Spaces:
Runtime error
Runtime error
File size: 4,679 Bytes
05aac64 |
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 |
import os
import re
import sys
import json
import codecs
import tempfile
import requests
from urllib.parse import urlparse, parse_qs, unquote
def parse_url(url):
parsed = urlparse(url)
is_download_link = parsed.path.endswith("/uc")
if not parsed.hostname in ("drive.google.com", "docs.google.com"): return None, is_download_link
file_id = parse_qs(parsed.query).get("id", [None])[0]
if file_id is None:
for pattern in (r"^/file/d/(.*?)/(edit|view)$", r"^/file/u/[0-9]+/d/(.*?)/(edit|view)$", r"^/document/d/(.*?)/(edit|htmlview|view)$", r"^/document/u/[0-9]+/d/(.*?)/(edit|htmlview|view)$", r"^/presentation/d/(.*?)/(edit|htmlview|view)$", r"^/presentation/u/[0-9]+/d/(.*?)/(edit|htmlview|view)$", r"^/spreadsheets/d/(.*?)/(edit|htmlview|view)$", r"^/spreadsheets/u/[0-9]+/d/(.*?)/(edit|htmlview|view)$"):
match = re.match(pattern, parsed.path)
if match:
file_id = match.group(1)
break
return file_id, is_download_link
def get_url_from_gdrive_confirmation(contents):
for pattern in (r'href="(\/uc\?export=download[^"]+)', r'href="/open\?id=([^"]+)"', r'"downloadUrl":"([^"]+)'):
match = re.search(pattern, contents)
if match:
url = match.group(1)
if pattern == r'href="/open\?id=([^"]+)"': url = (codecs.decode("uggcf://qevir.hfrepbagrag.tbbtyr.pbz/qbjaybnq?vq=", "rot13") + url + "&confirm=t&uuid=" + re.search(r'<input\s+type="hidden"\s+name="uuid"\s+value="([^"]+)"', contents).group(1))
elif pattern == r'"downloadUrl":"([^"]+)': url = url.replace("\\u003d", "=").replace("\\u0026", "&")
else: url = codecs.decode("uggcf://qbpf.tbbtyr.pbz", "rot13") + url.replace("&", "&")
return url
match = re.search(r'<p class="uc-error-subcaption">(.*)</p>', contents)
if match: raise Exception(match.group(1))
raise Exception
def _get_session(use_cookies, return_cookies_file=False):
sess = requests.session()
sess.headers.update({"User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_6)"})
cookies_file = os.path.join(os.path.expanduser("~"), ".cache/gdown/cookies.json")
if os.path.exists(cookies_file) and use_cookies:
with open(cookies_file) as f:
for k, v in json.load(f):
sess.cookies[k] = v
return (sess, cookies_file) if return_cookies_file else sess
def gdown_download(url=None, id=None, output=None):
if not (id is None) ^ (url is None): raise ValueError
if id is not None: url = f"{codecs.decode('uggcf://qevir.tbbtyr.pbz/hp?vq=', 'rot13')}{id}"
url_origin = url
sess, cookies_file = _get_session(use_cookies=True, return_cookies_file=True)
gdrive_file_id, is_gdrive_download_link = parse_url(url)
if gdrive_file_id:
url = f"{codecs.decode('uggcf://qevir.tbbtyr.pbz/hp?vq=', 'rot13')}{gdrive_file_id}"
url_origin = url
is_gdrive_download_link = True
while 1:
res = sess.get(url, stream=True, verify=True)
if url == url_origin and res.status_code == 500:
url = f"{codecs.decode('uggcf://qevir.tbbtyr.pbz/bcra?vq=', 'rot13')}{gdrive_file_id}"
continue
os.makedirs(os.path.dirname(cookies_file), exist_ok=True)
with open(cookies_file, "w") as f:
json.dump([(k, v) for k, v in sess.cookies.items() if not k.startswith("download_warning_")], f, indent=2)
if "Content-Disposition" in res.headers: break
if not (gdrive_file_id and is_gdrive_download_link): break
try:
url = get_url_from_gdrive_confirmation(res.text)
except Exception as e:
raise Exception(e)
if gdrive_file_id and is_gdrive_download_link:
content_disposition = unquote(res.headers["Content-Disposition"])
filename_from_url = (re.search(r"filename\*=UTF-8''(.*)", content_disposition) or re.search(r'filename=["\']?(.*?)["\']?$', content_disposition)).group(1).replace(os.path.sep, "_")
else: filename_from_url = os.path.basename(url)
output = os.path.join(output or ".", filename_from_url)
tmp_file = tempfile.mktemp(suffix=tempfile.template, prefix=os.path.basename(output), dir=os.path.dirname(output))
f = open(tmp_file, "ab")
if tmp_file is not None and f.tell() != 0: res = sess.get(url, headers={"Range": f"bytes={f.tell()}-"}, stream=True, verify=True)
print("To:", os.path.abspath(output), file=sys.stderr)
try:
for chunk in res.iter_content(chunk_size=512 * 1024):
f.write(chunk)
if tmp_file: f.close()
finally:
os.rename(tmp_file, output)
sess.close()
return output |