<div xml:lang="en">
<p begin="0" end="1">The following line contains Chinese characters and special symbols</p>
<p begin="1" end="2">第二行<br/>♪♪</p>
- <p begin="2" end="3"><span>Third<br/>Line</span></p>
+ <p begin="2" dur="1"><span>Third<br/>Line</span></p>
</div>
</body>
</tt>'''
req_format = self.params.get('format')
if req_format is None:
req_format_list = []
- if (self.params.get('outtmpl', DEFAULT_OUTTMPL) != '-'
- and info_dict['extractor'] in ['youtube', 'ted']):
+ if (self.params.get('outtmpl', DEFAULT_OUTTMPL) != '-' and
+ info_dict['extractor'] in ['youtube', 'ted']):
merger = FFmpegMergerPP(self)
if merger.available and merger.can_merge():
req_format_list.append('bestvideo+bestaudio')
if opts.xattrs:
postprocessors.append({'key': 'XAttrMetadata'})
if opts.embedthumbnail:
- postprocessors.append({'key': 'EmbedThumbnail'})
+ already_have_thumbnail = opts.writethumbnail or opts.write_all_thumbnails
+ postprocessors.append({
+ 'key': 'EmbedThumbnail',
+ 'already_have_thumbnail': already_have_thumbnail
+ })
+ if not already_have_thumbnail:
+ opts.writethumbnail = True
# Please keep ExecAfterDownload towards the bottom as it allows the user to modify the final file in any way.
# So if the user is able to remove the file before your postprocessor runs it might cause a few problems.
if opts.exec_cmd:
)
from .southpark import (
SouthParkIE,
- SouthParkEsIE,
SouthParkDeIE,
+ SouthParkDkIE,
+ SouthParkEsIE,
SouthParkNlIE
)
from .space import SpaceIE
from .thisav import ThisAVIE
from .tinypic import TinyPicIE
from .tlc import TlcIE, TlcDeIE
-from .tmz import TMZIE
+from .tmz import (
+ TMZIE,
+ TMZArticleIE,
+)
from .tnaflix import TNAFlixIE
from .thvideo import (
THVideoIE,
'ext': 'mp4',
'description': 'md5:5438d33774b6bdc662f9485a340401cc',
'title': 'Season 5 Episode 5',
- 'thumbnail': 're:^https?://.*promo.*'
+ 'thumbnail': 're:^https?://.*\.jpg$'
},
'params': {
'skip_download': True,
}
_TESTS = [{
- 'url': 'http://www.canalplus.fr/c-infos-documentaires/pid1830-c-zapping.html?vid=922470',
- 'md5': '3db39fb48b9685438ecf33a1078023e4',
+ 'url': 'http://www.canalplus.fr/c-emissions/pid1830-c-zapping.html?vid=1263092',
+ 'md5': 'b3481d7ca972f61e37420798d0a9d934',
'info_dict': {
- 'id': '922470',
+ 'id': '1263092',
'ext': 'flv',
- 'title': 'Zapping - 26/08/13',
- 'description': 'Le meilleur de toutes les chaînes, tous les jours.\nEmission du 26 août 2013',
- 'upload_date': '20130826',
+ 'title': 'Le Zapping - 13/05/15',
+ 'description': 'md5:09738c0d06be4b5d06a0940edb0da73f',
+ 'upload_date': '20150513',
},
}, {
'url': 'http://www.piwiplus.fr/videos-piwi/pid1405-le-labyrinthe-boing-super-ranger.html?vid=1108190',
'skip': 'videos get deleted after a while',
}, {
'url': 'http://www.itele.fr/france/video/aubervilliers-un-lycee-en-colere-111559',
- 'md5': '65aa83ad62fe107ce29e564bb8712580',
+ 'md5': 'f3a46edcdf28006598ffaf5b30e6a2d4',
'info_dict': {
'id': '1213714',
'ext': 'flv',
def _get_automatic_captions(self, *args, **kwargs):
raise NotImplementedError("This method must be implemented by subclasses")
- def _subtitles_timecode(self, seconds):
- return '%02d:%02d:%02d.%03d' % (seconds / 3600, (seconds % 3600) / 60, seconds % 60, (seconds % 1) * 1000)
-
class SearchInfoExtractor(InfoExtractor):
"""
video_id = self._match_id(url)
req = compat_urllib_request.Request(url)
- req.add_header('Cookie', 'nsfw=1')
+ req.add_header('Cookie', 'nsfw=1; cpc=10')
webpage = self._download_webpage(req, video_id)
files_base64 = self._search_regex(
from ..utils import (
ExtractorError,
float_or_none,
+ srt_subtitles_timecode,
)
'%s\r\n%s --> %s\r\n%s'
% (
num,
- self._subtitles_timecode(item['startMillis'] / 1000.0),
- self._subtitles_timecode(item['endMillis'] / 1000.0),
+ srt_subtitles_timecode(item['startMillis'] / 1000.0),
+ srt_subtitles_timecode(item['endMillis'] / 1000.0),
item['text'],
) for num, item in enumerate(subs, 1))
import re
from .common import InfoExtractor
-from ..compat import compat_str
from ..utils import (
ExtractorError,
float_or_none,
url = "%s%s" % (baseurl, subtitlesurl)
self._debug_print('%s: Subtitle url: %s' % (video_id, url))
captions = self._download_xml(
- url, video_id, 'Downloading subtitles',
- transform_source=lambda s: s.replace(r'<br />', '\r\n'))
+ url, video_id, 'Downloading subtitles')
lang = captions.get('lang', 'no')
- ps = captions.findall('./{0}body/{0}div/{0}p'.format('{http://www.w3.org/ns/ttml}'))
- srt = ''
- for pos, p in enumerate(ps):
- begin = parse_duration(p.get('begin'))
- duration = parse_duration(p.get('dur'))
- starttime = self._subtitles_timecode(begin)
- endtime = self._subtitles_timecode(begin + duration)
- srt += '%s\r\n%s --> %s\r\n%s\r\n\r\n' % (compat_str(pos), starttime, endtime, p.text)
return {lang: [
{'ext': 'ttml', 'url': url},
- {'ext': 'srt', 'data': srt},
]}
def _extract_f4m(self, manifest_url, video_id):
class NYTimesArticleIE(NYTimesBaseIE):
- _VALID_URL = r'https?://(?:www)?\.nytimes\.com/(.(?<!video))*?/(?:[^/]+/)*(?P<id>[^.]+)(?:\.html)?'
+ _VALID_URL = r'https?://(?:www\.)?nytimes\.com/(.(?<!video))*?/(?:[^/]+/)*(?P<id>[^.]+)(?:\.html)?'
_TESTS = [{
'url': 'http://www.nytimes.com/2015/04/14/business/owner-of-gravity-payments-a-credit-card-processor-is-setting-a-new-minimum-wage-70000-a-year.html?_r=0',
'md5': 'e2076d58b4da18e6a001d53fd56db3c9',
unified_strdate,
int_or_none,
qualities,
+ unescapeHTML,
)
webpage = self._download_webpage(url, video_id)
player = self._parse_json(
- self._search_regex(
- r"OKVideo\.start\(({.+?})\s*,\s*'VideoAutoplay_player'", webpage, 'player'),
+ unescapeHTML(self._search_regex(
+ r'data-attributes="([^"]+)"', webpage, 'player')),
video_id)
metadata = self._parse_json(player['flashvars']['metadata'], video_id)
'url': 'http://www.southpark.nl/full-episodes/s18e06-freemium-isnt-free',
'playlist_count': 4,
}]
+
+
+class SouthParkDkIE(SouthParkIE):
+ IE_NAME = 'southparkstudios.dk'
+ _VALID_URL = r'https?://(?:www\.)?(?P<url>southparkstudios\.dk/(?:clips|full-episodes)/(?P<id>.+?)(\?|#|$))'
+ _FEED_URL = 'http://www.southparkstudios.dk/feeds/video-player/mrss/'
+
+ _TESTS = [{
+ 'url': 'http://www.southparkstudios.dk/full-episodes/s18e07-grounded-vindaloop',
+ 'playlist_count': 4,
+ }]
'description': self._og_search_description(webpage),
'thumbnail': self._html_search_meta('ThumbURL', webpage),
}
+
+
+class TMZArticleIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:www\.)?tmz\.com/\d{4}/\d{2}/\d{2}/(?P<id>[^/]+)/?'
+ _TEST = {
+ 'url': 'http://www.tmz.com/2015/04/19/bobby-brown-bobbi-kristina-awake-video-concert',
+ 'md5': 'e482a414a38db73087450e3a6ce69d00',
+ 'info_dict': {
+ 'id': '0_6snoelag',
+ 'ext': 'mp4',
+ 'title': 'Bobby Brown Tells Crowd ... Bobbi Kristina is Awake',
+ 'description': 'Bobby Brown stunned his audience during a concert Saturday night, when he told the crowd, "Bobbi is awake. She\'s watching me."',
+ }
+ }
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+
+ webpage = self._download_webpage(url, video_id)
+ embedded_video_info_str = self._html_search_regex(
+ r'tmzVideoEmbedV2\("([^)]+)"\);', webpage, 'embedded video info')
+
+ embedded_video_info = self._parse_json(
+ embedded_video_info_str, video_id,
+ transform_source=lambda s: s.replace('\\', ''))
+
+ return self.url_result(
+ 'http://www.tmz.com/videos/%s/' % embedded_video_info['id'])
return {
'id': video_id,
'title': self._og_search_title(webpage),
- 'alt_title': self._og_search_description(webpage),
+ 'alt_title': self._og_search_description(webpage, default=None),
'description': data['description'],
'thumbnail': data['thumbnailUrl'],
'upload_date': unified_strdate(data['created']),
import re
from .common import InfoExtractor
+from ..utils import ExtractorError
class ZingMp3BaseInfoExtractor(InfoExtractor):
- @staticmethod
- def _extract_item(item):
+ def _extract_item(self, item):
+ error_message = item.find('./errormessage').text
+ if error_message:
+ raise ExtractorError(
+ '%s returned error: %s' % (self.IE_NAME, error_message),
+ expected=True)
+
title = item.find('./title').text.strip()
source = item.find('./source').text
extension = item.attrib['type']
from .ffmpeg import FFmpegPostProcessor
-from ..compat import (
- compat_urlretrieve,
-)
from ..utils import (
- determine_ext,
check_executable,
+ encodeArgument,
encodeFilename,
PostProcessingError,
prepend_extension,
class EmbedThumbnailPP(FFmpegPostProcessor):
+ def __init__(self, downloader=None, already_have_thumbnail=False):
+ super(EmbedThumbnailPP, self).__init__(downloader)
+ self._already_have_thumbnail = already_have_thumbnail
+
def run(self, info):
filename = info['filepath']
temp_filename = prepend_extension(filename, 'temp')
- temp_thumbnail = filename + '.' + determine_ext(info['thumbnail'])
- if not info.get('thumbnail'):
+ if not info.get('thumbnails'):
raise EmbedThumbnailPPError('Thumbnail was not found. Nothing to do.')
- compat_urlretrieve(info['thumbnail'], temp_thumbnail)
+ thumbnail_filename = info['thumbnails'][-1]['filename']
if info['ext'] == 'mp3':
options = [
- '-i', temp_thumbnail, '-c', 'copy', '-map', '0', '-map', '1',
+ '-c', 'copy', '-map', '0', '-map', '1',
'-metadata:s:v', 'title="Album cover"', '-metadata:s:v', 'comment="Cover (Front)"']
self._downloader.to_screen('[ffmpeg] Adding thumbnail to "%s"' % filename)
- self.run_ffmpeg(filename, temp_filename, options)
+ self.run_ffmpeg_multiple_files([filename, thumbnail_filename], temp_filename, options)
- os.remove(encodeFilename(temp_thumbnail))
+ if not self._already_have_thumbnail:
+ os.remove(encodeFilename(thumbnail_filename))
os.remove(encodeFilename(filename))
os.rename(encodeFilename(temp_filename), encodeFilename(filename))
if not check_executable('AtomicParsley', ['-v']):
raise EmbedThumbnailPPError('AtomicParsley was not found. Please install.')
- cmd = ['AtomicParsley', filename, '--artwork', temp_thumbnail, '-o', temp_filename]
+ cmd = [encodeFilename('AtomicParsley', True),
+ encodeFilename(filename, True),
+ encodeArgument('--artwork'),
+ encodeFilename(thumbnail_filename, True),
+ encodeArgument('-o'),
+ encodeFilename(temp_filename, True)]
self._downloader.to_screen('[atomicparsley] Adding thumbnail to "%s"' % filename)
msg = stderr.decode('utf-8', 'replace').strip()
raise EmbedThumbnailPPError(msg)
- os.remove(encodeFilename(temp_thumbnail))
+ if not self._already_have_thumbnail:
+ os.remove(encodeFilename(thumbnail_filename))
# for formats that don't support thumbnails (like 3gp) AtomicParsley
# won't create to the temporary file
if b'No changes' in stdout:
import os
import subprocess
import sys
+import errno
from .common import PostProcessor
-from ..compat import (
- subprocess_check_output
-)
from ..utils import (
check_executable,
hyphenate_date,
version_tuple,
+ PostProcessingError,
+ encodeArgument,
+ encodeFilename,
)
+class XAttrMetadataError(PostProcessingError):
+ def __init__(self, code=None, msg='Unknown error'):
+ super(XAttrMetadataError, self).__init__(msg)
+ self.code = code
+
+ # Parsing code and msg
+ if (self.code in (errno.ENOSPC, errno.EDQUOT) or
+ 'No space left' in self.msg or 'Disk quota excedded' in self.msg):
+ self.reason = 'NO_SPACE'
+ elif self.code == errno.E2BIG or 'Argument list too long' in self.msg:
+ self.reason = 'VALUE_TOO_LONG'
+ else:
+ self.reason = 'NOT_SUPPORTED'
+
+
class XAttrMetadataPP(PostProcessor):
#
raise ImportError
def write_xattr(path, key, value):
- return xattr.setxattr(path, key, value)
+ try:
+ xattr.set(path, key, value)
+ except EnvironmentError as e:
+ raise XAttrMetadataError(e.errno, e.strerror)
except ImportError:
if os.name == 'nt':
assert os.path.exists(path)
ads_fn = path + ":" + key
- with open(ads_fn, "wb") as f:
- f.write(value)
+ try:
+ with open(ads_fn, "wb") as f:
+ f.write(value)
+ except EnvironmentError as e:
+ raise XAttrMetadataError(e.errno, e.strerror)
else:
user_has_setfattr = check_executable("setfattr", ['--version'])
user_has_xattr = check_executable("xattr", ['-h'])
if user_has_setfattr or user_has_xattr:
def write_xattr(path, key, value):
+ value = value.decode('utf-8')
if user_has_setfattr:
- cmd = ['setfattr', '-n', key, '-v', value, path]
+ executable = 'setfattr'
+ opts = ['-n', key, '-v', value]
elif user_has_xattr:
- cmd = ['xattr', '-w', key, value, path]
-
- subprocess_check_output(cmd)
+ executable = 'xattr'
+ opts = ['-w', key, value]
+
+ cmd = ([encodeFilename(executable, True)] +
+ [encodeArgument(o) for o in opts] +
+ [encodeFilename(path, True)])
+
+ try:
+ p = subprocess.Popen(
+ cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE, stdin=subprocess.PIPE)
+ except EnvironmentError as e:
+ raise XAttrMetadataError(e.errno, e.strerror)
+ stdout, stderr = p.communicate()
+ stderr = stderr.decode('utf-8', 'replace')
+ if p.returncode != 0:
+ raise XAttrMetadataError(p.returncode, stderr)
else:
# On Unix, and can't find pyxattr, setfattr, or xattr.
return [], info
- except (subprocess.CalledProcessError, OSError):
- self._downloader.report_error("This filesystem doesn't support extended attributes. (You may have to enable them in your /etc/fstab)")
+ except XAttrMetadataError as e:
+ if e.reason == 'NO_SPACE':
+ self._downloader.report_warning(
+ 'There\'s no disk space left or disk quota exceeded. ' +
+ 'Extended attributes are not written.')
+ elif e.reason == 'VALUE_TOO_LONG':
+ self._downloader.report_warning(
+ 'Unable to write extended attributes due to too long values.')
+ else:
+ msg = 'This filesystem doesn\'t support extended attributes. '
+ if os.name == 'nt':
+ msg += 'You need to use NTFS.'
+ else:
+ msg += '(You may have to enable them in your /etc/fstab)'
+ self._downloader.report_error(msg)
return [], info
return 3600 * int(mobj.group(1)) + 60 * int(mobj.group(2)) + float(mobj.group(3))
-def format_srt_time(seconds):
- (mins, secs) = divmod(seconds, 60)
- (hours, mins) = divmod(mins, 60)
- millisecs = (secs - int(secs)) * 1000
- secs = int(secs)
- return '%02d:%02d:%02d,%03d' % (hours, mins, secs, millisecs)
+def srt_subtitles_timecode(seconds):
+ return '%02d:%02d:%02d,%03d' % (seconds / 3600, (seconds % 3600) / 60, seconds % 60, (seconds % 1) * 1000)
def dfxp2srt(dfxp_data):
paras = dfxp.findall(_x('.//ttml:p'))
for para, index in zip(paras, itertools.count(1)):
+ begin_time = parse_dfxp_time_expr(para.attrib['begin'])
+ end_time = parse_dfxp_time_expr(para.attrib.get('end'))
+ if not end_time:
+ end_time = begin_time + parse_dfxp_time_expr(para.attrib['dur'])
out.append('%d\n%s --> %s\n%s\n\n' % (
index,
- format_srt_time(parse_dfxp_time_expr(para.attrib.get('begin'))),
- format_srt_time(parse_dfxp_time_expr(para.attrib.get('end'))),
+ srt_subtitles_timecode(begin_time),
+ srt_subtitles_timecode(end_time),
parse_node(para)))
return ''.join(out)
projects / youtube-dl / commitdiff