aboutsummaryrefslogtreecommitdiffstats
path: root/youtube_dlc/extractor
diff options
context:
space:
mode:
Diffstat (limited to 'youtube_dlc/extractor')
-rw-r--r--youtube_dlc/extractor/brightcove.py13
-rw-r--r--youtube_dlc/extractor/extractors.py4
-rw-r--r--youtube_dlc/extractor/mtv.py7
-rw-r--r--youtube_dlc/extractor/skyitalia.py119
-rw-r--r--youtube_dlc/extractor/xtube.py47
-rw-r--r--youtube_dlc/extractor/youtube.py4
6 files changed, 160 insertions, 34 deletions
diff --git a/youtube_dlc/extractor/brightcove.py b/youtube_dlc/extractor/brightcove.py
index 2aa9f4782..638673c31 100644
--- a/youtube_dlc/extractor/brightcove.py
+++ b/youtube_dlc/extractor/brightcove.py
@@ -471,12 +471,17 @@ class BrightcoveNewIE(AdobePassIE):
title = json_data['name'].strip()
formats = []
+ sources_num = len(json_data.get('sources'))
+ key_systems_present = 0
for source in json_data.get('sources', []):
container = source.get('container')
ext = mimetype2ext(source.get('type'))
src = source.get('src')
- # https://support.brightcove.com/playback-api-video-fields-reference#key_systems_object
- if ext == 'ism' or container == 'WVM' or source.get('key_systems'):
+ # https://apis.support.brightcove.com/playback/references/playback-api-video-fields-reference.html
+ if source.get('key_systems'):
+ key_systems_present += 1
+ continue
+ elif ext == 'ism' or container == 'WVM':
continue
elif ext == 'm3u8' or container == 'M2TS':
if not src:
@@ -533,6 +538,10 @@ class BrightcoveNewIE(AdobePassIE):
'format_id': build_format_id('rtmp'),
})
formats.append(f)
+
+ if sources_num == key_systems_present:
+ raise ExtractorError('This video is DRM protected', expected=True)
+
if not formats:
# for sonyliv.com DRM protected videos
s3_source_url = json_data.get('custom_fields', {}).get('s3sourceurl')
diff --git a/youtube_dlc/extractor/extractors.py b/youtube_dlc/extractor/extractors.py
index 1dc2ab34c..666134d86 100644
--- a/youtube_dlc/extractor/extractors.py
+++ b/youtube_dlc/extractor/extractors.py
@@ -1038,6 +1038,10 @@ from .sky import (
SkyNewsIE,
SkySportsIE,
)
+from .skyitalia import (
+ SkyArteItaliaIE,
+ SkyItaliaIE,
+)
from .slideshare import SlideshareIE
from .slideslive import SlidesLiveIE
from .slutload import SlutloadIE
diff --git a/youtube_dlc/extractor/mtv.py b/youtube_dlc/extractor/mtv.py
index 6b3658397..04cc95b6a 100644
--- a/youtube_dlc/extractor/mtv.py
+++ b/youtube_dlc/extractor/mtv.py
@@ -289,7 +289,7 @@ class MTVServicesInfoExtractor(InfoExtractor):
return mgid
- def _extract_mgid(self, webpage, url, data_zone=None):
+ def _extract_mgid(self, webpage, url, title=None, data_zone=None):
try:
# the url can be http://media.mtvnservices.com/fb/{mgid}.swf
# or http://media.mtvnservices.com/{mgid}
@@ -300,7 +300,8 @@ class MTVServicesInfoExtractor(InfoExtractor):
except RegexNotFoundError:
mgid = None
- title = self._match_id(url)
+ if not title:
+ title = url_basename(url)
try:
window_data = self._parse_json(self._search_regex(
@@ -336,7 +337,7 @@ class MTVServicesInfoExtractor(InfoExtractor):
def _real_extract(self, url):
title = url_basename(url)
webpage = self._download_webpage(url, title)
- mgid = self._extract_mgid(webpage, url)
+ mgid = self._extract_mgid(webpage, url, title=title)
videos_info = self._get_videos_info(mgid, url=url)
return videos_info
diff --git a/youtube_dlc/extractor/skyitalia.py b/youtube_dlc/extractor/skyitalia.py
new file mode 100644
index 000000000..3c7bd465d
--- /dev/null
+++ b/youtube_dlc/extractor/skyitalia.py
@@ -0,0 +1,119 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import ExtractorError
+
+
+class SkyItaliaBaseIE(InfoExtractor):
+ _GET_VIDEO_DATA = 'https://apid.sky.it/vdp/v1/getVideoData?token={token}&caller=sky&rendition=web&id={id}'
+ _RES = {
+ 'low': [426, 240],
+ 'med': [640, 360],
+ 'high': [854, 480],
+ 'hd': [1280, 720]
+ }
+
+ def _extract_video_id(self, url):
+ webpage = self._download_webpage(url, 'skyitalia')
+ video_id = self._html_search_regex(
+ [r'data-videoid=\"(\d+)\"',
+ r'http://player\.sky\.it/social\?id=(\d+)\&'],
+ webpage, 'video_id')
+ if video_id:
+ return video_id
+ raise ExtractorError('Video ID not found.')
+
+ def _get_formats(self, video_id, token):
+ data_url = self._GET_VIDEO_DATA.replace('{id}', video_id)
+ data_url = data_url.replace('{token}', token)
+ video_data = self._parse_json(
+ self._download_webpage(data_url, video_id),
+ video_id)
+
+ formats = []
+ for q, r in self._RES.items():
+ key = 'web_%s_url' % q
+ if key not in video_data:
+ continue
+ formats.append({
+ 'url': video_data.get(key),
+ 'format_id': q,
+ 'width': r[0],
+ 'height': r[1]
+ })
+
+ self._sort_formats(formats)
+ title = video_data.get('title')
+ thumb = video_data.get('thumb')
+
+ return {
+ 'id': video_id,
+ 'title': title,
+ 'thumbnail': thumb,
+ 'formats': formats
+ }
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+ if video_id == 'None':
+ video_id = self._extract_video_id(url)
+ return self._get_formats(video_id, self._TOKEN)
+
+
+class SkyItaliaIE(SkyItaliaBaseIE):
+ IE_NAME = 'sky.it'
+ _VALID_URL = r'''(?x)https?://
+ (?P<ie>sport|tg24|video)
+ \.sky\.it/(?:.+?)
+ (?P<id>[0-9]{6})?
+ (?:$|\?)'''
+
+ _TESTS = [{
+ 'url': 'https://video.sky.it/sport/motogp/video/motogp-gp-emilia-romagna-highlights-prove-libere-616162',
+ 'md5': '9c03b590b06e5952d8051f0e02b0feca',
+ 'info_dict': {
+ 'id': '616162',
+ 'ext': 'mp4',
+ 'title': 'MotoGP, GP Emilia Romagna: gli highlights delle prove libere',
+ 'thumbnail': 'https://videoplatform.sky.it/thumbnail/2020/09/18/1600441214452_hl-libere-motogp-misano2_5602634_thumbnail_1.jpg',
+ }
+ }, {
+ 'url': 'https://sport.sky.it/motogp/2020/09/18/motogp-gp-emilia-romagna-misano-2020-prove-libere-diretta',
+ 'md5': '9c03b590b06e5952d8051f0e02b0feca',
+ 'info_dict': {
+ 'id': '616162',
+ 'ext': 'mp4',
+ 'title': 'MotoGP, GP Emilia Romagna: gli highlights delle prove libere',
+ 'thumbnail': 'https://videoplatform.sky.it/thumbnail/2020/09/18/1600441214452_hl-libere-motogp-misano2_5602634_thumbnail_1.jpg',
+ }
+ }, {
+ 'url': 'https://tg24.sky.it/salute-e-benessere/2020/09/18/coronavirus-vaccino-ue-sanofi',
+ 'md5': 'caa25e62dadb529bc5e0b078da99f854',
+ 'info_dict': {
+ 'id': '615904',
+ 'ext': 'mp4',
+ 'title': 'Covid-19, al Buzzi di Milano tamponi drive-in per studenti',
+ 'thumbnail': 'https://videoplatform.sky.it/thumbnail/2020/09/17/1600351405841_error-coronavirus-al-buzzi-di-milano-tamponi_thumbnail_1.jpg',
+ }
+ }, {
+ 'url': 'https://video.sky.it/sport/motogp/video/motogp-gp-emilia-romagna-highlights-prove-libere-616162?itm_source=parsely-api',
+ 'only_matching': True,
+ }]
+ _TOKEN = 'F96WlOd8yoFmLQgiqv6fNQRvHZcsWk5jDaYnDvhbiJk'
+
+
+class SkyArteItaliaIE(SkyItaliaBaseIE):
+ IE_NAME = 'arte.sky.it'
+ _VALID_URL = r'https?://arte\.sky\.it/video/.+?(?P<id>[0-9]{6})?$'
+ _TEST = {
+ 'url': 'https://arte.sky.it/video/federico-fellini-maestri-cinema/',
+ 'md5': '2f22513a89f45142f2746f878d690647',
+ 'info_dict': {
+ 'id': '612888',
+ 'ext': 'mp4',
+ 'title': 'I maestri del cinema Federico Felini',
+ 'thumbnail': 'https://videoplatform.sky.it/thumbnail/2020/09/03/1599146747305_i-maestri-del-cinema-federico-felini_thumbnail_1.jpg',
+ }
+ }
+ _TOKEN = 'LWk29hfiU39NNdq87ePeRach3nzTSV20o0lTv2001Cd'
diff --git a/youtube_dlc/extractor/xtube.py b/youtube_dlc/extractor/xtube.py
index 01b253dcb..081c5e2e7 100644
--- a/youtube_dlc/extractor/xtube.py
+++ b/youtube_dlc/extractor/xtube.py
@@ -5,6 +5,7 @@ import re
from .common import InfoExtractor
from ..utils import (
+ ExtractorError,
int_or_none,
js_to_json,
orderedSet,
@@ -33,28 +34,12 @@ class XTubeIE(InfoExtractor):
'title': 'strange erotica',
'description': 'contains:an ET kind of thing',
'uploader': 'greenshowers',
- 'duration': 450,
+ 'duration': 449,
'view_count': int,
'comment_count': int,
'age_limit': 18,
}
}, {
- # FLV videos with duplicated formats
- 'url': 'http://www.xtube.com/video-watch/A-Super-Run-Part-1-YT-9299752',
- 'md5': 'a406963eb349dd43692ec54631efd88b',
- 'info_dict': {
- 'id': '9299752',
- 'display_id': 'A-Super-Run-Part-1-YT',
- 'ext': 'flv',
- 'title': 'A Super Run - Part 1 (YT)',
- 'description': 'md5:4cc3af1aa1b0413289babc88f0d4f616',
- 'uploader': 'tshirtguy59',
- 'duration': 579,
- 'view_count': int,
- 'comment_count': int,
- 'age_limit': 18,
- },
- }, {
# new URL schema
'url': 'http://www.xtube.com/video-watch/strange-erotica-625837',
'only_matching': True,
@@ -89,16 +74,24 @@ class XTubeIE(InfoExtractor):
title, thumbnail, duration = [None] * 3
- config = self._parse_json(self._search_regex(
- r'playerConf\s*=\s*({.+?})\s*,\s*\n', webpage, 'config',
- default='{}'), video_id, transform_source=js_to_json, fatal=False)
- if config:
- config = config.get('mainRoll')
- if isinstance(config, dict):
- title = config.get('title')
- thumbnail = config.get('poster')
- duration = int_or_none(config.get('duration'))
- sources = config.get('sources') or config.get('format')
+ json_config_string = self._search_regex(
+ r'playerConf=({.+?}),loaderConf',
+ webpage, 'config', default=None)
+ if not json_config_string:
+ raise ExtractorError("Could not extract video player data")
+
+ json_config_string = json_config_string.replace("!0", "true").replace("!1", "false")
+
+ config = self._parse_json(json_config_string, video_id, transform_source=js_to_json, fatal=False)
+ if not config:
+ raise ExtractorError("Could not extract video player data")
+
+ config = config.get('mainRoll')
+ if isinstance(config, dict):
+ title = config.get('title')
+ thumbnail = config.get('poster')
+ duration = int_or_none(config.get('duration'))
+ sources = config.get('sources') or config.get('format')
if not isinstance(sources, dict):
sources = self._parse_json(self._search_regex(
diff --git a/youtube_dlc/extractor/youtube.py b/youtube_dlc/extractor/youtube.py
index 5fd22081a..ccfaa733d 100644
--- a/youtube_dlc/extractor/youtube.py
+++ b/youtube_dlc/extractor/youtube.py
@@ -1366,14 +1366,14 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'ext': ext,
})
sub_lang_list[lang] = sub_formats
- """ if has_live_chat_replay:
+ if has_live_chat_replay:
sub_lang_list['live_chat'] = [
{
'video_id': video_id,
'ext': 'json',
'protocol': 'youtube_live_chat_replay',
},
- ] """
+ ]
if not sub_lang_list:
self._downloader.report_warning('video doesn\'t have subtitles')
return {}
generated by cgit v1.2.3 (git 2.25.1) at 2025-10-13 15:41:02 +0000