1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
|
# -*- coding: utf-8 -*-
# Copyright 2017-2025 Mike Fährmann
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License version 2 as
# published by the Free Software Foundation.
"""Extractors for https://www.xvideos.com/"""
from .common import GalleryExtractor, Extractor, Message
from .. import text, util
BASE_PATTERN = (r"(?:https?://)?(?:www\.)?xvideos\.com"
r"/(?:profiles|(?:amateur-|model-)?channels)")
class XvideosBase():
"""Base class for xvideos extractors"""
category = "xvideos"
root = "https://www.xvideos.com"
class XvideosGalleryExtractor(XvideosBase, GalleryExtractor):
"""Extractor for user profile galleries on xvideos.com"""
subcategory = "gallery"
directory_fmt = ("{category}", "{user[name]}",
"{gallery[id]} {gallery[title]}")
filename_fmt = "{category}_{gallery[id]}_{num:>03}.{extension}"
archive_fmt = "{gallery[id]}_{num}"
pattern = BASE_PATTERN + r"/([^/?#]+)/photos/(\d+)"
example = "https://www.xvideos.com/profiles/USER/photos/12345"
def __init__(self, match):
self.user, self.gallery_id = match.groups()
url = f"{self.root}/profiles/{self.user}/photos/{self.gallery_id}"
GalleryExtractor.__init__(self, match, url)
def metadata(self, page):
extr = text.extract_from(page)
user = {
"id" : text.parse_int(extr('"id_user":', ',')),
"display": extr('"display":"', '"'),
"sex" : extr('"sex":"', '"'),
"name" : self.user,
}
title = extr('"title":"', '"')
user["description"] = extr(
'<small class="mobile-hide">', '</small>').strip()
tags = extr('<em>Tagged:</em>', '<').strip()
return {
"user": user,
"gallery": {
"id" : text.parse_int(self.gallery_id),
"title": text.unescape(title),
"tags" : text.unescape(tags).split(", ") if tags else [],
},
}
def images(self, page):
results = [
(url, None)
for url in text.extract_iter(
page, '<a class="embed-responsive-item" href="', '"')
]
if not results:
return
while len(results) % 500 == 0:
path = text.rextr(page, ' href="', '"', page.find(">Next</"))
if not path:
break
page = self.request(self.root + path).text
results.extend(
(url, None)
for url in text.extract_iter(
page, '<a class="embed-responsive-item" href="', '"')
)
return results
class XvideosUserExtractor(XvideosBase, Extractor):
"""Extractor for user profiles on xvideos.com"""
subcategory = "user"
categorytransfer = True
pattern = BASE_PATTERN + r"/([^/?#]+)/?(?:#.*)?$"
example = "https://www.xvideos.com/profiles/USER"
def __init__(self, match):
Extractor.__init__(self, match)
self.user = match[1]
def items(self):
url = f"{self.root}/profiles/{self.user}"
page = self.request(url, notfound=self.subcategory).text
data = util.json_loads(text.extr(
page, "xv.conf=", ";</script>"))["data"]
if not isinstance(data["galleries"], dict):
return
if "0" in data["galleries"]:
del data["galleries"]["0"]
galleries = [
{
"id" : text.parse_int(gid),
"title": text.unescape(gdata["title"]),
"count": gdata["nb_pics"],
"_extractor": XvideosGalleryExtractor,
}
for gid, gdata in data["galleries"].items()
]
galleries.sort(key=lambda x: x["id"])
base = f"{self.root}/profiles/{self.user}/photos/"
for gallery in galleries:
url = f"{base}{gallery['id']}"
yield Message.Queue, url, gallery
|
