mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-11-21 20:46:36 -05:00
[spankwire] Improve and modernize
This commit is contained in:
parent
1cf563d84b
commit
9767726b66
1 changed files with 41 additions and 24 deletions
|
@ -1,6 +1,5 @@
|
|||
from __future__ import unicode_literals
|
||||
|
||||
import os
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
|
@ -8,23 +7,27 @@
|
|||
compat_urllib_parse_urlparse,
|
||||
compat_urllib_request,
|
||||
compat_urllib_parse,
|
||||
unified_strdate,
|
||||
str_to_int,
|
||||
int_or_none,
|
||||
)
|
||||
from ..aes import (
|
||||
aes_decrypt_text
|
||||
)
|
||||
from ..aes import aes_decrypt_text
|
||||
|
||||
|
||||
class SpankwireIE(InfoExtractor):
|
||||
_VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>spankwire\.com/[^/]*/video(?P<videoid>[0-9]+)/?)'
|
||||
_VALID_URL = r'https?://(?:www\.)?(?P<url>spankwire\.com/[^/]*/video(?P<videoid>[0-9]+)/?)'
|
||||
_TEST = {
|
||||
'url': 'http://www.spankwire.com/Buckcherry-s-X-Rated-Music-Video-Crazy-Bitch/video103545/',
|
||||
'file': '103545.mp4',
|
||||
'md5': '1b3f55e345500552dbc252a3e9c1af43',
|
||||
'md5': '8bbfde12b101204b39e4b9fe7eb67095',
|
||||
'info_dict': {
|
||||
"uploader": "oreusz",
|
||||
"title": "Buckcherry`s X Rated Music Video Crazy Bitch",
|
||||
"description": "Crazy Bitch X rated music video.",
|
||||
"age_limit": 18,
|
||||
'id': '103545',
|
||||
'ext': 'mp4',
|
||||
'title': 'Buckcherry`s X Rated Music Video Crazy Bitch',
|
||||
'description': 'Crazy Bitch X rated music video.',
|
||||
'uploader': 'oreusz',
|
||||
'uploader_id': '124697',
|
||||
'upload_date': '20070508',
|
||||
'age_limit': 18,
|
||||
}
|
||||
}
|
||||
|
||||
|
@ -37,13 +40,26 @@ def _real_extract(self, url):
|
|||
req.add_header('Cookie', 'age_verified=1')
|
||||
webpage = self._download_webpage(req, video_id)
|
||||
|
||||
video_title = self._html_search_regex(r'<h1>([^<]+)', webpage, 'title')
|
||||
video_uploader = self._html_search_regex(
|
||||
r'by:\s*<a [^>]*>(.+?)</a>', webpage, 'uploader', fatal=False)
|
||||
thumbnail = self._html_search_regex(
|
||||
r'flashvars\.image_url = "([^"]+)', webpage, 'thumbnail', fatal=False)
|
||||
title = self._html_search_regex(r'<h1>([^<]+)', webpage, 'title')
|
||||
description = self._html_search_regex(
|
||||
r'<div\s+id="descriptionContent">([^<]+)<', webpage, 'description', fatal=False)
|
||||
thumbnail = self._html_search_regex(
|
||||
r'flashvars\.image_url = "([^"]+)', webpage, 'thumbnail', fatal=False)
|
||||
|
||||
uploader = self._html_search_regex(
|
||||
r'by:\s*<a [^>]*>(.+?)</a>', webpage, 'uploader', fatal=False)
|
||||
uploader_id = self._html_search_regex(
|
||||
r'by:\s*<a href="/Profile.aspx?.*?UserId=(\d+).*?"', webpage, 'uploader id', fatal=False)
|
||||
upload_date = self._html_search_regex(r'</a> on (.+?) at \d+:\d+', webpage, 'upload date', fatal=False)
|
||||
if upload_date:
|
||||
upload_date = unified_strdate(upload_date)
|
||||
|
||||
view_count = self._html_search_regex(
|
||||
r'<div id="viewsCounter"><span>([^<]+)</span> views</div>', webpage, 'view count', fatal=False)
|
||||
if view_count:
|
||||
view_count = str_to_int(view_count)
|
||||
comment_count = int_or_none(self._html_search_regex(
|
||||
r'<span id="spCommentCount">\s*(\d+)</span> Comments</div>', webpage, 'comment count', fatal=False))
|
||||
|
||||
video_urls = list(map(compat_urllib_parse.unquote , re.findall(r'flashvars\.quality_[0-9]{3}p = "([^"]+)', webpage)))
|
||||
if webpage.find('flashvars\.encrypted = "true"') != -1:
|
||||
|
@ -53,16 +69,13 @@ def _real_extract(self, url):
|
|||
formats = []
|
||||
for video_url in video_urls:
|
||||
path = compat_urllib_parse_urlparse(video_url).path
|
||||
extension = os.path.splitext(path)[1][1:]
|
||||
format = path.split('/')[4].split('_')[:2]
|
||||
resolution, bitrate_str = format
|
||||
format = "-".join(format)
|
||||
height = int(resolution.rstrip('P'))
|
||||
tbr = int(bitrate_str.rstrip('K'))
|
||||
|
||||
height = int(resolution.rstrip('Pp'))
|
||||
tbr = int(bitrate_str.rstrip('Kk'))
|
||||
formats.append({
|
||||
'url': video_url,
|
||||
'ext': extension,
|
||||
'resolution': resolution,
|
||||
'format': format,
|
||||
'tbr': tbr,
|
||||
|
@ -75,10 +88,14 @@ def _real_extract(self, url):
|
|||
|
||||
return {
|
||||
'id': video_id,
|
||||
'uploader': video_uploader,
|
||||
'title': video_title,
|
||||
'thumbnail': thumbnail,
|
||||
'title': title,
|
||||
'description': description,
|
||||
'thumbnail': thumbnail,
|
||||
'uploader': uploader,
|
||||
'uploader_id': uploader_id,
|
||||
'upload_date': upload_date,
|
||||
'view_count': view_count,
|
||||
'comment_count': comment_count,
|
||||
'formats': formats,
|
||||
'age_limit': age_limit,
|
||||
}
|
||||
|
|
Loading…
Reference in a new issue