X-Git-Url: http://git.cielonegro.org/gitweb.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fcommon.py;h=4782326826670ba7d7f24abcf46970cf2f821a98;hb=e72c7e41238681338c92427f6731c74947645308;hp=2277ec6ab1ddf3a3e345045104e9870488bc39d4;hpb=69f491f14e132a54e8ca7de291183dced64d461d;p=youtube-dl.git
diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py
index 2277ec6ab..478232682 100644
--- a/youtube_dl/extractor/common.py
+++ b/youtube_dl/extractor/common.py
@@ -14,6 +14,7 @@ import xml.etree.ElementTree
from ..compat import (
compat_cookiejar,
+ compat_HTTPError,
compat_http_client,
compat_urllib_error,
compat_urllib_parse_urlparse,
@@ -21,10 +22,12 @@ from ..compat import (
compat_str,
)
from ..utils import (
+ age_restricted,
clean_html,
compiled_regex_type,
ExtractorError,
float_or_none,
+ HEADRequest,
int_or_none,
RegexNotFoundError,
sanitize_filename,
@@ -40,7 +43,7 @@ class InfoExtractor(object):
information about the video (or videos) the URL refers to. This
information includes the real video URL, the video title, author and
others. The information is stored in a dictionary which is then
- passed to the FileDownloader. The FileDownloader processes this
+ passed to the YoutubeDL. The YoutubeDL processes this
information possibly downloading the video to the file system, among
other possible outcomes.
@@ -92,6 +95,8 @@ class InfoExtractor(object):
by this field, regardless of all other values.
-1 for default (order by other properties),
-2 or smaller for less than default.
+ < -1000 to hide the format (if there is
+ another one which is strictly better)
* language_preference Is this in the correct requested
language?
10 if it's what the URL is about,
@@ -105,12 +110,17 @@ class InfoExtractor(object):
(quality takes higher priority)
-1 for default (order by other properties),
-2 or smaller for less than default.
- * http_referer HTTP Referer header value to set.
* http_method HTTP method to use for the download.
* http_headers A dictionary of additional HTTP headers
to add to the request.
* http_post_data Additional data to send with a POST
request.
+ * stretched_ratio If given and not 1, indicates that the
+ video's pixels are not square.
+ width : height ratio as float.
+ * no_resume The server does not support resuming the
+ (HTTP or RTMP) download. Boolean.
+
url: Final video URL.
ext: Video filename extension.
format: The video format, defaults to ext (used for --get-format)
@@ -118,18 +128,21 @@ class InfoExtractor(object):
The following fields are optional:
+ alt_title: A secondary title of the video.
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 following entries:
+ * "id" (optional, string) - Thumbnail format ID
* "url"
+ * "preference" (optional, int) - quality of the image
* "width" (optional, int)
* "height" (optional, int)
* "resolution" (optional, string "{width}x{height"},
deprecated)
thumbnail: Full URL to a video thumbnail image.
- description: One-line video description.
+ description: Full 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).
@@ -143,6 +156,17 @@ class InfoExtractor(object):
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
+ comments: A list of comments, each with one or more of the following
+ properties (all but one of text or html optional):
+ * "author" - human-readable name of the comment author
+ * "author_id" - user ID of the comment author
+ * "id" - Comment ID
+ * "html" - Comment as HTML
+ * "text" - Plain text of the comment
+ * "timestamp" - UNIX timestamp of comment
+ * "parent" - ID of the comment this one is replying to.
+ 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
should allow to get the same result again. (It will be set
@@ -361,9 +385,19 @@ class InfoExtractor(object):
return content
- def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True):
+ def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, tries=1, timeout=5):
""" Returns the data of the page as a string """
- res = self._download_webpage_handle(url_or_request, video_id, note, errnote, fatal)
+ success = False
+ try_count = 0
+ while success is False:
+ try:
+ res = self._download_webpage_handle(url_or_request, video_id, note, errnote, fatal)
+ success = True
+ except compat_http_client.IncompleteRead as e:
+ try_count += 1
+ if try_count >= tries:
+ raise e
+ self._sleep(timeout, video_id)
if res is False:
return res
else:
@@ -391,6 +425,10 @@ class InfoExtractor(object):
url_or_request, video_id, note, errnote, fatal=fatal)
if (not fatal) and json_string is False:
return None
+ return self._parse_json(
+ json_string, video_id, transform_source=transform_source, fatal=fatal)
+
+ def _parse_json(self, json_string, video_id, transform_source=None, fatal=True):
if transform_source:
json_string = transform_source(json_string)
try:
@@ -584,9 +622,9 @@ class InfoExtractor(object):
if display_name is None:
display_name = name
return self._html_search_regex(
- r'''(?ix)]+(?:itemprop|name|property)=(["\']?)%s\1)
- [^>]+content=(["\'])(?P.*?)\1''' % re.escape(name),
+ [^>]+?content=(["\'])(?P.*?)\2''' % re.escape(name),
html, display_name, fatal=fatal, group='content', **kwargs)
def _dc_search_uploader(self, html):
@@ -680,6 +718,27 @@ class InfoExtractor(object):
)
formats.sort(key=_formats_key)
+ def _check_formats(self, formats, video_id):
+ if formats:
+ formats[:] = filter(
+ lambda f: self._is_valid_url(
+ f['url'], video_id,
+ item='%s video format' % f.get('format_id') if f.get('format_id') else 'video'),
+ formats)
+
+ def _is_valid_url(self, url, video_id, item='video'):
+ try:
+ self._request_webpage(
+ HEADRequest(url), video_id,
+ 'Checking %s URL' % item)
+ return True
+ except ExtractorError as e:
+ if isinstance(e.cause, compat_HTTPError):
+ self.report_warning(
+ '%s URL is invalid, skipping' % item, video_id)
+ return False
+ raise
+
def http_scheme(self):
""" Either "http:" or "https:", depending on the user's preferences """
return (
@@ -710,8 +769,14 @@ class InfoExtractor(object):
'Unable to download f4m manifest')
formats = []
+ manifest_version = '1.0'
media_nodes = manifest.findall('{http://ns.adobe.com/f4m/1.0}media')
+ if not media_nodes:
+ manifest_version = '2.0'
+ media_nodes = manifest.findall('{http://ns.adobe.com/f4m/2.0}media')
for i, media_el in enumerate(media_nodes):
+ if manifest_version == '2.0':
+ manifest_url = '/'.join(manifest_url.split('/')[:-1]) + '/' + media_el.attrib.get('href')
tbr = int_or_none(media_el.attrib.get('bitrate'))
format_id = 'f4m-%d' % (i if tbr is None else tbr)
formats.append({
@@ -870,6 +935,35 @@ class InfoExtractor(object):
None, '/', True, False, expire_time, '', None, None, None)
self._downloader.cookiejar.set_cookie(cookie)
+ def get_testcases(self, include_onlymatching=False):
+ t = getattr(self, '_TEST', None)
+ if t:
+ assert not hasattr(self, '_TESTS'), \
+ '%s has _TEST and _TESTS' % type(self).__name__
+ tests = [t]
+ else:
+ tests = getattr(self, '_TESTS', [])
+ for t in tests:
+ if not include_onlymatching and t.get('only_matching', False):
+ continue
+ t['name'] = type(self).__name__[:-len('IE')]
+ yield t
+
+ def is_suitable(self, age_limit):
+ """ Test whether the extractor is generally suitable for the given
+ age limit (i.e. pornographic sites are not, all others usually are) """
+
+ any_restricted = False
+ for tc in self.get_testcases(include_onlymatching=False):
+ if 'playlist' in tc:
+ tc = tc['playlist'][0]
+ is_restricted = age_restricted(
+ tc.get('info_dict', {}).get('age_limit'), age_limit)
+ if not is_restricted:
+ return True
+ any_restricted = any_restricted or is_restricted
+ return not any_restricted
+
class SearchInfoExtractor(InfoExtractor):
"""