aboutsummaryrefslogtreecommitdiffstats
path: root/youtube_dlc
diff options
context:
space:
mode:
Diffstat (limited to 'youtube_dlc')
-rw-r--r--youtube_dlc/YoutubeDL.py24
-rw-r--r--youtube_dlc/__init__.py1
-rw-r--r--youtube_dlc/extractor/kakao.py35
-rw-r--r--youtube_dlc/extractor/ndr.py15
-rw-r--r--youtube_dlc/extractor/youtube.py2
-rw-r--r--youtube_dlc/version.py2
6 files changed, 48 insertions, 31 deletions
diff --git a/youtube_dlc/YoutubeDL.py b/youtube_dlc/YoutubeDL.py
index f79d31deb..4cec2298c 100644
--- a/youtube_dlc/YoutubeDL.py
+++ b/youtube_dlc/YoutubeDL.py
@@ -105,6 +105,7 @@ from .postprocessor import (
FFmpegFixupStretchedPP,
FFmpegMergerPP,
FFmpegPostProcessor,
+ FFmpegSubtitlesConvertorPP,
get_postprocessor,
)
from .version import __version__
@@ -1846,6 +1847,29 @@ class YoutubeDL(object):
(sub_lang, error_to_compat_str(err)))
continue
+ if self.params.get('skip_download', False):
+ if self.params.get('convertsubtitles', False):
+ subconv = FFmpegSubtitlesConvertorPP(self, format=self.params.get('convertsubtitles'))
+ filename_real_ext = os.path.splitext(filename)[1][1:]
+ filename_wo_ext = (
+ os.path.splitext(filename)[0]
+ if filename_real_ext == info_dict['ext']
+ else filename)
+ afilename = '%s.%s' % (filename_wo_ext, self.params.get('convertsubtitles'))
+ if subconv.available:
+ info_dict.setdefault('__postprocessors', [])
+ # info_dict['__postprocessors'].append(subconv)
+ if os.path.exists(encodeFilename(afilename)):
+ self.to_screen(
+ '[download] %s has already been downloaded and '
+ 'converted' % afilename)
+ else:
+ try:
+ self.post_process(filename, info_dict)
+ except (PostProcessingError) as err:
+ self.report_error('postprocessing: %s' % str(err))
+ return
+
if self.params.get('writeinfojson', False):
infofn = replace_extension(filename, 'info.json', info_dict.get('ext'))
if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(infofn)):
diff --git a/youtube_dlc/__init__.py b/youtube_dlc/__init__.py
index a663417da..fc11642b9 100644
--- a/youtube_dlc/__init__.py
+++ b/youtube_dlc/__init__.py
@@ -315,6 +315,7 @@ def _real_main(argv=None):
else match_filter_func(opts.match_filter))
ydl_opts = {
+ 'convertsubtitles': opts.convertsubtitles,
'usenetrc': opts.usenetrc,
'username': opts.username,
'password': opts.password,
diff --git a/youtube_dlc/extractor/kakao.py b/youtube_dlc/extractor/kakao.py
index 32935bb28..fefd8a215 100644
--- a/youtube_dlc/extractor/kakao.py
+++ b/youtube_dlc/extractor/kakao.py
@@ -8,13 +8,13 @@ from ..utils import (
int_or_none,
strip_or_none,
unified_timestamp,
- update_url_query,
)
class KakaoIE(InfoExtractor):
_VALID_URL = r'https?://(?:play-)?tv\.kakao\.com/(?:channel/\d+|embed/player)/cliplink/(?P<id>\d+|[^?#&]+@my)'
- _API_BASE_TMPL = 'http://tv.kakao.com/api/v1/ft/cliplinks/%s/'
+ _API_BASE_TMPL = 'http://tv.kakao.com/api/v1/ft/playmeta/cliplink/%s/'
+ _CDN_API = 'https://tv.kakao.com/katz/v1/ft/cliplink/%s/readyNplay?'
_TESTS = [{
'url': 'http://tv.kakao.com/channel/2671005/cliplink/301965083',
@@ -45,18 +45,8 @@ class KakaoIE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
- display_id = video_id.rstrip('@my')
api_base = self._API_BASE_TMPL % video_id
-
- player_header = {
- 'Referer': update_url_query(
- 'http://tv.kakao.com/embed/player/cliplink/%s' % video_id, {
- 'service': 'kakao_tv',
- 'autoplay': '1',
- 'profile': 'HIGH',
- 'wmode': 'transparent',
- })
- }
+ cdn_api_base = self._CDN_API % video_id
query = {
'player': 'monet_html5',
@@ -73,17 +63,14 @@ class KakaoIE(InfoExtractor):
'videoOutputList', 'width', 'height', 'kbps', 'profile', 'label'])
}
- impress = self._download_json(
- api_base + 'impress', display_id, 'Downloading video info',
- query=query, headers=player_header)
+ api_json = self._download_json(
+ api_base, video_id, 'Downloading video info')
- clip_link = impress['clipLink']
+ clip_link = api_json['clipLink']
clip = clip_link['clip']
title = clip.get('title') or clip_link.get('displayTitle')
- query['tid'] = impress.get('tid', '')
-
formats = []
for fmt in clip.get('videoOutputList', []):
try:
@@ -94,15 +81,17 @@ class KakaoIE(InfoExtractor):
'profile': profile_name,
'fields': '-*,url',
})
+
fmt_url_json = self._download_json(
- api_base + 'raw/videolocation', display_id,
+ cdn_api_base, video_id,
'Downloading video URL for profile %s' % profile_name,
- query=query, headers=player_header, fatal=False)
+ query=query, fatal=False)
if fmt_url_json is None:
continue
- fmt_url = fmt_url_json['url']
+ fmt_vidLocation = fmt_url_json['videoLocation']
+ fmt_url = fmt_vidLocation['url']
formats.append({
'url': fmt_url,
'format_id': profile_name,
@@ -131,7 +120,7 @@ class KakaoIE(InfoExtractor):
})
return {
- 'id': display_id,
+ 'id': video_id,
'title': title,
'description': strip_or_none(clip.get('description')),
'uploader': clip_link.get('channel', {}).get('name'),
diff --git a/youtube_dlc/extractor/ndr.py b/youtube_dlc/extractor/ndr.py
index 2447c812e..f3897c71b 100644
--- a/youtube_dlc/extractor/ndr.py
+++ b/youtube_dlc/extractor/ndr.py
@@ -19,14 +19,15 @@ class NDRBaseIE(InfoExtractor):
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
display_id = next(group for group in mobj.groups() if group)
+ id = mobj.group('id')
webpage = self._download_webpage(url, display_id)
- return self._extract_embed(webpage, display_id)
+ return self._extract_embed(webpage, display_id, id)
class NDRIE(NDRBaseIE):
IE_NAME = 'ndr'
IE_DESC = 'NDR.de - Norddeutscher Rundfunk'
- _VALID_URL = r'https?://(?:www\.)?ndr\.de/(?:[^/]+/)*(?P<id>[^/?#]+),[\da-z]+\.html'
+ _VALID_URL = r'https?://(?:www\.)?(?:daserste\.)?ndr\.de/(?:[^/]+/)*(?P<display_id>[^/?#]+),(?P<id>[\da-z]+)\.html'
_TESTS = [{
# httpVideo, same content id
'url': 'http://www.ndr.de/fernsehen/Party-Poette-und-Parade,hafengeburtstag988.html',
@@ -86,12 +87,14 @@ class NDRIE(NDRBaseIE):
'only_matching': True,
}]
- def _extract_embed(self, webpage, display_id):
+ def _extract_embed(self, webpage, display_id, id):
embed_url = self._html_search_meta(
'embedURL', webpage, 'embed URL',
default=None) or self._search_regex(
r'\bembedUrl["\']\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
- 'embed URL', group='url')
+ 'embed URL', fatal=False, group='url')
+ if embed_url is None:
+ return self.url_result('ndr:%s' % id, ie=NDREmbedBaseIE.ie_key())
description = self._search_regex(
r'<p[^>]+itemprop="description">([^<]+)</p>',
webpage, 'description', default=None) or self._og_search_description(webpage)
@@ -152,7 +155,7 @@ class NJoyIE(NDRBaseIE):
'only_matching': True,
}]
- def _extract_embed(self, webpage, display_id):
+ def _extract_embed(self, webpage, display_id, id):
video_id = self._search_regex(
r'<iframe[^>]+id="pp_([\da-z]+)"', webpage, 'embed id')
description = self._search_regex(
@@ -253,7 +256,7 @@ class NDREmbedBaseIE(InfoExtractor):
class NDREmbedIE(NDREmbedBaseIE):
IE_NAME = 'ndr:embed'
- _VALID_URL = r'https?://(?:www\.)?ndr\.de/(?:[^/]+/)*(?P<id>[\da-z]+)-(?:player|externalPlayer)\.html'
+ _VALID_URL = r'https?://(?:www\.)?(?:daserste\.)?ndr\.de/(?:[^/]+/)*(?P<id>[\da-z]+)-(?:player|externalPlayer)\.html'
_TESTS = [{
'url': 'http://www.ndr.de/fernsehen/sendungen/ndr_aktuell/ndraktuell28488-player.html',
'md5': '8b9306142fe65bbdefb5ce24edb6b0a9',
diff --git a/youtube_dlc/extractor/youtube.py b/youtube_dlc/extractor/youtube.py
index d3ba4c73c..a97921060 100644
--- a/youtube_dlc/extractor/youtube.py
+++ b/youtube_dlc/extractor/youtube.py
@@ -549,7 +549,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'396': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'},
'397': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'},
}
- _SUBTITLE_FORMATS = ('srv1', 'srv2', 'srv3', 'ttml', 'vtt', 'json3')
+ _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
_GEO_BYPASS = False
diff --git a/youtube_dlc/version.py b/youtube_dlc/version.py
index 9dd9adf08..af04ea8b9 100644
--- a/youtube_dlc/version.py
+++ b/youtube_dlc/version.py
@@ -1,3 +1,3 @@
from __future__ import unicode_literals
-__version__ = '2020.09.12'
+__version__ = '2020.09.13'
generated by cgit v1.2.3 (git 2.25.1) at 2025-08-02 23:55:47 +0000