[extractor/common] do not process f4m manifest that contain akamai playerVerification...

[youtube-dl] / youtube_dl / extractor / common.py

diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py
index b9014fc23e53eaf335d65ee56c3db560d218d642..e3d1dd076364261dcd2e8860f281a48dfc2b39cc 100644 (file)
--- a/youtube_dl/extractor/common.py
+++ b/youtube_dl/extractor/common.py
@@ -14,10 +14,12 @@ import xml.etree.ElementTree
 
 from ..compat import (
     compat_cookiejar,
+    compat_cookies,
     compat_HTTPError,
     compat_http_client,
     compat_urllib_error,
     compat_urllib_parse_urlparse,
+    compat_urllib_request,
     compat_urlparse,
     compat_str,
 )
@@ -65,7 +67,7 @@ class InfoExtractor(object):
 
                     Potential fields:
                     * url        Mandatory. The URL of the video file
-                    * ext        Will be calculated from url if missing
+                    * ext        Will be calculated from URL if missing
                     * format     A human-readable description of the format
                                  ("mp4 container with h264/opus").
                                  Calculated from the format_id, width, height.
@@ -155,7 +157,7 @@ class InfoExtractor(object):
                     lower to higher preference, each element is a dictionary
                     with the "ext" entry and one of:
                         * "data": The subtitles file contents
-                        * "url": A url pointing to the subtitles file
+                        * "url": A URL pointing to the subtitles file
     automatic_captions: Like 'subtitles', used by the YoutubeIE for
                     automatically generated captions
     duration:       Length of the video in seconds, as an integer.
@@ -176,13 +178,18 @@ class InfoExtractor(object):
                                      Set to "root" to indicate that this is a
                                      comment to the original video.
     age_limit:      Age restriction for the video, as an integer (years)
-    webpage_url:    The url to the video webpage, if given to youtube-dl it
+    webpage_url:    The URL to the video webpage, if given to youtube-dl it
                     should allow to get the same result again. (It will be set
                     by YoutubeDL if it's missing)
     categories:     A list of categories that the video falls in, for example
                     ["Sports", "Berlin"]
+    tags:           A list of tags assigned to the video, e.g. ["sweden", "pop music"]
     is_live:        True, False, or None (=unknown). Whether this video is a
                     live stream that goes on instead of a fixed-length video.
+    start_time:     Time in seconds where the reproduction should start, as
+                    specified in the URL.
+    end_time:       Time in seconds where the reproduction should end, as
+                    specified in the URL.
 
     Unless mentioned otherwise, the fields should be Unicode strings.
 
@@ -501,7 +508,7 @@ class InfoExtractor(object):
     # Methods for following #608
     @staticmethod
     def url_result(url, ie=None, video_id=None, video_title=None):
-        """Returns a url that points to a page that should be processed"""
+        """Returns a URL that points to a page that should be processed"""
         # TODO: ie should be the class used for getting the info
         video_info = {'_type': 'url',
                       'url': url,
@@ -626,6 +633,12 @@ class InfoExtractor(object):
             template % (content_re, property_re),
         ]
 
+    @staticmethod
+    def _meta_regex(prop):
+        return r'''(?isx)<meta
+                    (?=[^>]+(?:itemprop|name|property)=(["\']?)%s\1)
+                    [^>]+?content=(["\'])(?P<content>.*?)\2''' % re.escape(prop)
+
     def _og_search_property(self, prop, html, name=None, **kargs):
         if name is None:
             name = 'OpenGraph %s' % prop
@@ -635,7 +648,7 @@ class InfoExtractor(object):
         return unescapeHTML(escaped)
 
     def _og_search_thumbnail(self, html, **kargs):
-        return self._og_search_property('image', html, 'thumbnail url', fatal=False, **kargs)
+        return self._og_search_property('image', html, 'thumbnail URL', fatal=False, **kargs)
 
     def _og_search_description(self, html, **kargs):
         return self._og_search_property('description', html, fatal=False, **kargs)
@@ -656,9 +669,7 @@ class InfoExtractor(object):
         if display_name is None:
             display_name = name
         return self._html_search_regex(
-            r'''(?isx)<meta
-                    (?=[^>]+(?:itemprop|name|property)=(["\']?)%s\1)
-                    [^>]+?content=(["\'])(?P<content>.*?)\2''' % re.escape(name),
+            self._meta_regex(name),
             html, display_name, fatal=fatal, group='content', **kwargs)
 
     def _dc_search_uploader(self, html):
@@ -845,6 +856,13 @@ class InfoExtractor(object):
             # (see https://github.com/rg3/youtube-dl/issues/6215#issuecomment-121704244)
             transform_source=transform_source)
 
+        # currently youtube-dl cannot decode the playerVerificationChallenge as Akamai uses Adobe Alchemy
+        akamai_pv = manifest.find('{http://ns.adobe.com/f4m/1.0}pv-2.0')
+        if akamai_pv is not None and ';' in akamai_pv.text:
+            playerVerificationChallenge = akamai_pv.text.split(';')[0]
+            if playerVerificationChallenge.strip() != '':
+                return []
+
         formats = []
         manifest_version = '1.0'
         media_nodes = manifest.findall('{http://ns.adobe.com/f4m/1.0}media')
@@ -1065,6 +1083,12 @@ class InfoExtractor(object):
             None, '/', True, False, expire_time, '', None, None, None)
         self._downloader.cookiejar.set_cookie(cookie)
 
+    def _get_cookies(self, url):
+        """ Return a compat_cookies.SimpleCookie with the cookies for the url """
+        req = compat_urllib_request.Request(url)
+        self._downloader.cookiejar.add_cookie_header(req)
+        return compat_cookies.SimpleCookie(req.get_header('Cookie'))
+
     def get_testcases(self, include_onlymatching=False):
         t = getattr(self, '_TEST', None)
         if t:
@@ -1116,7 +1140,7 @@ class InfoExtractor(object):
 class SearchInfoExtractor(InfoExtractor):
     """
     Base class for paged search queries extractors.
-    They accept urls in the format _SEARCH_KEY(|all|[0-9]):{query}
+    They accept URLs in the format _SEARCH_KEY(|all|[0-9]):{query}
     Instances should define _SEARCH_KEY and _MAX_RESULTS.
     """