mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2026-02-27 02:40:02 +00:00
Code Issues Projects Releases Wiki Activity

[ie/zapiks] Improve extraction (#16030)

Browse Source 
Authored by: doe1080
This commit is contained in:
doe1080
2026-02-27 01:26:17 +09:00
committed by GitHub
parent e3118604aa
commit 6f796a2bff
1 changed files with 166 additions and 71 deletions
Download Patch File Download Diff File Expand all files Collapse all files

237
yt_dlp/extractor/zapiks.py
View File

@@ -1,110 +1,205 @@
import json
import re
import urllib.parse
from .common import InfoExtractor
from ..utils import (
clean_html,
extract_attributes,
int_or_none,
parse_duration,
parse_iso8601,
xpath_text,
xpath_with_ns,
parse_resolution,
str_or_none,
unified_timestamp,
url_or_none,
)
from ..utils.traversal import (
find_element,
find_elements,
traverse_obj,
)
class ZapiksIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?zapiks\.(?:fr|com)/(?:(?:[a-z]{2}/)?(?P<display_id>.+?)\.html|index\.php\?.*\bmedia_id=(?P<id>\d+))'
_EMBED_REGEX = [r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"']
_VALID_URL = [
r'https?://(?:www\.)?zapiks\.(?:com|fr)/(?P<id>[\w-]+)\.html',
r'https?://(?:www\.)?zapiks\.fr/index\.php\?(?:[^#]+&)?media_id=(?P<id>\d+)',
]
_EMBED_REGEX = [r'<iframe\b[^>]+\bsrc=["\'](?P<url>(?:https?:)?//(?:www\.)?zapiks\.fr/index\.php\?(?:[^#"\']+&(?:amp;)?)?media_id=\d+)']
_TESTS = [{
'url': 'http://www.zapiks.fr/ep2s3-bon-appetit-eh-be-viva.html',
'url': 'https://www.zapiks.fr/ep2s3-bon-appetit-eh-be-viva.html',
'md5': 'aeb3c473b2d564b2d46d664d28d5f050',
'info_dict': {
'id': '80798',
'ext': 'mp4',
'title': 'EP2S3 - Bon Appétit - Eh bé viva les pyrénées con!',
'description': 'md5:7054d6f6f620c6519be1fe710d4da847',
'thumbnail': r're:https?://zpks\.com/.+\.jpg',
'description': 'md5:db07a553c1550e2905bceafa923000fd',
'display_id': 'ep2s3-bon-appetit-eh-be-viva',
'duration': 528,
'tags': 'count:5',
'thumbnail': r're:https?://zpks\.com/.+',
'timestamp': 1359044972,
'upload_date': '20130124',
'uploader': 'BonAppetit',
'uploader_id': 'bonappetit',
'view_count': int,
},
}, {
'url': 'http://www.zapiks.com/ep3s5-bon-appetit-baqueira-m-1.html',
'only_matching': True,
}, {
'url': 'http://www.zapiks.com/nl/ep3s5-bon-appetit-baqueira-m-1.html',
'only_matching': True,
}, {
'url': 'http://www.zapiks.fr/index.php?action=playerIframe&amp;media_id=118046&amp;width=640&amp;height=360&amp;autoStart=false&amp;language=fr',
'only_matching': True,
}]
_WEBPAGE_TESTS = [{
'url': 'https://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
'url': 'https://www.zapiks.com/ep3s5-bon-appetit-baqueira-m-1.html',
'md5': '196fe42901639d868956b1dcaa48de15',
'info_dict': {
'id': '118046',
'ext': 'mp4',
'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
'thumbnail': r're:https?://zpks\.com/.+\.jpg',
'display_id': 'ep3s5-bon-appetit-baqueira-m-1',
'duration': 642,
'tags': 'count:8',
'thumbnail': r're:https?://zpks\.com/.+',
'timestamp': 1424370543,
'upload_date': '20150219',
'uploader': 'BonAppetit',
'uploader_id': 'bonappetit',
'view_count': int,
},
}, {
'url': 'https://www.zapiks.fr/index.php?action=playerIframe&media_id=164049',
'md5': 'fb81a7c9b7b84c00ba111028aee593b8',
'info_dict': {
'id': '164049',
'ext': 'mp4',
'title': 'Courchevel Hiver 2025/2026',
'display_id': 'courchevel-hiver-2025-2026',
'duration': 38,
'tags': 'count:1',
'thumbnail': r're:https?://zpks\.com/.+',
'timestamp': 1769019147,
'upload_date': '20260121',
'uploader': 'jamrek',
'uploader_id': 'jamrek',
'view_count': int,
},
}, {
# https://www.youtube.com/watch?v=UBAABvegu2M
'url': 'https://www.zapiks.com/live-fwt18-vallnord-arcalis-.html',
'info_dict': {
'id': 'UBAABvegu2M',
'ext': 'mp4',
'title': 'Replay Live - FWT18 Vallnord-Arcalís Andorra - Freeride World Tour 2018',
'age_limit': 0,
'availability': 'public',
'categories': ['Sports'],
'channel': 'FIS Freeride World Tour by Peak Performance',
'channel_follower_count': int,
'channel_id': 'UCraJ3GNFfw6LXFuCV6McByg',
'channel_url': 'https://www.youtube.com/channel/UCraJ3GNFfw6LXFuCV6McByg',
'comment_count': int,
'description': 'md5:2d9fefef758d5ad0d5a987d46aff7572',
'duration': 11328,
'heatmap': 'count:100',
'like_count': int,
'live_status': 'was_live',
'media_type': 'livestream',
'playable_in_embed': True,
'release_date': '20180306',
'release_timestamp': 1520321809,
'tags': 'count:27',
'thumbnail': r're:https?://i\.ytimg\.com/.+',
'timestamp': 1520336958,
'upload_date': '20180306',
'uploader': 'FIS Freeride World Tour by Peak Performance',
'uploader_id': '@FISFreerideWorldTour',
'uploader_url': 'https://www.youtube.com/@FISFreerideWorldTour',
'view_count': int,
},
'add_ie': ['Youtube'],
}, {
# https://vimeo.com/235746460
'url': 'https://www.zapiks.fr/waking-dream-2017-full-movie.html',
'info_dict': {
'id': '235746460',
'ext': 'mp4',
'title': '"WAKING DREAM" (2017) Full Movie by Sam Favret & Julien Herry',
'duration': 1649,
'thumbnail': r're:https?://i\.vimeocdn\.com/video/.+',
'uploader': 'Favret Sam',
'uploader_id': 'samfavret',
'uploader_url': 'https://vimeo.com/samfavret',
},
'add_ie': ['Vimeo'],
'expected_warnings': ['Failed to parse XML: not well-formed'],
}]
_WEBPAGE_TESTS = [{
# https://www.zapiks.fr/ep3s5-bon-appetit-baqueira-m-1.html
# https://www.zapiks.fr/index.php?action=playerIframe&media_id=118046
'url': 'https://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
'md5': '196fe42901639d868956b1dcaa48de15',
'info_dict': {
'id': '118046',
'ext': 'mp4',
'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
'description': 'md5:b45295c3897c4c01d7c04e8484c26aaf',
'display_id': 'ep3s5-bon-appetit-baqueira-m-1',
'duration': 642,
'tags': 'count:8',
'thumbnail': r're:https?://zpks\.com/.+',
'timestamp': 1424370543,
'upload_date': '20150219',
'uploader': 'BonAppetit',
'uploader_id': 'bonappetit',
'view_count': int,
},
}]
_UPLOADER_ID_RE = re.compile(r'/pro(?:fil)?/(?P<id>[^/?#]+)/?')
def _real_extract(self, url):
mobj = self._match_valid_url(url)
video_id = mobj.group('id')
display_id = mobj.group('display_id') or video_id
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
if embed_url := traverse_obj(webpage, (
{find_element(cls='embed-container')}, {find_element(tag='iframe', html=True)},
{extract_attributes}, 'src', {self._proto_relative_url}, {url_or_none},
)):
if not self.suitable(embed_url):
return self.url_result(embed_url)
if not video_id:
video_id = self._search_regex(
r'data-media-id="(\d+)"', webpage, 'video id')
playlist = self._download_xml(
f'http://www.zapiks.fr/view/index.php?action=playlist&media_id={video_id}&lang=en',
display_id)
NS_MAP = {
'jwplayer': 'http://rss.jwpcdn.com/',
}
def ns(path):
return xpath_with_ns(path, NS_MAP)
item = playlist.find('./channel/item')
title = xpath_text(item, 'title', 'title') or self._og_search_title(webpage)
description = self._og_search_description(webpage, default=None)
thumbnail = xpath_text(
item, ns('./jwplayer:image'), 'thumbnail') or self._og_search_thumbnail(webpage, default=None)
duration = parse_duration(self._html_search_meta(
'duration', webpage, 'duration', default=None))
timestamp = parse_iso8601(self._html_search_meta(
'uploadDate', webpage, 'upload date', default=None), ' ')
view_count = int_or_none(self._search_regex(
r'UserPlays:(\d+)', webpage, 'view count', default=None))
comment_count = int_or_none(self._search_regex(
r'UserComments:(\d+)', webpage, 'comment count', default=None))
video_responsive = traverse_obj(webpage, (
{find_element(cls='video-responsive', html=True)}, {extract_attributes}, {dict}))
data_media_url = traverse_obj(video_responsive, ('data-media-url', {url_or_none}))
if data_media_url and urllib.parse.urlparse(url).path == '/index.php':
return self.url_result(data_media_url, ZapiksIE)
data_playlist = traverse_obj(video_responsive, ('data-playlist', {json.loads}, ..., any))
formats = []
for source in item.findall(ns('./jwplayer:source')):
format_id = source.attrib['label']
f = {
'url': source.attrib['file'],
for source in traverse_obj(data_playlist, (
'sources', lambda _, v: url_or_none(v['file']),
)):
format_id = traverse_obj(source, ('label', {str_or_none}))
formats.append({
'format_id': format_id,
}
m = re.search(r'^(?P<height>\d+)[pP]', format_id)
if m:
f['height'] = int(m.group('height'))
formats.append(f)
'url': source['file'],
**parse_resolution(format_id),
})
return {
'id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'duration': duration,
'timestamp': timestamp,
'view_count': view_count,
'comment_count': comment_count,
'display_id': display_id,
'duration': parse_duration(self._html_search_meta('duration', webpage, default=None)),
'formats': formats,
'timestamp': unified_timestamp(self._html_search_meta('uploadDate', webpage, default=None)),
**traverse_obj(webpage, {
'description': ({find_element(cls='description-text')}, {clean_html}, filter),
'tags': (
{find_elements(cls='bs-label', html=True)},
..., {extract_attributes}, 'title', {clean_html}, filter),
'view_count': (
{find_element(cls='video-content-view-counter')}, {clean_html},
{lambda x: re.sub(r'(?:vues|views|\s+)', '', x)}, {int_or_none}),
}),
**traverse_obj(webpage, ({find_element(cls='video-content-user-link', html=True)}, {
'uploader': ({clean_html}, filter),
'uploader_id': ({extract_attributes}, 'href', {self._UPLOADER_ID_RE.fullmatch}, 'id'),
})),
**traverse_obj(data_playlist, {
'id': ('mediaid', {str_or_none}),
'title': ('title', {clean_html}, filter),
'thumbnail': ('image', {url_or_none}),
}),
}