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
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
|
#!/bin/env python
import os
import re
import requests
import sys
import csv
import lxml
import json
from urllib.parse import urlparse
from pathlib import Path
import lxml.html
import argparse
DEBUG_MODE = True
dirOut = Path("r34")
class Spinner(object):
def __init__(self):
self.SPINNER = ['⠋', '⠙', '⠹', '⠸', '⠼', '⠴', '⠦', '⠧', '⠇', '⠏']
self.SPINNER_status = 1
def __call__(self):
self.SPINNER_status = (self.SPINNER_status + 1) % len(self.SPINNER)
return self.SPINNER[self.SPINNER_status]
quickSpinner = Spinner()
def pretty_print_Request_header(req):
print(f"{req.method} {req.url}")
for k, v in req.headers.items():
print(f"{k}: {v}")
def outputFileFromURL(url):
u = urlparse(url)
name = Path(u.path).name
alreadyExists = False
finalDest = dirOut.joinpath(Path(name))
i = 1
while finalDest.exists():
alreadyExists = True
s_name = Path(u.path).stem
s_suffix = Path(u.path).suffix
next_name = f"{s_name}_{i}{s_suffix}"
i += 1
finalDest = dirOut.joinpath(Path(next_name))
return alreadyExists, str(finalDest)
def downloadURL(s, url, idLink, output, headers={}):
r = s.get(url, stream=True, headers=headers)
u = urlparse(url)
if r.ok:
if DEBUG_MODE:
print(f"\n{url} >> {output}")
print(f"\r⬇️ {Path(u.path).name}", end='')
try:
with open(output, "wb") as f:
print(f"\r⬇️ {quickSpinner()} {Path(u.path).name}", end='')
chunk_size = 4 * 1024
for chunk in r.iter_content(chunk_size=chunk_size):
f.write(chunk)
print(f"\rDownloaded {Path(u.path).name} - {idLink}")
except Exception as e:
print(f"\r☠️ error {Path(u.path).name} - {idLink}")
if DEBUG_MODE:
print(e)
def downloadFromItems(items, s, u):
replace = {
'mov480.': 'mov.',
'mov720.': 'mov.',
'mov256.': 'mov.',
'pic256.': 'pic.',
'pic480.': 'pic.',
'pic720.': 'pic.',
'picsmall.': 'pic.'
}
for item in items:
isDownloaded = False
isVideo = item['duration'] is not None
for file in item['imageLinks']:
url = file['url']
if isVideo and not url.endswith('.mp4'):
continue
for r,t in replace.items():
if r in url:
url = url.replace(r, t)
e, outputFile = outputFileFromURL(url)
if e:
print("Already downloaded")
return
headers = {"Referer": f"{u.scheme}://{u.hostname}/"}
headers['Accept'] = "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,*/*;q=0.8"
headers['Accept-encoding'] = "gzip, deflate, br"
downloadURL(s, url, "???", outputFile, headers)
isDownloaded = True
break
if isDownloaded:
break
def downloadImagesFromPlaylist(index, link):
s = requests.Session()
u = urlparse(link)
p = Path(u.path)
playlistId = p.stem
print(f"Link n°{index} - {playlistId}")
nbPage = 0
while True:
urlPlaylistFormat = f"https://rule34.world/api/playlist-item?playlistId={playlistId}&Skip={nbPage*60}&Take=60&DisableTotal=true"
resp = s.get(urlPlaylistFormat)
if resp.ok and resp.status_code == 200:
data = json.loads(resp.content)
if len(data['items']) > 0:
print(f"Ok ! {len(data['items'])}")
downloadFromItems(data['items'], s, u)
else:
break
nbPage += 1
return
try:
html = lxml.html.fromstring(resp.content)
boxes = html.cssselect("div.box a.boxInner")
for box in boxes:
url = box.attrib['href']
url = f"{u.scheme}://{u.hostname}{url}"
downloadImageFromPage(index, url)
except Exception as e:
print(f"\r☠️ error {Path(u.path).name} - {idLink}")
if DEBUG_MODE:
print(e)
def downloadImagesFromUserboard(index, link):
s = requests.Session()
u = urlparse(link)
p = Path(u.path)
boardName = p.stem
print(f"Link n°{index} - {boardName}", end='')
resp = s.get(link)
findImagesRegex = re.compile('<img class="image" src="/images/t.png" data-src="(.+)\?width=300"')
if resp.ok and resp.status_code == 200:
for subIndex, urlImg in enumerate(findImagesRegex.findall(resp.content.decode('utf8'))):
match = re.search(r'(\d{7,})', urlImg)
if not match:
return
e, outputFile = outputFileFromURL(urlImg)
if e:
print("Already downloaded")
return
if DEBUG_MODE:
print(f"\n{urlImg} >> {outputFile}")
idLink = match.group(1)
print(f"Link n°{index}.{subIndex} - {boardName}>{idLink}", end='')
headers = {"Referer": f"{u.scheme}://{u.hostname}/"}
headers['Accept'] = "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,*/*;q=0.8"
headers['Accept-encoding'] = "gzip, deflate, br"
downloadURL(s, urlImg, idLink, outputFile, headers)
def downloadVideoFromSource(index, urlBase, idVid, urlVideo):
s = requests.Session()
print(f"Link n°{index} - Vidéo {idVid}", end='')
print(f"Link : {urlVideo} !", end='\n')
u = urlparse(urlBase)
urlVideo = urlVideo.replace('mov480', 'mov')
e, outputFile = outputFileFromURL(urlVideo)
if e:
print("Already downloaded")
return
headers = {"Referer": f"{u.scheme}://{u.hostname}/"}
headers['Accept'] = "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,*/*;q=0.8"
headers['Accept-encoding'] = "gzip, deflate, br"
print(f"Download to {outputFile}")
downloadURL(s, urlVideo, idVid, outputFile, headers)
def downloadImageFromPage(index, link):
s = requests.Session()
match = re.search(r'(\d{6,})', link)
if not match:
return
idLink = match.group(1)
print(f"Link n°{index} - {idLink}\n", end='')
resp = s.get(link)
if resp.ok and resp.status_code == 200:
try:
html = lxml.html.fromstring(resp.content)
imgs = html.cssselect("img.img.shadow-base")
if len(imgs) == 0:
vids = html.cssselect("video.video.shadow-base source")
if len(vids) > 0:
url = vids[0].attrib['src']
u = urlparse(link)
if url[0] == '/':
url = f"{u.scheme}://{u.hostname}{url}"
downloadVideoFromSource(index, link, idLink, url)
else:
img = imgs[0]
if 'src' in img.attrib:
url = img.attrib['src']
u = urlparse(link)
if url[0] == '/':
url = f"{u.scheme}://{u.hostname}{url}"
url = url.replace('picsmall', 'pic')
e, outputFile = outputFileFromURL(url)
if e:
print("Already downloaded")
return
headers = {"Referer": f"{u.scheme}://{u.hostname}/"}
headers['Accept'] = "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,*/*;q=0.8"
headers['Accept-encoding'] = "gzip, deflate, br"
downloadURL(s, url, idLink, outputFile, headers)
except:
print(f"\r☠️ error {Path(u.path).name} - {idLink}")
if DEBUG_MODE:
print(e)
return
def main():
parser = argparse.ArgumentParser()
parser.add_argument("-d", "--directory", help="Output directory")
parser.add_argument('files', nargs=argparse.REMAINDER)
args = parser.parse_args()
if args.directory:
global dirOut
dirOut = Path(args.directory)
if not dirOut.exists():
print(f"Output dir \"{dirOut}\" doesn't exists")
return
if not dirOut.is_dir():
print(f"Output dir \"{dirOut}\" isn't a directory")
return
for file in args.files:
with open(file) as f_listLink:
for index, link in enumerate(f_listLink.read().split()):
if '/post/' in link:
downloadImageFromPage(index, link)
if '/user/' in link:
downloadImagesFromUserboard(index, link)
if '/playlists/' in link:
downloadImagesFromPlaylist(index, link)
if __name__ == "__main__":
main()
|