mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-11-30 03:33:02 +00:00
[zippcast] Improve (Closes #8198)
This commit is contained in:
Sergey M․
parent
2ddfd26f1b
commit
315bdae00a
1 changed files with 64 additions and 28 deletions
|
|
@ -1,58 +1,94 @@
|
||||||
# coding: utf-8
|
|
||||||
from __future__ import unicode_literals
|
from __future__ import unicode_literals
|
||||||
|
|
||||||
|
import re
|
||||||
|
|
||||||
from .common import InfoExtractor
|
from .common import InfoExtractor
|
||||||
|
from ..utils import (
|
||||||
|
determine_ext,
|
||||||
|
str_to_int,
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
class ZippCastIE(InfoExtractor):
|
class ZippCastIE(InfoExtractor):
|
||||||
_VALID_URL = r'https?://(?:www\.)?zippcast\.com/video/(?P<id>[0-9a-zA-Z]+)'
|
_VALID_URL = r'https?://(?:www\.)?zippcast\.com/(?:video/|videoview\.php\?.*\bvplay=)(?P<id>[0-9a-zA-Z]+)'
|
||||||
_TESTS = [{
|
_TESTS = [{
|
||||||
|
# m3u8, hq direct link
|
||||||
'url': 'http://www.zippcast.com/video/c9cfd5c7e44dbc29c81',
|
'url': 'http://www.zippcast.com/video/c9cfd5c7e44dbc29c81',
|
||||||
'md5': 'f2aea8659962d9155031aaeac53f7c54',
|
'md5': '5ea0263b5606866c4d6cda0fc5e8c6b6',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': 'c9cfd5c7e44dbc29c81',
|
'id': 'c9cfd5c7e44dbc29c81',
|
||||||
'ext': 'mp4',
|
'ext': 'mp4',
|
||||||
'title': '[Vinesauce] Vinny - Digital Space Traveler',
|
'title': '[Vinesauce] Vinny - Digital Space Traveler',
|
||||||
|
'description': 'Muted on youtube, but now uploaded in it\'s original form.',
|
||||||
'thumbnail': 're:^https?://.*\.jpg$',
|
'thumbnail': 're:^https?://.*\.jpg$',
|
||||||
'uploader': 'vinesauce',
|
'uploader': 'vinesauce',
|
||||||
'description': 'Muted on youtube, but now uploaded in it\'s original form.',
|
|
||||||
'categories': ['Entertainment'],
|
|
||||||
'view_count': int,
|
'view_count': int,
|
||||||
|
'categories': ['Entertainment'],
|
||||||
|
'tags': list,
|
||||||
},
|
},
|
||||||
}, {
|
}, {
|
||||||
|
# f4m, lq ipod direct link
|
||||||
'url': 'http://www.zippcast.com/video/b79c0a233e9c6581775',
|
'url': 'http://www.zippcast.com/video/b79c0a233e9c6581775',
|
||||||
'md5': 'b8631f0cc48ed15387f9179988d0c97c',
|
'only_matching': True,
|
||||||
'info_dict': {
|
}, {
|
||||||
'id': 'b79c0a233e9c6581775',
|
'url': 'http://www.zippcast.com/videoview.php?vplay=c9cfd5c7e44dbc29c81&auto=no',
|
||||||
'ext': 'mp4',
|
'only_matching': True,
|
||||||
'title': 'Battlefield Hardline Trailer',
|
|
||||||
'thumbnail': 're:^https?://.*\.jpg$',
|
|
||||||
'uploader': 'IGXGaming',
|
|
||||||
'description': 'Battlefield Hardline Trailer',
|
|
||||||
'categories': ['Gaming'],
|
|
||||||
'view_count': int,
|
|
||||||
},
|
|
||||||
}]
|
}]
|
||||||
|
|
||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
video_id = self._match_id(url)
|
video_id = self._match_id(url)
|
||||||
webpage = self._download_webpage(url, video_id)
|
|
||||||
|
|
||||||
title = self._html_search_regex(r'title="(.+?)"', webpage, 'title')
|
webpage = self._download_webpage(
|
||||||
uploader = self._html_search_regex(r'http://www.zippcast.com/profile/(.+?)">', webpage, 'uploader')
|
'http://www.zippcast.com/video/%s' % video_id, video_id)
|
||||||
url = self._html_search_regex(r'<source src="(.+?)" type="', webpage, 'url')
|
|
||||||
description = self._html_search_regex(r'<span class="vdescr".+>(.+?)</span>', webpage, 'description')
|
formats = []
|
||||||
thumbnail = self._html_search_regex(r'poster="(.+?)" controls>', webpage, 'thumbnail')
|
video_url = self._search_regex(
|
||||||
categories = self._html_search_regex(r'<a href="http://www.zippcast.com/categories/(.+?)"', webpage, 'categories')
|
r'<source[^>]+src=(["\'])(?P<url>.+?)\1', webpage,
|
||||||
view_count = self._html_search_regex(r'<td align="right"><h3>(.+?) views!', webpage, 'view_count')
|
'video url', default=None, group='url')
|
||||||
|
if video_url:
|
||||||
|
formats.append({
|
||||||
|
'url': video_url,
|
||||||
|
'format_id': 'http',
|
||||||
|
'preference': 0, # direct link is almost always of worse quality
|
||||||
|
})
|
||||||
|
src_url = self._search_regex(
|
||||||
|
r'src\s*:\s*(?:escape\()?(["\'])(?P<url>http://.+?)\1',
|
||||||
|
webpage, 'src', default=None, group='url')
|
||||||
|
ext = determine_ext(src_url)
|
||||||
|
if ext == 'm3u8':
|
||||||
|
formats.extend(self._extract_m3u8_formats(
|
||||||
|
src_url, video_id, 'mp4', entry_protocol='m3u8_native',
|
||||||
|
m3u8_id='hls', fatal=False))
|
||||||
|
elif ext == 'f4m':
|
||||||
|
formats.extend(self._extract_f4m_formats(
|
||||||
|
src_url, video_id, f4m_id='hds', fatal=False))
|
||||||
|
self._sort_formats(formats)
|
||||||
|
|
||||||
|
title = self._og_search_title(webpage)
|
||||||
|
description = self._og_search_description(webpage) or self._html_search_meta(
|
||||||
|
'description', webpage)
|
||||||
|
uploader = self._search_regex(
|
||||||
|
r'<a[^>]+href="https?://[^/]+/profile/[^>]+>([^<]+)</a>',
|
||||||
|
webpage, 'uploader', fatal=False)
|
||||||
|
thumbnail = self._og_search_thumbnail(webpage)
|
||||||
|
view_count = str_to_int(self._search_regex(
|
||||||
|
r'>([\d,.]+) views!', webpage, 'view count', fatal=False))
|
||||||
|
|
||||||
|
categories = re.findall(
|
||||||
|
r'<a[^>]+href="https?://[^/]+/categories/[^"]+">([^<]+),?<',
|
||||||
|
webpage)
|
||||||
|
tags = re.findall(
|
||||||
|
r'<a[^>]+href="https?://[^/]+/search/tags/[^"]+">([^<]+),?<',
|
||||||
|
webpage)
|
||||||
|
|
||||||
return {
|
return {
|
||||||
'id': video_id,
|
'id': video_id,
|
||||||
'title': title,
|
'title': title,
|
||||||
'url': url,
|
|
||||||
'description': description,
|
'description': description,
|
||||||
'uploader': uploader,
|
|
||||||
'thumbnail': thumbnail,
|
'thumbnail': thumbnail,
|
||||||
'categories': [categories],
|
'uploader': uploader,
|
||||||
'view_count': int(view_count.replace(',', '')),
|
'view_count': view_count,
|
||||||
|
'categories': categories,
|
||||||
|
'tags': tags,
|
||||||
|
'formats': formats,
|
||||||
}
|
}
|
||||||
|
|
|
||||||
Loading…
Reference in a new issue