github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-07 20:30:41 -05:00
Code Issues Projects Releases Packages Wiki Activity

[pornhd] Detect removed videos and modernize

Browse source
This commit is contained in:
Sergey M․ 2016-06-18 05:42:20 +07:00
parent e6fe993c31
commit 667d96480b
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
1 changed files with 18 additions and 10 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

28
youtube_dl/extractor/pornhd.py
View file

@ -1,10 +1,10 @@
from __future__ import unicode_literals
import re
import json
from .common import InfoExtractor
from ..utils import (
ExtractorError,
int_or_none,
js_to_json,
)
@ -37,17 +37,17 @@ def _real_extract(self, url):
title = self._html_search_regex(
[r'<span[^>]+class=["\']video-name["\'][^>]*>([^<]+)',
r'<title>(.+?) - .*?[Pp]ornHD.*?</title>'], webpage, 'title')
description = self._html_search_regex(
r'<(div|p)[^>]+class="description"[^>]*>(?P<value>[^<]+)</\1',
webpage, 'description', fatal=False, group='value')
view_count = int_or_none(self._html_search_regex(
r'(\d+) views\s*<', webpage, 'view count', fatal=False))
thumbnail = self._search_regex(
r"'poster'\s*:\s*'([^']+)'", webpage, 'thumbnail', fatal=False)
sources = json.loads(js_to_json(self._search_regex(
sources = self._parse_json(js_to_json(self._search_regex(
r"(?s)'sources'\s*:\s*(\{.+?\})\s*\}[;,)]",
webpage, 'sources')))
webpage, 'sources', default='{}')), video_id)
if not sources:
message = self._html_search_regex(
r'(?s)<(div|p)[^>]+class="no-video"[^>]*>(?P<value>.+?)</\1',
webpage, 'error message', group='value')
raise ExtractorError('%s said: %s' % (self.IE_NAME, message), expected=True)
formats = []
for format_id, video_url in sources.items():
if not video_url:
@ -61,6 +61,14 @@ def _real_extract(self, url):
})
self._sort_formats(formats)
description = self._html_search_regex(
r'<(div|p)[^>]+class="description"[^>]*>(?P<value>[^<]+)</\1',
webpage, 'description', fatal=False, group='value')
view_count = int_or_none(self._html_search_regex(
r'(\d+) views\s*<', webpage, 'view count', fatal=False))
thumbnail = self._search_regex(
r"'poster'\s*:\s*'([^']+)'", webpage, 'thumbnail', fatal=False)
return {
'id': video_id,
'display_id': display_id,