paradizelost/youtube-dl
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[phoenix] Fix extraction (closes #29057)

Browse Source
This commit is contained in:
Sergey M․ 2021-05-16 21:21:14 +07:00
parent 286e01ce30
commit eb5080286a
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D
1 changed files with 28 additions and 23 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

51
youtube_dl/extractor/phoenix.py
View File

@ -9,8 +9,9 @@ from ..compat import compat_str
from ..utils import ( from ..utils import (
int_or_none, int_or_none,
merge_dicts, merge_dicts,
try_get,
unified_timestamp, unified_timestamp,
xpath_text, urljoin,
) )
@ -27,10 +28,11 @@ class PhoenixIE(ZDFBaseIE):
'title': 'Wohin führt der Protest in der Pandemie?', 'title': 'Wohin führt der Protest in der Pandemie?',
'description': 'md5:7d643fe7f565e53a24aac036b2122fbd', 'description': 'md5:7d643fe7f565e53a24aac036b2122fbd',
'duration': 1691, 'duration': 1691,
'timestamp': 1613906100, 'timestamp': 1613902500,
'upload_date': '20210221', 'upload_date': '20210221',
'uploader': 'Phoenix', 'uploader': 'Phoenix',
'channel': 'corona nachgehakt', 'series': 'corona nachgehakt',
'episode': 'Wohin führt der Protest in der Pandemie?',
}, },
}, { }, {
# Youtube embed # Youtube embed
@ -79,50 +81,53 @@ class PhoenixIE(ZDFBaseIE):
video_id = compat_str(video.get('basename') or video.get('content')) video_id = compat_str(video.get('basename') or video.get('content'))
details = self._download_xml( details = self._download_json(
'https://www.phoenix.de/php/mediaplayer/data/beitrags_details.php', 'https://www.phoenix.de/php/mediaplayer/data/beitrags_details.php',
video_id, 'Downloading details XML', query={ video_id, 'Downloading details JSON', query={
'ak': 'web', 'ak': 'web',
'ptmd': 'true', 'ptmd': 'true',
'id': video_id, 'id': video_id,
'profile': 'player2', 'profile': 'player2',
}) })
title = title or xpath_text( title = title or details['title']
details, './/information/title', 'title', fatal=True) content_id = details['tracking']['nielsen']['content']['assetid']
content_id = xpath_text(
details, './/video/details/basename', 'content id', fatal=True)
info = self._extract_ptmd( info = self._extract_ptmd(
'https://tmd.phoenix.de/tmd/2/ngplayer_2_3/vod/ptmd/phoenix/%s' % content_id, 'https://tmd.phoenix.de/tmd/2/ngplayer_2_3/vod/ptmd/phoenix/%s' % content_id,
content_id, None, url) content_id, None, url)
timestamp = unified_timestamp(xpath_text(details, './/details/airtime')) duration = int_or_none(try_get(
details, lambda x: x['tracking']['nielsen']['content']['length']))
timestamp = unified_timestamp(details.get('editorialDate'))
series = try_get(
details, lambda x: x['tracking']['nielsen']['content']['program'],
compat_str)
episode = title if details.get('contentType') == 'episode' else None
thumbnails = [] thumbnails = []
for node in details.findall('.//teaserimages/teaserimage'): teaser_images = try_get(details, lambda x: x['teaserImageRef']['layouts'], dict) or {}
thumbnail_url = node.text for thumbnail_key, thumbnail_url in teaser_images.items():
thumbnail_url = urljoin(url, thumbnail_url)
if not thumbnail_url: if not thumbnail_url:
continue continue
thumbnail = { thumbnail = {
'url': thumbnail_url, 'url': thumbnail_url,
} }
thumbnail_key = node.get('key') m = re.match('^([0-9]+)x([0-9]+)$', thumbnail_key)
if thumbnail_key: if m:
m = re.match('^([0-9]+)x([0-9]+)$', thumbnail_key) thumbnail['width'] = int(m.group(1))
if m: thumbnail['height'] = int(m.group(2))
thumbnail['width'] = int(m.group(1))
thumbnail['height'] = int(m.group(2))
thumbnails.append(thumbnail) thumbnails.append(thumbnail)
return merge_dicts(info, { return merge_dicts(info, {
'id': content_id, 'id': content_id,
'title': title, 'title': title,
'description': xpath_text(details, './/information/detail'), 'description': details.get('leadParagraph'),
'duration': int_or_none(xpath_text(details, './/details/lengthSec')), 'duration': duration,
'thumbnails': thumbnails, 'thumbnails': thumbnails,
'timestamp': timestamp, 'timestamp': timestamp,
'uploader': xpath_text(details, './/details/channel'), 'uploader': details.get('tvService'),
'uploader_id': xpath_text(details, './/details/originChannelId'), 'series': series,
'channel': xpath_text(details, './/details/originChannelTitle'), 'episode': episode,
}) })