X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fcommon.py;h=534908a2b89af8db08f5d7ba0fc7f983c1199fa9;hb=1d87e3a1c64e3183d17a6dc6fbc4353a86aa5f99;hp=e0ccba533534709b6ce65af518ca16fadee0c4ea;hpb=9103bbc5cd11957de2e906e4401dcf4df9511d28;p=youtube-dl diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index e0ccba533..534908a2b 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -4,11 +4,11 @@ import re import socket import sys import netrc +import xml.etree.ElementTree from ..utils import ( compat_http_client, compat_urllib_error, - compat_urllib_request, compat_str, clean_html, @@ -19,6 +19,7 @@ from ..utils import ( unescapeHTML, ) + class InfoExtractor(object): """Information Extractor class. @@ -54,6 +55,9 @@ class InfoExtractor(object): 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. + like_count: Number of positive ratings of the video + dislike_count: Number of negative ratings of the video + comment_count: Number of comments on the video urlhandle: [internal] The urlHandle to be used to download the file, like returned by urllib.request.urlopen age_limit: Age restriction for the video, as an integer (years) @@ -71,6 +75,11 @@ class InfoExtractor(object): ("3D" or "DASH video") * width Width of the video, if known * height Height of the video, if known + * abr Average audio bitrate in KBit/s + * acodec Name of the audio codec in use + * vbr Average video bitrate in KBit/s + * vcodec Name of the video codec in use + * filesize The number of bytes, if known in advance 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) @@ -145,27 +154,38 @@ class InfoExtractor(object): def IE_NAME(self): return type(self).__name__[:-2] - def _request_webpage(self, url_or_request, video_id, note=None, errnote=None): + def _request_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True): """ Returns the response handle """ if note is None: self.report_download_webpage(video_id) elif note is not False: - self.to_screen(u'%s: %s' % (video_id, note)) + if video_id is None: + self.to_screen(u'%s' % (note,)) + else: + self.to_screen(u'%s: %s' % (video_id, note)) try: - return compat_urllib_request.urlopen(url_or_request) + return self._downloader.urlopen(url_or_request) 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], cause=err) + errmsg = u'%s: %s' % (errnote, compat_str(err)) + if fatal: + raise ExtractorError(errmsg, sys.exc_info()[2], cause=err) + else: + self._downloader.report_warning(errmsg) + return False - def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None): + def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None, fatal=True): """ 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) + urlh = self._request_webpage(url_or_request, video_id, note, errnote, fatal) + if urlh is False: + assert not fatal + return False 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) @@ -200,9 +220,20 @@ class InfoExtractor(object): content = webpage_bytes.decode(encoding, 'replace') return (content, urlh) - def _download_webpage(self, url_or_request, video_id, note=None, errnote=None): + def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True): """ Returns the data of the page as a string """ - return self._download_webpage_handle(url_or_request, video_id, note, errnote)[0] + res = self._download_webpage_handle(url_or_request, video_id, note, errnote, fatal) + if res is False: + return res + else: + content, _ = res + return content + + def _download_xml(self, url_or_request, video_id, + note=u'Downloading XML', errnote=u'Unable to download XML'): + """Return the xml as an xml.etree.ElementTree.Element""" + xml_string = self._download_webpage(url_or_request, video_id, note, errnote) + return xml.etree.ElementTree.fromstring(xml_string.encode('utf-8')) def to_screen(self, msg): """Print msg to screen, prefixing it with '[ie_name]'""" @@ -225,12 +256,14 @@ class InfoExtractor(object): self.to_screen(u'Logging in') #Methods for following #608 - def url_result(self, url, ie=None): + def url_result(self, url, ie=None, video_id=None): """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, 'ie_key': ie} + if video_id is not None: + video_info['id'] = video_id return video_info def playlist_result(self, entries, playlist_id=None, playlist_title=None): """Returns a playlist""" @@ -315,13 +348,21 @@ class InfoExtractor(object): # Helper functions for extracting OpenGraph info @staticmethod - def _og_regex(prop): - return r']+?)"|\'(.+?)\')' + property_re = r'property=[\'"]og:%s[\'"]' % re.escape(prop) + template = r']+?%s[^>]+?%s' + return [ + template % (property_re, content_re), + template % (content_re, property_re), + ] 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) + escaped = self._search_regex(self._og_regexes(prop), html, name, flags=re.DOTALL, **kargs) + if escaped is None: + return None return unescapeHTML(escaped) def _og_search_thumbnail(self, html, **kargs): @@ -334,10 +375,22 @@ class InfoExtractor(object): 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')) + regexes = self._og_regexes('video') + 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): + if display_name is None: + display_name = name + return self._html_search_regex( + r'''(?ix)]+(?:itemprop|name|property)=["\']%s["\']) + [^>]+content=["\']([^"\']+)["\']''' % re.escape(name), + html, display_name, fatal=False) + + def _dc_search_uploader(self, html): + return self._html_search_meta('dc.creator', html, 'uploader') + def _rta_search(self, html): # See http://www.rtalabel.org/index.php?content=howtofaq#single if re.search(r'(?ix)