aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl
diff options
context:
space:
mode:
Diffstat (limited to 'youtube_dl')
-rw-r--r--youtube_dl/downloader/__init__.py6
-rw-r--r--youtube_dl/downloader/common.py13
-rw-r--r--youtube_dl/downloader/external.py16
-rw-r--r--youtube_dl/downloader/rtmp.py21
-rw-r--r--youtube_dl/downloader/rtsp.py (renamed from youtube_dl/downloader/mplayer.py)20
-rw-r--r--youtube_dl/extractor/__init__.py2
-rw-r--r--youtube_dl/extractor/cspan.py11
-rw-r--r--youtube_dl/extractor/instagram.py10
-rw-r--r--youtube_dl/extractor/mtv.py7
-rw-r--r--youtube_dl/extractor/orf.py14
-rw-r--r--youtube_dl/extractor/philharmoniedeparis.py78
-rw-r--r--youtube_dl/extractor/southpark.py16
-rw-r--r--youtube_dl/postprocessor/embedthumbnail.py3
-rw-r--r--youtube_dl/postprocessor/ffmpeg.py25
-rw-r--r--youtube_dl/utils.py102
-rw-r--r--youtube_dl/version.py2
16 files changed, 269 insertions, 77 deletions
diff --git a/youtube_dl/downloader/__init__.py b/youtube_dl/downloader/__init__.py
index 9fb66e2f7..f110830c4 100644
--- a/youtube_dl/downloader/__init__.py
+++ b/youtube_dl/downloader/__init__.py
@@ -6,7 +6,7 @@ from .f4m import F4mFD
from .hls import HlsFD
from .hls import NativeHlsFD
from .http import HttpFD
-from .mplayer import MplayerFD
+from .rtsp import RtspFD
from .rtmp import RtmpFD
from ..utils import (
@@ -17,8 +17,8 @@ PROTOCOL_MAP = {
'rtmp': RtmpFD,
'm3u8_native': NativeHlsFD,
'm3u8': HlsFD,
- 'mms': MplayerFD,
- 'rtsp': MplayerFD,
+ 'mms': RtspFD,
+ 'rtsp': RtspFD,
'f4m': F4mFD,
}
diff --git a/youtube_dl/downloader/common.py b/youtube_dl/downloader/common.py
index a0fc5ead0..97e755d4b 100644
--- a/youtube_dl/downloader/common.py
+++ b/youtube_dl/downloader/common.py
@@ -8,6 +8,7 @@ import time
from ..compat import compat_str
from ..utils import (
encodeFilename,
+ decodeArgument,
format_bytes,
timeconvert,
)
@@ -353,19 +354,15 @@ class FileDownloader(object):
# this interface
self._progress_hooks.append(ph)
- def _debug_cmd(self, args, subprocess_encoding, exe=None):
+ def _debug_cmd(self, args, exe=None):
if not self.params.get('verbose', False):
return
+ str_args = [decodeArgument(a) for a in args]
+
if exe is None:
- exe = os.path.basename(args[0])
+ exe = os.path.basename(str_args[0])
- if subprocess_encoding:
- str_args = [
- a.decode(subprocess_encoding) if isinstance(a, bytes) else a
- for a in args]
- else:
- str_args = args
try:
import pipes
shell_quote = lambda args: ' '.join(map(pipes.quote, str_args))
diff --git a/youtube_dl/downloader/external.py b/youtube_dl/downloader/external.py
index 1673b2382..7ca2d3143 100644
--- a/youtube_dl/downloader/external.py
+++ b/youtube_dl/downloader/external.py
@@ -2,11 +2,11 @@ from __future__ import unicode_literals
import os.path
import subprocess
-import sys
from .common import FileDownloader
from ..utils import (
encodeFilename,
+ encodeArgument,
)
@@ -60,17 +60,9 @@ class ExternalFD(FileDownloader):
def _call_downloader(self, tmpfilename, info_dict):
""" Either overwrite this or implement _make_cmd """
- cmd = self._make_cmd(tmpfilename, info_dict)
-
- if sys.platform == 'win32' and sys.version_info < (3, 0):
- # Windows subprocess module does not actually support Unicode
- # on Python 2.x
- # See http://stackoverflow.com/a/9951851/35070
- subprocess_encoding = sys.getfilesystemencoding()
- cmd = [a.encode(subprocess_encoding, 'ignore') for a in cmd]
- else:
- subprocess_encoding = None
- self._debug_cmd(cmd, subprocess_encoding)
+ cmd = [encodeArgument(a) for a in self._make_cmd(tmpfilename, info_dict)]
+
+ self._debug_cmd(cmd)
p = subprocess.Popen(
cmd, stderr=subprocess.PIPE)
diff --git a/youtube_dl/downloader/rtmp.py b/youtube_dl/downloader/rtmp.py
index ddf5724ae..6865b5e2f 100644
--- a/youtube_dl/downloader/rtmp.py
+++ b/youtube_dl/downloader/rtmp.py
@@ -3,7 +3,6 @@ from __future__ import unicode_literals
import os
import re
import subprocess
-import sys
import time
from .common import FileDownloader
@@ -11,6 +10,7 @@ from ..compat import compat_str
from ..utils import (
check_executable,
encodeFilename,
+ encodeArgument,
get_exe_version,
)
@@ -121,7 +121,7 @@ class RtmpFD(FileDownloader):
# possible. This is part of rtmpdump's normal usage, AFAIK.
basic_args = [
'rtmpdump', '--verbose', '-r', url,
- '-o', encodeFilename(tmpfilename, True)]
+ '-o', tmpfilename]
if player_url is not None:
basic_args += ['--swfVfy', player_url]
if page_url is not None:
@@ -154,16 +154,9 @@ class RtmpFD(FileDownloader):
if not live and continue_dl:
args += ['--skip', '1']
- if sys.platform == 'win32' and sys.version_info < (3, 0):
- # Windows subprocess module does not actually support Unicode
- # on Python 2.x
- # See http://stackoverflow.com/a/9951851/35070
- subprocess_encoding = sys.getfilesystemencoding()
- args = [a.encode(subprocess_encoding, 'ignore') for a in args]
- else:
- subprocess_encoding = None
+ args = [encodeArgument(a) for a in args]
- self._debug_cmd(args, subprocess_encoding, exe='rtmpdump')
+ self._debug_cmd(args, exe='rtmpdump')
RD_SUCCESS = 0
RD_FAILED = 1
@@ -180,7 +173,11 @@ class RtmpFD(FileDownloader):
prevsize = os.path.getsize(encodeFilename(tmpfilename))
self.to_screen('[rtmpdump] %s bytes' % prevsize)
time.sleep(5.0) # This seems to be needed
- retval = run_rtmpdump(basic_args + ['-e'] + [[], ['-k', '1']][retval == RD_FAILED])
+ args = basic_args + ['--resume']
+ if retval == RD_FAILED:
+ args += ['--skip', '1']
+ args = [encodeArgument(a) for a in args]
+ retval = run_rtmpdump(args)
cursize = os.path.getsize(encodeFilename(tmpfilename))
if prevsize == cursize and retval == RD_FAILED:
break
diff --git a/youtube_dl/downloader/mplayer.py b/youtube_dl/downloader/rtsp.py
index 72cef30ea..3eb29526c 100644
--- a/youtube_dl/downloader/mplayer.py
+++ b/youtube_dl/downloader/rtsp.py
@@ -10,21 +10,23 @@ from ..utils import (
)
-class MplayerFD(FileDownloader):
+class RtspFD(FileDownloader):
def real_download(self, filename, info_dict):
url = info_dict['url']
self.report_destination(filename)
tmpfilename = self.temp_name(filename)
- args = [
- 'mplayer', '-really-quiet', '-vo', 'null', '-vc', 'dummy',
- '-dumpstream', '-dumpfile', tmpfilename, url]
- # Check for mplayer first
- if not check_executable('mplayer', ['-h']):
- self.report_error('MMS or RTSP download detected but "%s" could not be run' % args[0])
+ if check_executable('mplayer', ['-h']):
+ args = [
+ 'mplayer', '-really-quiet', '-vo', 'null', '-vc', 'dummy',
+ '-dumpstream', '-dumpfile', tmpfilename, url]
+ elif check_executable('mpv', ['-h']):
+ args = [
+ 'mpv', '-really-quiet', '--vo=null', '--stream-dump=' + tmpfilename, url]
+ else:
+ self.report_error('MMS or RTSP download detected but neither "mplayer" nor "mpv" could be run. Please install any.')
return False
- # Download using mplayer.
retval = subprocess.call(args)
if retval == 0:
fsize = os.path.getsize(encodeFilename(tmpfilename))
@@ -39,5 +41,5 @@ class MplayerFD(FileDownloader):
return True
else:
self.to_stderr('\n')
- self.report_error('mplayer exited with code %d' % retval)
+ self.report_error('%s exited with code %d' % (args[0], retval))
return False
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index a64afa1da..641c45f43 100644
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -377,6 +377,7 @@ from .orf import (
from .parliamentliveuk import ParliamentLiveUKIE
from .patreon import PatreonIE
from .pbs import PBSIE
+from .philharmoniedeparis import PhilharmonieDeParisIE
from .phoenix import PhoenixIE
from .photobucket import PhotobucketIE
from .planetaplay import PlanetaPlayIE
@@ -478,6 +479,7 @@ from .soundgasm import (
)
from .southpark import (
SouthParkIE,
+ SouthParkEsIE,
SouthparkDeIE,
)
from .space import SpaceIE
diff --git a/youtube_dl/extractor/cspan.py b/youtube_dl/extractor/cspan.py
index d516b1402..fbefd37d0 100644
--- a/youtube_dl/extractor/cspan.py
+++ b/youtube_dl/extractor/cspan.py
@@ -8,6 +8,7 @@ from ..utils import (
unescapeHTML,
find_xpath_attr,
smuggle_url,
+ determine_ext,
)
from .senateisvp import SenateISVPIE
@@ -87,6 +88,10 @@ class CSpanIE(InfoExtractor):
return self.url_result(surl, 'SenateISVP', video_id, title)
files = data['video']['files']
+ try:
+ capfile = data['video']['capfile']['#text']
+ except KeyError:
+ capfile = None
entries = [{
'id': '%s_%d' % (video_id, partnum + 1),
@@ -97,6 +102,12 @@ class CSpanIE(InfoExtractor):
'description': description,
'thumbnail': thumbnail,
'duration': int_or_none(f.get('length', {}).get('#text')),
+ 'subtitles': {
+ 'en': [{
+ 'url': capfile,
+ 'ext': determine_ext(capfile, 'dfxp')
+ }],
+ } if capfile else None,
} for partnum, f in enumerate(files)]
if len(entries) == 1:
diff --git a/youtube_dl/extractor/instagram.py b/youtube_dl/extractor/instagram.py
index b020e2621..65f6ca103 100644
--- a/youtube_dl/extractor/instagram.py
+++ b/youtube_dl/extractor/instagram.py
@@ -3,13 +3,11 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
-from ..utils import (
- int_or_none,
-)
+from ..utils import int_or_none
class InstagramIE(InfoExtractor):
- _VALID_URL = r'http://instagram\.com/p/(?P<id>.*?)/'
+ _VALID_URL = r'https?://instagram\.com/p/(?P<id>[\da-zA-Z]+)'
_TEST = {
'url': 'http://instagram.com/p/aye83DjauH/?foo=bar#abc',
'md5': '0d2da106a9d2631273e192b372806516',
@@ -23,8 +21,8 @@ class InstagramIE(InfoExtractor):
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
+ video_id = self._match_id(url)
+
webpage = self._download_webpage(url, video_id)
uploader_id = self._search_regex(r'"owner":{"username":"(.+?)"',
webpage, 'uploader id', fatal=False)
diff --git a/youtube_dl/extractor/mtv.py b/youtube_dl/extractor/mtv.py
index 4430b3416..b48fac5e3 100644
--- a/youtube_dl/extractor/mtv.py
+++ b/youtube_dl/extractor/mtv.py
@@ -25,6 +25,7 @@ def _media_xml_tag(tag):
class MTVServicesInfoExtractor(InfoExtractor):
_MOBILE_TEMPLATE = None
+ _LANG = None
@staticmethod
def _id_from_uri(uri):
@@ -169,8 +170,12 @@ class MTVServicesInfoExtractor(InfoExtractor):
video_id = self._id_from_uri(uri)
feed_url = self._get_feed_url(uri)
data = compat_urllib_parse.urlencode({'uri': uri})
+ info_url = feed_url + '?'
+ if self._LANG:
+ info_url += 'lang=%s&' % self._LANG
+ info_url += data
idoc = self._download_xml(
- feed_url + '?' + data, video_id,
+ info_url, video_id,
'Downloading info', transform_source=fix_xml_ampersands)
return self.playlist_result(
[self._get_video_info(item) for item in idoc.findall('.//item')])
diff --git a/youtube_dl/extractor/orf.py b/youtube_dl/extractor/orf.py
index ca1a5bb3c..2e6c9872b 100644
--- a/youtube_dl/extractor/orf.py
+++ b/youtube_dl/extractor/orf.py
@@ -210,16 +210,16 @@ class ORFIPTVIE(InfoExtractor):
_VALID_URL = r'http://iptv\.orf\.at/(?:#/)?stories/(?P<id>\d+)'
_TEST = {
- 'url': 'http://iptv.orf.at/stories/2267952',
- 'md5': '26ffa4bab6dbce1eee78bbc7021016cd',
+ 'url': 'http://iptv.orf.at/stories/2275236/',
+ 'md5': 'c8b22af4718a4b4af58342529453e3e5',
'info_dict': {
- 'id': '339775',
+ 'id': '350612',
'ext': 'flv',
- 'title': 'Kreml-Kritiker Nawalny wieder frei',
- 'description': 'md5:6f24e7f546d364dacd0e616a9e409236',
- 'duration': 84.729,
+ 'title': 'Weitere Evakuierungen um Vulkan Calbuco',
+ 'description': 'md5:d689c959bdbcf04efeddedbf2299d633',
+ 'duration': 68.197,
'thumbnail': 're:^https?://.*\.jpg$',
- 'upload_date': '20150306',
+ 'upload_date': '20150425',
},
}
diff --git a/youtube_dl/extractor/philharmoniedeparis.py b/youtube_dl/extractor/philharmoniedeparis.py
new file mode 100644
index 000000000..6e60e5fe9
--- /dev/null
+++ b/youtube_dl/extractor/philharmoniedeparis.py
@@ -0,0 +1,78 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+ float_or_none,
+ int_or_none,
+ parse_iso8601,
+ xpath_text,
+)
+
+
+class PhilharmonieDeParisIE(InfoExtractor):
+ IE_DESC = 'Philharmonie de Paris'
+ _VALID_URL = r'http://live\.philharmoniedeparis\.fr/(?:[Cc]oncert/|misc/Playlist\.ashx\?id=)(?P<id>\d+)'
+ _TESTS = [{
+ 'url': 'http://live.philharmoniedeparis.fr/concert/1032066.html',
+ 'info_dict': {
+ 'id': '1032066',
+ 'ext': 'flv',
+ 'title': 'md5:d1f5585d87d041d07ce9434804bc8425',
+ 'timestamp': 1428179400,
+ 'upload_date': '20150404',
+ 'duration': 6592.278,
+ },
+ 'params': {
+ # rtmp download
+ 'skip_download': True,
+ }
+ }, {
+ 'url': 'http://live.philharmoniedeparis.fr/Concert/1030324.html',
+ 'only_matching': True,
+ }, {
+ 'url': 'http://live.philharmoniedeparis.fr/misc/Playlist.ashx?id=1030324&track=&lang=fr',
+ 'only_matching': True,
+ }]
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+
+ concert = self._download_xml(
+ 'http://live.philharmoniedeparis.fr/misc/Playlist.ashx?id=%s' % video_id,
+ video_id).find('./concert')
+
+ formats = []
+ info_dict = {
+ 'id': video_id,
+ 'title': xpath_text(concert, './titre', 'title', fatal=True),
+ 'formats': formats,
+ }
+
+ fichiers = concert.find('./fichiers')
+ stream = fichiers.attrib['serveurstream']
+ for fichier in fichiers.findall('./fichier'):
+ info_dict['duration'] = float_or_none(fichier.get('timecodefin'))
+ for quality, (format_id, suffix) in enumerate([('lq', ''), ('hq', '_hd')]):
+ format_url = fichier.get('url%s' % suffix)
+ if not format_url:
+ continue
+ formats.append({
+ 'url': stream,
+ 'play_path': format_url,
+ 'ext': 'flv',
+ 'format_id': format_id,
+ 'width': int_or_none(concert.get('largeur%s' % suffix)),
+ 'height': int_or_none(concert.get('hauteur%s' % suffix)),
+ 'quality': quality,
+ })
+ self._sort_formats(formats)
+
+ date, hour = concert.get('date'), concert.get('heure')
+ if date and hour:
+ info_dict['timestamp'] = parse_iso8601(
+ '%s-%s-%sT%s:00' % (date[0:4], date[4:6], date[6:8], hour))
+ elif date:
+ info_dict['upload_date'] = date
+
+ return info_dict
diff --git a/youtube_dl/extractor/southpark.py b/youtube_dl/extractor/southpark.py
index c20397b3d..e3b73295c 100644
--- a/youtube_dl/extractor/southpark.py
+++ b/youtube_dl/extractor/southpark.py
@@ -1,3 +1,4 @@
+# encoding: utf-8
from __future__ import unicode_literals
from .mtv import MTVServicesInfoExtractor
@@ -5,7 +6,7 @@ from .mtv import MTVServicesInfoExtractor
class SouthParkIE(MTVServicesInfoExtractor):
IE_NAME = 'southpark.cc.com'
- _VALID_URL = r'https?://(www\.)?(?P<url>southpark\.cc\.com/(clips|full-episodes)/(?P<id>.+?)(\?|#|$))'
+ _VALID_URL = r'https?://(?:www\.)?(?P<url>southpark\.cc\.com/(?:clips|full-episodes)/(?P<id>.+?)(\?|#|$))'
_FEED_URL = 'http://www.southparkstudios.com/feeds/video-player/mrss'
@@ -20,9 +21,20 @@ class SouthParkIE(MTVServicesInfoExtractor):
}]
+class SouthParkEsIE(SouthParkIE):
+ IE_NAME = 'southpark.cc.com:español'
+ _VALID_URL = r'https?://(?:www\.)?(?P<url>southpark\.cc\.com/episodios-en-espanol/(?P<id>.+?)(\?|#|$))'
+ _LANG = 'es'
+
+ _TESTS = [{
+ 'url': 'http://southpark.cc.com/episodios-en-espanol/s01e01-cartman-consigue-una-sonda-anal#source=351c1323-0b96-402d-a8b9-40d01b2e9bde&position=1&sort=!airdate',
+ 'playlist_count': 4,
+ }]
+
+
class SouthparkDeIE(SouthParkIE):
IE_NAME = 'southpark.de'
- _VALID_URL = r'https?://(www\.)?(?P<url>southpark\.de/(clips|alle-episoden)/(?P<id>.+?)(\?|#|$))'
+ _VALID_URL = r'https?://(?:www\.)?(?P<url>southpark\.de/(?:clips|alle-episoden)/(?P<id>.+?)(\?|#|$))'
_FEED_URL = 'http://www.southpark.de/feeds/video-player/mrss/'
_TESTS = [{
diff --git a/youtube_dl/postprocessor/embedthumbnail.py b/youtube_dl/postprocessor/embedthumbnail.py
index 7ba98a0ea..4868a42fd 100644
--- a/youtube_dl/postprocessor/embedthumbnail.py
+++ b/youtube_dl/postprocessor/embedthumbnail.py
@@ -11,6 +11,7 @@ from ..compat import (
compat_urlretrieve,
)
from ..utils import (
+ determine_ext,
check_executable,
encodeFilename,
PostProcessingError,
@@ -27,7 +28,7 @@ class EmbedThumbnailPP(FFmpegPostProcessor):
def run(self, info):
filename = info['filepath']
temp_filename = prepend_extension(filename, 'temp')
- temp_thumbnail = prepend_extension(filename, 'thumb')
+ temp_thumbnail = filename + '.' + determine_ext(info['thumbnail'])
if not info.get('thumbnail'):
raise EmbedThumbnailPPError('Thumbnail was not found. Nothing to do.')
diff --git a/youtube_dl/postprocessor/ffmpeg.py b/youtube_dl/postprocessor/ffmpeg.py
index 7a952963e..1765f4969 100644
--- a/youtube_dl/postprocessor/ffmpeg.py
+++ b/youtube_dl/postprocessor/ffmpeg.py
@@ -20,6 +20,7 @@ from ..utils import (
prepend_extension,
shell_quote,
subtitles_filename,
+ dfxp2srt,
)
@@ -651,6 +652,30 @@ class FFmpegSubtitlesConvertorPP(FFmpegPostProcessor):
'format' % new_ext)
continue
new_file = subtitles_filename(filename, lang, new_ext)
+
+ if ext == 'dfxp' or ext == 'ttml':
+ self._downloader.report_warning(
+ 'You have requested to convert dfxp (TTML) subtitles into another format, '
+ 'which results in style information loss')
+
+ dfxp_file = subtitles_filename(filename, lang, ext)
+ srt_file = subtitles_filename(filename, lang, 'srt')
+
+ with io.open(dfxp_file, 'rt', encoding='utf-8') as f:
+ srt_data = dfxp2srt(f.read())
+
+ with io.open(srt_file, 'wt', encoding='utf-8') as f:
+ f.write(srt_data)
+
+ ext = 'srt'
+ subs[lang] = {
+ 'ext': 'srt',
+ 'data': srt_data
+ }
+
+ if new_ext == 'srt':
+ continue
+
self.run_ffmpeg(
subtitles_filename(filename, lang, ext),
new_file, ['-f', new_format])
diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py
index c69d3e165..7d15eab64 100644
--- a/youtube_dl/utils.py
+++ b/youtube_dl/utils.py
@@ -371,6 +371,18 @@ def unescapeHTML(s):
r'&([^;]+);', lambda m: _htmlentity_transform(m.group(1)), s)
+def get_subprocess_encoding():
+ if sys.platform == 'win32' and sys.getwindowsversion()[0] >= 5:
+ # For subprocess calls, encode with locale encoding
+ # Refer to http://stackoverflow.com/a/9951851/35070
+ encoding = preferredencoding()
+ else:
+ encoding = sys.getfilesystemencoding()
+ if encoding is None:
+ encoding = 'utf-8'
+ return encoding
+
+
def encodeFilename(s, for_subprocess=False):
"""
@param s The name of the file
@@ -382,21 +394,24 @@ def encodeFilename(s, for_subprocess=False):
if sys.version_info >= (3, 0):
return s
- if sys.platform == 'win32' and sys.getwindowsversion()[0] >= 5:
- # Pass '' directly to use Unicode APIs on Windows 2000 and up
- # (Detecting Windows NT 4 is tricky because 'major >= 4' would
- # match Windows 9x series as well. Besides, NT 4 is obsolete.)
- if not for_subprocess:
- return s
- else:
- # For subprocess calls, encode with locale encoding
- # Refer to http://stackoverflow.com/a/9951851/35070
- encoding = preferredencoding()
- else:
- encoding = sys.getfilesystemencoding()
- if encoding is None:
- encoding = 'utf-8'
- return s.encode(encoding, 'ignore')
+ # Pass '' directly to use Unicode APIs on Windows 2000 and up
+ # (Detecting Windows NT 4 is tricky because 'major >= 4' would
+ # match Windows 9x series as well. Besides, NT 4 is obsolete.)
+ if not for_subprocess and sys.platform == 'win32' and sys.getwindowsversion()[0] >= 5:
+ return s
+
+ return s.encode(get_subprocess_encoding(), 'ignore')
+
+
+def decodeFilename(b, for_subprocess=False):
+
+ if sys.version_info >= (3, 0):
+ return b
+
+ if not isinstance(b, bytes):
+ return b
+
+ return b.decode(get_subprocess_encoding(), 'ignore')
def encodeArgument(s):
@@ -408,6 +423,10 @@ def encodeArgument(s):
return encodeFilename(s, True)
+def decodeArgument(b):
+ return decodeFilename(b, True)
+
+
def decodeOption(optval):
if optval is None:
return optval
@@ -1791,6 +1810,59 @@ def match_filter_func(filter_str):
return _match_func
+def parse_dfxp_time_expr(time_expr):
+ if not time_expr:
+ return 0.0
+
+ mobj = re.match(r'^(?P<time_offset>\d+(?:\.\d+)?)s?$', time_expr)
+ if mobj:
+ return float(mobj.group('time_offset'))
+
+ mobj = re.match(r'^(\d+):(\d\d):(\d\d(?:\.\d+)?)$', time_expr)
+ if mobj:
+ 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 dfxp2srt(dfxp_data):
+ _x = functools.partial(xpath_with_ns, ns_map={'ttml': 'http://www.w3.org/ns/ttml'})
+
+ def parse_node(node):
+ str_or_empty = functools.partial(str_or_none, default='')
+
+ out = str_or_empty(node.text)
+
+ for child in node:
+ if child.tag == _x('ttml:br'):
+ out += '\n' + str_or_empty(child.tail)
+ elif child.tag == _x('ttml:span'):
+ out += str_or_empty(parse_node(child))
+ else:
+ out += str_or_empty(xml.etree.ElementTree.tostring(child))
+
+ return out
+
+ dfxp = xml.etree.ElementTree.fromstring(dfxp_data.encode('utf-8'))
+ out = []
+ paras = dfxp.findall(_x('.//ttml:p'))
+
+ for para, index in zip(paras, itertools.count(1)):
+ 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'))),
+ parse_node(para)))
+
+ return ''.join(out)
+
+
class PerRequestProxyHandler(compat_urllib_request.ProxyHandler):
def __init__(self, proxies=None):
# Set default handlers
diff --git a/youtube_dl/version.py b/youtube_dl/version.py
index 3fd0e7e56..dc7d666dd 100644
--- a/youtube_dl/version.py
+++ b/youtube_dl/version.py
@@ -1,3 +1,3 @@
from __future__ import unicode_literals
-__version__ = '2015.04.17'
+__version__ = '2015.04.26'
generated by cgit v1.2.3 (git 2.26.2) at 2024-11-05 07:44:20 +0000