Mercurial > codedump

comparison kemonopartydownloader.py @ 51:6eb6c657c7eb

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 03:02:29 -0400
parents 717feded576e
children ae64a0c8831b
comparison
equal deleted inserted replaced
50:6661f088a504 51:6eb6c657c7eb
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 argparse 2 import argparse
3 import http.cookiejar 3 import http.cookiejar
4 import json
5 import os 4 import os
6 import re 5 import re
7 import requests # pip install requests 6 import requests # pip install requests
8 import time 7 import time
9 import unicodedata
10 import urllib.request
11 from urllib.error import HTTPError 8 from urllib.error import HTTPError
12 9
10
13 def sanitize(filename): 11 def sanitize(filename):
14 return re.sub("^[\w\-. ]+$", "_", filename) 12 return re.sub(r"[\/:*?\"<>|]", "_", filename)
13
15 14
16 def downloadfile(i, x, count): 15 def downloadfile(i, x, count):
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"]: 16 filename = "{4}\\{0}_{1}p_{2}_{3}".format(i["id"], count, sanitize(i["title"]), os.path.basename(x["path"]), output)
18 with req.get(f"https://data.kemono.party{x['path']}", stream=True) as r: 17 if os.path.exists(filename):
18 filesize = os.stat(filename).st_size
19 else:
20 filesize = 0
21 if str(filesize) != req.head(f"https://data.kemono.party{x['path']}").headers["Content-Length"]:
22 print("unfinished download")
23 with req.get(f"https://data.kemono.party{x['path']}", stream=True, headers={"Range": f"bytes={filesize}-"}) as r:
19 r.raise_for_status() 24 r.raise_for_status()
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: 25 with open(filename, "ab") as f:
21 for chunk in r.iter_content(chunk_size=4096): 26 for chunk in r.iter_content(chunk_size=4096):
22 f.write(chunk) 27 f.write(chunk)
23 print("image " + str(count) + " successfully downloaded!") 28 print("image " + str(count) + " successfully downloaded!")
29 return
24 else: 30 else:
25 print("image " + str(count) + " already downloaded!") 31 print("image " + str(count) + " already downloaded!")
32 return
33
26 34
27 parser = argparse.ArgumentParser(description="Downloads (deleted) videos from YTPMV creators") 35 parser = argparse.ArgumentParser(description="Downloads (deleted) videos from YTPMV creators")
28 parser.add_argument("-u", "--url", help="user URL", metavar='<url>', required=True) 36 parser.add_argument("-u", "--url", help="user URL", metavar='<url>', required=True)
29 parser.add_argument("-c", "--cookies", help="", metavar='<url>', required=True) # required because of DDoS-GUARD 37 parser.add_argument("-c", "--cookies", help="", metavar='<url>', required=True) # required because of DDoS-GUARD
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 38 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