Mercurial > codedump

comparison kemonopartydownloader.py @ 49:717feded576e

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Update kemonopartydownloader.py committer: GitHub <noreply@github.com>
author Paper <37962225+mrpapersonic@users.noreply.github.com>
date Sat, 31 Jul 2021 02:24:22 -0400
parents 522ad91a230e
children 6eb6c657c7eb
comparison
equal deleted inserted replaced
48:267e3e6bba63 49:717feded576e
1 # example args.url: https://kemono.party/fanbox/user/5375435/post/2511461 1 # example args.url: https://kemono.party/fanbox/user/5375435/post/2511461
2 import json
3 import urllib.request
4 import os
5 import requests # pip install requests
6 import argparse 2 import argparse
7 import http.cookiejar 3 import http.cookiejar
4 import json
5 import os
6 import re
7 import requests # pip install requests
8 import time 8 import time
9 import unicodedata
10 import urllib.request
9 from urllib.error import HTTPError 11 from urllib.error import HTTPError
10 12
13 def sanitize(filename):
14 return re.sub("^[\w\-. ]+$", "_", filename)
15
11 def downloadfile(i, x, count): 16 def downloadfile(i, x, count):
12 with req.get(f"https://data.kemono.party{x['path']}", stream=True) as r: 17 if not os.path.exists("{4}\\{0}_{1}p_{2}_{3}".format(i["id"], count, sanitize(i["title"]), os.path.basename(x["path"]), output)) or str(os.stat("{4}\\{0}_{1}p_{2}_{3}".format(i["id"], count, sanitize(i["title"]), os.path.basename(x["path"]), output)).st_size) != req.head(f"https://data.kemono.party{x['path']}").headers["Content-Length"]:
13 r.raise_for_status() 18 with req.get(f"https://data.kemono.party{x['path']}", stream=True) as r:
14 if not os.path.exists("{4}\\{0}_{1}p_{2}_{3}".format(i["id"], count, i["title"], os.path.basename(x["path"]), output)): 19 r.raise_for_status()
15 with open("{4}\\{0}_{1}p_{2}_{3}".format(i["id"], count, i["title"], os.path.basename(x["path"]), output), "wb") as f: 20 with open("{4}\\{0}_{1}p_{2}_{3}".format(i["id"], count, sanitize(i["title"]), os.path.basename(x["path"]), output), "wb") as f:
16 for chunk in r.iter_content(chunk_size=4096): 21 for chunk in r.iter_content(chunk_size=4096):
17 f.write(chunk) 22 f.write(chunk)
18 print("image {0} successfully downloaded!".format(count)) 23 print("image " + str(count) + " successfully downloaded!")
19 else: 24 else:
20 print("image {0} already downloaded! skipping...".format(count)) 25 print("image " + str(count) + " already downloaded!")
21 26
22 parser = argparse.ArgumentParser(description="Downloads (deleted) videos from YTPMV creators") 27 parser = argparse.ArgumentParser(description="Downloads (deleted) videos from YTPMV creators")
23 parser.add_argument("-u", "--url", help="user URL", metavar='<url>', required=True) 28 parser.add_argument("-u", "--url", help="user URL", metavar='<url>', required=True)
24 parser.add_argument("-c", "--cookies", help="", metavar='<url>', required=True) # required because of DDoS-GUARD 29 parser.add_argument("-c", "--cookies", help="", metavar='<url>', required=True) # required because of DDoS-GUARD
25 parser.add_argument("-p", "--proxy", help="proxy\n supported types: http, https, socks5 (requires pysocks)", metavar='<url>') # SOCKS proxy support is through PySocks - pip install pysocks 30 parser.add_argument("-p", "--proxy", help="proxy\n supported types: http, https, socks5 (requires pysocks)", metavar='<url>') # SOCKS proxy support is through PySocks - pip install pysocks
81 print(i["id"]) 86 print(i["id"])
82 post = i["id"] 87 post = i["id"]
83 count = 0 88 count = 0
84 for x in i["attachments"]: 89 for x in i["attachments"]:
85 count += 1 90 count += 1
86 if os.path.exists("{4}\\{0}_{1}p_{2}_{3}".format(int(i["id"]) - 1, count, i["title"], os.path.basename(x["path"]), output)): 91 while not os.path.exists("{4}\\{0}_{1}p_{2}_{3}".format(int(i["id"]) - 1, count, sanitize(i["title"]), os.path.basename(x["path"]), output)):
87 print("image {0} already downloaded! skipping...".format(count))
88 continue
89 while not os.path.exists("{4}\\{0}_{1}p_{2}_{3}".format(int(i["id"]) - 1, count, i["title"], os.path.basename(x["path"]), output)):
90 try: 92 try:
91 downloadfile(i, x, count) 93 downloadfile(i, x, count)
92 break 94 break
93 except HTTPError: 95 except HTTPError:
94 time.sleep(10) 96 time.sleep(10)