From e7e90b094a9c65c0336e40cd64878517722f9e21 Mon Sep 17 00:00:00 2001
From: JChris246 <43832407+JChris246@users.noreply.github.com>
Date: Sat, 2 Feb 2019 12:54:22 -0400
Subject: [PATCH 1/3] Fixed extractor #16276
fixed parsing description
fixed parsing uploader
fixed parsing view count
fixed parsing duration,
fixed parsing video_urls
fixed parsing thumbnail
---
youtube_dl/extractor/vporn.py | 48 ++++++++++++++---------------------
1 file changed, 19 insertions(+), 29 deletions(-)
diff --git a/youtube_dl/extractor/vporn.py b/youtube_dl/extractor/vporn.py
index 858ac9e71..9a11ebfc0 100644
--- a/youtube_dl/extractor/vporn.py
+++ b/youtube_dl/extractor/vporn.py
@@ -6,8 +6,8 @@ from .common import InfoExtractor
from ..utils import (
ExtractorError,
parse_duration,
+ parse_resolution,
str_to_int,
- urljoin,
)
@@ -64,47 +64,37 @@ class VpornIE(InfoExtractor):
title = self._html_search_regex(
r'videoname\s*=\s*\'([^\']+)\'', webpage, 'title').strip()
- description = self._html_search_regex(
- r'class="(?:descr|description_txt)">(.*?)',
- webpage, 'description', fatal=False)
- thumbnail = urljoin('http://www.vporn.com', self._html_search_regex(
- r'flashvars\.imageUrl\s*=\s*"([^"]+)"', webpage, 'description',
- default=None))
- uploader = self._html_search_regex(
- r'(?s)Uploaded by:.*?]*>(.+?)',
- webpage, 'uploader', fatal=False)
+ description = self._search_regex(r'[^>]*class="(?:sidebar-box)"[^>]*>[\n](.*?)
',
+ webpage, 'description', fatal=False)
- categories = re.findall(r']*>([^<]+)', webpage)
+ thumbnail = self._search_regex(r']+poster="([^"])"', webpage, 'thumbnail', default=None) or self._search_regex(r'posterurl\s=\s\'([^\']+)', webpage, 'thumbnail', fatal=False)
+
+ uploader = self._search_regex(r'class="avatarname">(.*?)',
+ webpage, 'uploader', fatal=False)
+
+ categories = re.findall(r']*class="tags links"[^>]*>([^<]+)', webpage)
duration = parse_duration(self._search_regex(
- r'Runtime:\s*\s*(\d+ min \d+ sec)',
+ r'class="durat-img"[^>]*>\s*(\d+ min \d+ sec)',
webpage, 'duration', fatal=False))
view_count = str_to_int(self._search_regex(
- r'class="views">([\d,\.]+) [Vv]iews<',
+ r'class="view-count">[\n]([\d,\.]+) [Vv]iews[\n]<',
webpage, 'view count', fatal=False))
+
comment_count = str_to_int(self._html_search_regex(
r"'Comments \(([\d,\.]+)\)'",
webpage, 'comment count', default=None))
formats = []
-
- for video in re.findall(r'flashvars\.videoUrl([^=]+?)\s*=\s*"(https?://[^"]+)"', webpage):
- video_url = video[1]
- fmt = {
- 'url': video_url,
- 'format_id': video[0],
- }
- m = re.search(r'_(?P\d+)x(?P\d+)_(?P\d+)k\.mp4$', video_url)
- if m:
- fmt.update({
- 'width': int(m.group('width')),
- 'height': int(m.group('height')),
- 'vbr': int(m.group('vbr')),
- })
- formats.append(fmt)
-
+ for mobj in re.finditer(r']+src="([^"]+)"[^>]+label="([^"]+)[^>]*>', webpage):
+ f = parse_resolution(mobj.group(2))
+ f.update({
+ 'url': mobj.group(1),
+ 'format_id': mobj.group(2),
+ })
+ formats.append(f)
self._sort_formats(formats)
return {
From 0ace17d199bf9c23f685e9c265432ca4826ff65e Mon Sep 17 00:00:00 2001
From: JChris246 <43832407+JChris246@users.noreply.github.com>
Date: Sat, 2 Feb 2019 12:55:07 -0400
Subject: [PATCH 2/3] Fixed parsing tags #13720
---
youtube_dl/extractor/pornhub.py | 7 +++++--
1 file changed, 5 insertions(+), 2 deletions(-)
diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py
index be93d5d48..1804ba15d 100644
--- a/youtube_dl/extractor/pornhub.py
+++ b/youtube_dl/extractor/pornhub.py
@@ -307,10 +307,13 @@ class PornHubIE(PornHubBaseIE):
r'page_params\.zoneDetails\[([\'"])[^\'"]+\1\]\s*=\s*(?P{[^}]+})',
webpage, 'page parameters', group='data', default='{}'),
video_id, transform_source=js_to_json, fatal=False)
- tags = categories = None
+ tags = None
if page_params:
tags = page_params.get('tags', '').split(',')
- categories = page_params.get('categories', '').split(',')
+
+ categories = []
+ for mobj in re.finditer(r']+Category[^>]*>([^<]+)', webpage):
+ categories.append(mobj.group(1))
return {
'id': video_id,
From dfa1574377727809bea9fa81e8a9e1983d59ce09 Mon Sep 17 00:00:00 2001
From: JChris246 <43832407+JChris246@users.noreply.github.com>
Date: Sat, 2 Feb 2019 12:56:54 -0400
Subject: [PATCH 3/3] added like count to info dict
---
youtube_dl/extractor/pornhd.py | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/youtube_dl/extractor/pornhd.py b/youtube_dl/extractor/pornhd.py
index b52879c7a..534f06277 100644
--- a/youtube_dl/extractor/pornhd.py
+++ b/youtube_dl/extractor/pornhd.py
@@ -85,6 +85,9 @@ class PornHdIE(InfoExtractor):
r"poster'?\s*:\s*([\"'])(?P(?:(?!\1).)+)\1", webpage,
'thumbnail', fatal=False, group='url')
+ like_count = int_or_none(self._search_regex(
+ r'class="save-count">(\d+)<', webpage, 'like_count', fatal=False))
+
return {
'id': video_id,
'display_id': display_id,
@@ -94,4 +97,5 @@ class PornHdIE(InfoExtractor):
'view_count': view_count,
'formats': formats,
'age_limit': 18,
+ 'like_count': like_count,
}