X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fcommon.py;h=87fce9cd89425150baff91577199f706db2a1e81;hb=bfc993cc9183d5f001e30267551bcdf9f0a98be9;hp=d302fe45fdea0bc7556fdbda4f321d64d86c2c7c;hpb=2f15832f569834a37ac3ee6140a3b997407c04cd;p=youtube-dl
diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py
index d302fe45f..87fce9cd8 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,
@@ -21,6 +22,7 @@ from ..compat import (
compat_str,
)
from ..utils import (
+ age_restricted,
clean_html,
compiled_regex_type,
ExtractorError,
@@ -40,7 +42,7 @@ 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.
@@ -86,12 +88,15 @@ class InfoExtractor(object):
* player_url SWF Player URL (used for rtmpdump).
* protocol The protocol that will be used for the actual
download, lower-case.
- "http", "https", "rtsp", "rtmp", "m3u8" or so.
+ "http", "https", "rtsp", "rtmp", "rtmpe",
+ "m3u8", or "m3u8_native".
* preference Order number of this format. If this field is
present and not None, the formats get sorted
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)
@@ -124,7 +134,9 @@ class InfoExtractor(object):
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"},
@@ -132,18 +144,37 @@ class InfoExtractor(object):
thumbnail: Full URL to a video thumbnail image.
description: Full video description.
uploader: Full name of the video uploader.
+ creator: The main artist who created the video.
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 where the video was filmed.
- subtitles: The subtitle file contents as a dictionary in the format
- {language: subtitles}.
+ subtitles: The available subtitles as a dictionary in the format
+ {language: subformats}. "subformats" is a list sorted from
+ 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
+ automatic_captions: Like 'subtitles', used by the YoutubeIE for
+ automatically generated captions
duration: Length of the video in seconds, as an integer.
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
+ average_rating: Average rating give by users, the scale used depends on the webpage
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
@@ -239,8 +270,15 @@ class InfoExtractor(object):
def extract(self, url):
"""Extracts URL information and returns it in list of dicts."""
- self.initialize()
- return self._real_extract(url)
+ try:
+ self.initialize()
+ return self._real_extract(url)
+ except ExtractorError:
+ raise
+ except compat_http_client.IncompleteRead as e:
+ raise ExtractorError('A network error has occured.', cause=e, expected=True)
+ except (KeyError, StopIteration) as e:
+ raise ExtractorError('An extractor error has occured.', cause=e)
def set_downloader(self, downloader):
"""Sets the downloader for this IE."""
@@ -359,12 +397,32 @@ class InfoExtractor(object):
if blocked_iframe:
msg += ' Visit %s for more details' % blocked_iframe
raise ExtractorError(msg, expected=True)
+ if 'The URL you requested has been blocked' in content[:512]:
+ msg = (
+ 'Access to this webpage has been blocked by Indian censorship. '
+ 'Use a VPN or proxy server (with --proxy) to route around it.')
+ block_msg = self._html_search_regex(
+ r'(.*?)
',
+ content, 'block message', default=None)
+ if block_msg:
+ msg += ' (Message: "%s")' % block_msg.replace('\n', ' ')
+ raise ExtractorError(msg, expected=True)
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:
@@ -472,7 +530,7 @@ class InfoExtractor(object):
if mobj:
break
- if os.name != 'nt' and sys.stderr.isatty():
+ if not self._downloader.params.get('no_color') and os.name != 'nt' and sys.stderr.isatty():
_name = '\033[0;34m%s\033[0m' % name
else:
_name = name
@@ -589,9 +647,9 @@ 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):
@@ -621,6 +679,21 @@ class InfoExtractor(object):
}
return RATING_TABLE.get(rating.lower(), None)
+ def _family_friendly_search(self, html):
+ # See http://schema.org/VideoObject
+ family_friendly = self._html_search_meta('isFamilyFriendly', html)
+
+ if not family_friendly:
+ return None
+
+ RATING_TABLE = {
+ '1': 0,
+ 'true': 0,
+ '0': 18,
+ 'false': 18,
+ }
+ return RATING_TABLE.get(family_friendly.lower(), None)
+
def _twitter_search_player(self, html):
return self._html_search_meta('twitter:player', html,
'twitter card player')
@@ -670,21 +743,40 @@ class InfoExtractor(object):
preference,
f.get('language_preference') if f.get('language_preference') is not None else -1,
f.get('quality') if f.get('quality') is not None else -1,
+ f.get('tbr') if f.get('tbr') is not None else -1,
+ f.get('filesize') if f.get('filesize') is not None else -1,
+ f.get('vbr') if f.get('vbr') is not None else -1,
f.get('height') if f.get('height') is not None else -1,
f.get('width') if f.get('width') is not None else -1,
ext_preference,
- f.get('tbr') if f.get('tbr') is not None else -1,
- f.get('vbr') if f.get('vbr') is not None else -1,
f.get('abr') if f.get('abr') is not None else -1,
audio_ext_preference,
f.get('fps') if f.get('fps') is not None else -1,
- f.get('filesize') if f.get('filesize') is not None else -1,
f.get('filesize_approx') if f.get('filesize_approx') is not None else -1,
f.get('source_preference') if f.get('source_preference') is not None else -1,
f.get('format_id'),
)
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(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 (
@@ -709,37 +801,45 @@ class InfoExtractor(object):
self.to_screen(msg)
time.sleep(timeout)
- def _extract_f4m_formats(self, manifest_url, video_id):
+ def _extract_f4m_formats(self, manifest_url, video_id, preference=None, f4m_id=None):
manifest = self._download_xml(
manifest_url, video_id, 'Downloading f4m manifest',
'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') or media_el.attrib.get('url')))
tbr = int_or_none(media_el.attrib.get('bitrate'))
- format_id = 'f4m-%d' % (i if tbr is None else tbr)
formats.append({
- 'format_id': format_id,
+ 'format_id': '-'.join(filter(None, [f4m_id, 'f4m-%d' % (i if tbr is None else tbr)])),
'url': manifest_url,
'ext': 'flv',
'tbr': tbr,
'width': int_or_none(media_el.attrib.get('width')),
'height': int_or_none(media_el.attrib.get('height')),
+ 'preference': preference,
})
self._sort_formats(formats)
return formats
def _extract_m3u8_formats(self, m3u8_url, video_id, ext=None,
- entry_protocol='m3u8', preference=None):
+ entry_protocol='m3u8', preference=None,
+ m3u8_id=None):
formats = [{
- 'format_id': 'm3u8-meta',
+ 'format_id': '-'.join(filter(None, [m3u8_id, 'm3u8-meta'])),
'url': m3u8_url,
'ext': ext,
'protocol': 'm3u8',
- 'preference': -1,
+ 'preference': preference - 1 if preference else -1,
'resolution': 'multiple',
'format_note': 'Quality selection URL',
}]
@@ -754,6 +854,7 @@ class InfoExtractor(object):
note='Downloading m3u8 information',
errnote='Failed to download m3u8 information')
last_info = None
+ last_media = None
kv_rex = re.compile(
r'(?P[a-zA-Z_-]+)=(?P"[^"]+"|[^",]+)(?:,|$)')
for line in m3u8_doc.splitlines():
@@ -764,6 +865,13 @@ class InfoExtractor(object):
if v.startswith('"'):
v = v[1:-1]
last_info[m.group('key')] = v
+ elif line.startswith('#EXT-X-MEDIA:'):
+ last_media = {}
+ for m in kv_rex.finditer(line):
+ v = m.group('val')
+ if v.startswith('"'):
+ v = v[1:-1]
+ last_media[m.group('key')] = v
elif line.startswith('#') or not line.strip():
continue
else:
@@ -771,9 +879,8 @@ class InfoExtractor(object):
formats.append({'url': format_url(line)})
continue
tbr = int_or_none(last_info.get('BANDWIDTH'), scale=1000)
-
f = {
- 'format_id': 'm3u8-%d' % (tbr if tbr else len(formats)),
+ 'format_id': '-'.join(filter(None, [m3u8_id, 'm3u8-%d' % (tbr if tbr else len(formats))])),
'url': format_url(line.strip()),
'tbr': tbr,
'ext': ext,
@@ -793,16 +900,22 @@ class InfoExtractor(object):
width_str, height_str = resolution.split('x')
f['width'] = int(width_str)
f['height'] = int(height_str)
+ if last_media is not None:
+ f['m3u8_media'] = last_media
+ last_media = None
formats.append(f)
last_info = {}
self._sort_formats(formats)
return formats
# TODO: improve extraction
- def _extract_smil_formats(self, smil_url, video_id):
+ def _extract_smil_formats(self, smil_url, video_id, fatal=True):
smil = self._download_xml(
smil_url, video_id, 'Downloading SMIL file',
- 'Unable to download SMIL file')
+ 'Unable to download SMIL file', fatal=fatal)
+ if smil is False:
+ assert not fatal
+ return []
base = smil.find('./head/meta').get('base')
@@ -875,6 +988,53 @@ 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
+
+ def extract_subtitles(self, *args, **kwargs):
+ if (self._downloader.params.get('writesubtitles', False) or
+ self._downloader.params.get('listsubtitles')):
+ return self._get_subtitles(*args, **kwargs)
+ return {}
+
+ def _get_subtitles(self, *args, **kwargs):
+ raise NotImplementedError("This method must be implemented by subclasses")
+
+ def extract_automatic_captions(self, *args, **kwargs):
+ if (self._downloader.params.get('writeautomaticsub', False) or
+ self._downloader.params.get('listsubtitles')):
+ return self._get_automatic_captions(*args, **kwargs)
+ return {}
+
+ def _get_automatic_captions(self, *args, **kwargs):
+ raise NotImplementedError("This method must be implemented by subclasses")
+
class SearchInfoExtractor(InfoExtractor):
"""