexes = self._og_regexes('video:secure_url') + regexes
         return self._html_search_regex(regexes, html, name, **kargs)
 
-    def _html_search_meta(self, name, html, display_name=None):
+    def _html_search_meta(self, name, html, display_name=None, fatal=False):
         if display_name is None:
             display_name = name
         return self._html_search_regex(
             r'''(?ix)<meta
                     (?=[^>]+(?:itemprop|name|property)=["\']%s["\'])
                     [^>]+content=["\']([^"\']+)["\']''' % re.escape(name),
-            html, display_name, fatal=False)
+            html, display_name, fatal=fatal)
 
     def _dc_search_uploader(self, html):
         return self._html_search_meta('dc.creator', html, 'uploader')
@@ -464,7 +488,14 @@ class InfoExtractor(object):
         }
         return RATING_TABLE.get(rating.lower(), None)
 
+    def _twitter_search_player(self, html):
+        return self._html_search_meta('twitter:player', html,
+            'twitter card player')
+
     def _sort_formats(self, formats):
+        if not formats:
+            raise ExtractorError(u'No video formats found')
+
         def _formats_key(f):
             # TODO remove the following workaround
             from ..utils import determine_ext