"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
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
_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.
"""
url = url_or_request.get_full_url()
except AttributeError:
url = url_or_request
- if len(url) > 200:
- h = u'___' + hashlib.md5(url.encode('utf-8')).hexdigest()
- url = url[:200 - len(h)] + h
- raw_filename = ('%s_%s.dump' % (video_id, url))
+ basen = video_id + '_' + url
+ if len(basen) > 240:
+ h = u'___' + hashlib.md5(basen.encode('utf-8')).hexdigest()
+ basen = basen[:240 - len(h)] + h
+ raw_filename = basen + '.dump'
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')
+ 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):
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:
# 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 [
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')
)
formats.sort(key=_formats_key)
+ def http_scheme(self):
+ """ Either "https:" or "https:", depending on the user's preferences """
+ return (
+ 'http:'
+ if self._downloader.params.get('prefer_insecure', False)
+ else 'https:')
+
+ def _proto_relative_url(self, url, scheme=None):
+ if url is None:
+ return url
+ if url.startswith('//'):
+ if scheme is None:
+ scheme = self.http_scheme()
+ return scheme + url
+ else:
+ return url
+
class SearchInfoExtractor(InfoExtractor):
"""
@property
def SEARCH_KEY(self):
return self._SEARCH_KEY
+
projects / youtube-dl / blobdiff