Update changelog.

[youtubedl] / youtube_dl / extractor / common.py

diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py
index 655836ff6efca2ef95e80631d528901d6ae28d46..fb2d50a098992f8088c41259b73d653c6f6f173d 100644 (file)
--- a/youtube_dl/extractor/common.py
+++ b/youtube_dl/extractor/common.py
@@ -3,6 +3,7 @@ import os
 import re
 import socket
 import sys
 import re
 import socket
 import sys

+import netrc

 
 from ..utils import (
     compat_http_client,
 
 from ..utils import (
     compat_http_client,


@@ -13,6 +14,9 @@ from ..utils import (
     clean_html,
     compiled_regex_type,
     ExtractorError,
     clean_html,
     compiled_regex_type,
     ExtractorError,

+    RegexNotFoundError,
+    sanitize_filename,
+    unescapeHTML,

 )
 
 class InfoExtractor(object):
 )
 
 class InfoExtractor(object):


@@ -33,9 +37,13 @@ class InfoExtractor(object):
     title:          Video title, unescaped.
     ext:            Video filename extension.
 
     title:          Video title, unescaped.
     ext:            Video filename extension.
 

+    Instead of url and ext, formats can also specified.
+

     The following fields are optional:
 
     format:         The video format, defaults to ext (used for --get-format)
     The following fields are optional:
 
     format:         The video format, defaults to ext (used for --get-format)

+    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.
     thumbnail:      Full URL to a video thumbnail image.
     description:    One-line video description.
     uploader:       Full name of the video uploader.


@@ -43,12 +51,31 @@ class InfoExtractor(object):
     uploader_id:    Nickname or id of the video uploader.
     location:       Physical location of the video.
     player_url:     SWF Player URL (used for rtmpdump).
     uploader_id:    Nickname or id of the video uploader.
     location:       Physical location of the video.
     player_url:     SWF Player URL (used for rtmpdump).

-    subtitles:      The subtitle file contents.
+    subtitles:      The subtitle file contents as a dictionary in the format
+                    {language: subtitles}.

     view_count:     How many users have watched the video on the platform.
     urlhandle:      [internal] The urlHandle to be used to download the file,
                     like returned by urllib.request.urlopen
     view_count:     How many users have watched the video on the platform.
     urlhandle:      [internal] The urlHandle to be used to download the file,
                     like returned by urllib.request.urlopen

-
-    The fields should all be Unicode strings.
+    age_limit:      Age restriction for the video, as an integer (years)
+    formats:        A list of dictionaries for each format available, it must
+                    be ordered from worst to best quality. Potential fields:
+                    * url       Mandatory. The URL of the video file
+                    * 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.
+                                and format_note fields if missing.
+                    * format_id A short description of the format
+                                ("mp4_h264_opus" or "19")
+                    * format_note Additional info about the format
+                                ("3D" or "DASH video")
+                    * width     Width of the video, if known
+                    * height    Height of the video, if known
+    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)
+
+    Unless mentioned otherwise, the fields should be Unicode strings.

 
     Subclasses of this one should re-define the _real_initialize() and
     _real_extract() methods and define a _VALID_URL regexp.
 
     Subclasses of this one should re-define the _real_initialize() and
     _real_extract() methods and define a _VALID_URL regexp.


@@ -73,7 +100,13 @@ class InfoExtractor(object):
     @classmethod
     def suitable(cls, url):
         """Receives a URL and returns True if suitable for this IE."""
     @classmethod
     def suitable(cls, url):
         """Receives a URL and returns True if suitable for this IE."""

-        return re.match(cls._VALID_URL, url) is not None
+
+        # This does not use has/getattr intentionally - we want to know whether
+        # we have cached the regexp for *this* class, whereas getattr would also
+        # match the superclass
+        if '_VALID_URL_RE' not in cls.__dict__:
+            cls._VALID_URL_RE = re.compile(cls._VALID_URL)
+        return cls._VALID_URL_RE.match(url) is not None

 
     @classmethod
     def working(cls):
 
     @classmethod
     def working(cls):


@@ -103,6 +136,11 @@ class InfoExtractor(object):
         """Real extraction process. Redefine in subclasses."""
         pass
 
         """Real extraction process. Redefine in subclasses."""
         pass
 

+    @classmethod
+    def ie_key(cls):
+        """A string for getting the InfoExtractor with get_info_extractor"""
+        return cls.__name__[:-2]
+

     @property
     def IE_NAME(self):
         return type(self).__name__[:-2]
     @property
     def IE_NAME(self):
         return type(self).__name__[:-2]


@@ -118,18 +156,28 @@ class InfoExtractor(object):
         except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
             if errnote is None:
                 errnote = u'Unable to download webpage'
         except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
             if errnote is None:
                 errnote = u'Unable to download webpage'

-            raise ExtractorError(u'%s: %s' % (errnote, compat_str(err)), sys.exc_info()[2])
+            raise ExtractorError(u'%s: %s' % (errnote, compat_str(err)), sys.exc_info()[2], cause=err)

 
     def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None):
         """ Returns a tuple (page content as string, URL handle) """
 
     def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None):
         """ Returns a tuple (page content as string, URL handle) """

+
+        # Strip hashes from the URL (#1038)
+        if isinstance(url_or_request, (compat_str, str)):
+            url_or_request = url_or_request.partition('#')[0]
+

         urlh = self._request_webpage(url_or_request, video_id, note, errnote)
         content_type = urlh.headers.get('Content-Type', '')
         urlh = self._request_webpage(url_or_request, video_id, note, errnote)
         content_type = urlh.headers.get('Content-Type', '')

+        webpage_bytes = urlh.read()

         m = re.match(r'[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+\s*;\s*charset=(.+)', content_type)
         if m:
             encoding = m.group(1)
         else:
         m = re.match(r'[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+\s*;\s*charset=(.+)', content_type)
         if m:
             encoding = m.group(1)
         else:

-            encoding = 'utf-8'
-        webpage_bytes = urlh.read()
+            m = re.search(br'<meta[^>]+charset=[\'"]?([^\'")]+)[ /\'">]',
+                          webpage_bytes[:1024])
+            if m:
+                encoding = m.group(1).decode('ascii')
+            else:
+                encoding = 'utf-8'

         if self._downloader.params.get('dump_intermediate_pages', False):
             try:
                 url = url_or_request.get_full_url()
         if self._downloader.params.get('dump_intermediate_pages', False):
             try:
                 url = url_or_request.get_full_url()


@@ -138,6 +186,17 @@ class InfoExtractor(object):
             self.to_screen(u'Dumping request to ' + url)
             dump = base64.b64encode(webpage_bytes).decode('ascii')
             self._downloader.to_screen(dump)
             self.to_screen(u'Dumping request to ' + url)
             dump = base64.b64encode(webpage_bytes).decode('ascii')
             self._downloader.to_screen(dump)

+        if self._downloader.params.get('write_pages', False):
+            try:
+                url = url_or_request.get_full_url()
+            except AttributeError:
+                url = url_or_request
+            raw_filename = ('%s_%s.dump' % (video_id, url))
+            filename = sanitize_filename(raw_filename, restricted=True)
+            self.to_screen(u'Saving request to ' + filename)
+            with open(filename, 'wb') as outf:
+                outf.write(webpage_bytes)
+

         content = webpage_bytes.decode(encoding, 'replace')
         return (content, urlh)
 
         content = webpage_bytes.decode(encoding, 'replace')
         return (content, urlh)
 


@@ -161,12 +220,11 @@ class InfoExtractor(object):
         """Report attempt to confirm age."""
         self.to_screen(u'Confirming age')
 
         """Report attempt to confirm age."""
         self.to_screen(u'Confirming age')
 

+    def report_login(self):
+        """Report attempt to log in."""
+        self.to_screen(u'Logging in')
+

     #Methods for following #608
     #Methods for following #608

-    #They set the correct value of the '_type' key
-    def video_result(self, video_info):
-        """Returns a video"""
-        video_info['_type'] = 'video'
-        return video_info

     def url_result(self, url, ie=None):
         """Returns a url that points to a page that should be processed"""
         #TODO: ie should be the class used for getting the info
     def url_result(self, url, ie=None):
         """Returns a url that points to a page that should be processed"""
         #TODO: ie should be the class used for getting the info


@@ -189,7 +247,7 @@ class InfoExtractor(object):
         Perform a regex search on the given string, using a single or a list of
         patterns returning the first matching group.
         In case of failure return a default value or raise a WARNING or a
         Perform a regex search on the given string, using a single or a list of
         patterns returning the first matching group.
         In case of failure return a default value or raise a WARNING or a

-        ExtractorError, depending on fatal, specifying the field name.
+        RegexNotFoundError, depending on fatal, specifying the field name.

         """
         if isinstance(pattern, (str, compat_str, compiled_regex_type)):
             mobj = re.search(pattern, string, flags)
         """
         if isinstance(pattern, (str, compat_str, compiled_regex_type)):
             mobj = re.search(pattern, string, flags)


@@ -209,7 +267,7 @@ class InfoExtractor(object):
         elif default is not None:
             return default
         elif fatal:
         elif default is not None:
             return default
         elif fatal:

-            raise ExtractorError(u'Unable to extract %s' % _name)
+            raise RegexNotFoundError(u'Unable to extract %s' % _name)

         else:
             self._downloader.report_warning(u'unable to extract %s; '
                 u'please report this issue on http://yt-dl.org/bug' % _name)
         else:
             self._downloader.report_warning(u'unable to extract %s; '
                 u'please report this issue on http://yt-dl.org/bug' % _name)


@@ -225,6 +283,72 @@ class InfoExtractor(object):
         else:
             return res
 
         else:
             return res
 

+    def _get_login_info(self):
+        """
+        Get the the login info as (username, password)
+        It will look in the netrc file using the _NETRC_MACHINE value
+        If there's no info available, return (None, None)
+        """
+        if self._downloader is None:
+            return (None, None)
+
+        username = None
+        password = None
+        downloader_params = self._downloader.params
+
+        # Attempt to use provided username and password or .netrc data
+        if downloader_params.get('username', None) is not None:
+            username = downloader_params['username']
+            password = downloader_params['password']
+        elif downloader_params.get('usenetrc', False):
+            try:
+                info = netrc.netrc().authenticators(self._NETRC_MACHINE)
+                if info is not None:
+                    username = info[0]
+                    password = info[2]
+                else:
+                    raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
+            except (IOError, netrc.NetrcParseError) as err:
+                self._downloader.report_warning(u'parsing .netrc: %s' % compat_str(err))
+        
+        return (username, password)
+
+    # Helper functions for extracting OpenGraph info
+    @staticmethod
+    def _og_regex(prop):
+        return r'<meta.+?property=[\'"]og:%s[\'"].+?content=(?:"(.+?)"|\'(.+?)\')' % re.escape(prop)
+
+    def _og_search_property(self, prop, html, name=None, **kargs):
+        if name is None:
+            name = 'OpenGraph %s' % prop
+        escaped = self._search_regex(self._og_regex(prop), html, name, flags=re.DOTALL, **kargs)
+        if not escaped is None:
+            return unescapeHTML(escaped)
+        return None
+
+    def _og_search_thumbnail(self, html, **kargs):
+        return self._og_search_property('image', html, u'thumbnail url', fatal=False, **kargs)
+
+    def _og_search_description(self, html, **kargs):
+        return self._og_search_property('description', html, fatal=False, **kargs)
+
+    def _og_search_title(self, html, **kargs):
+        return self._og_search_property('title', html, **kargs)
+
+    def _og_search_video_url(self, html, name='video url', secure=True, **kargs):
+        regexes = [self._og_regex('video')]
+        if secure: regexes.insert(0, self._og_regex('video:secure_url'))
+        return self._html_search_regex(regexes, html, name, **kargs)
+
+    def _rta_search(self, html):
+        # See http://www.rtalabel.org/index.php?content=howtofaq#single
+        if re.search(r'(?ix)<meta\s+name="rating"\s+'
+                     r'     content="RTA-5042-1996-1400-1577-RTA"',
+                     html):
+            return 18
+        return 0
+
+

 class SearchInfoExtractor(InfoExtractor):
     """
     Base class for paged search queries extractors.
 class SearchInfoExtractor(InfoExtractor):
     """
     Base class for paged search queries extractors.


@@ -262,7 +386,7 @@ class SearchInfoExtractor(InfoExtractor):
 
     def _get_n_results(self, query, n):
         """Get a specified number of results for a query"""
 
     def _get_n_results(self, query, n):
         """Get a specified number of results for a query"""

-        raise NotImplementedError("This method must be implemented by sublclasses")
+        raise NotImplementedError("This method must be implemented by subclasses")

 
     @property
     def SEARCH_KEY(self):
 
     @property
     def SEARCH_KEY(self):