def getCookie():
"""
Get cookie of Leetcode session from Chrome or Firefox
"""
cj = browsercookie.load()
sessionCSRF = ''
sessionID = ''
for cookie in cj:
if cookie.domain == 'leetcode.com' and cookie.name == 'csrftoken':
sessionCSRF = cookie.value
if cookie.domain == '.leetcode.com' and cookie.name == 'LEETCODE_SESSION':
sessionID = cookie.value
if not sessionCSRF or not sessionID:
print('ERROR: Cannot find Leetcode cookies.')
print(
'Are you sure you are logged into leetcode in Chrome or Firefox?')
return
with open(PATH + "config.json", "r") as jsonFile:
data = json.load(jsonFile)
data["LEETCODE_COOKIE"]["sessionCSRF"] = sessionCSRF
data["LEETCODE_COOKIE"]["sessionID"] = sessionID
with open(PATH + "config.json", "w") as jsonFile:
json.dump(data, jsonFile)
print('Leetcode cookies saved.')
def get_cookies_by_domain(domain, lazy):
domains = domain.find(',') > 0 and domain.split(',') or [domain]
cookies = []
for domain in domains:
cookies += [i for i in browsercookie.load()
if i.domain == domain and i.value or\
lazy and i.domain.find(domain)>0 and i.value]
return cookies
def main():
parser = argparse.ArgumentParser(description='Browser cookie inspector')
parser.add_argument(
"-d",
"--domain",
help="Print only cookies with matching domain. "
"If first char is ~, then treat as regexp.",
)
parser.add_argument(
"-n",
"--name",
help="Print only cookies with matching name. "
"If first char is ~, then treat as regexp.",
)
parser.add_argument(
"--path",
help="Print only cookies with matching path. "
"If first char is ~, then treat as regexp.",
)
parser.add_argument(
"--value",
help="Print only cookies with matching value. "
"If first char is ~, then treat as regexp.",
)
parser.add_argument(
"--ignore-expires",
action='store_true',
help="Print matching cookies even if they're expired",
)
parser.add_argument(
"--format",
choices=['netscape', 'lwp', 'json', 'value-only'],
default='netscape',
help="Print matching cookies even if they're expired",
)
args = parser.parse_args()
cookiejar = browsercookie.load()
if args.format == 'lwp':
out_cookiejar = cookielib.LWPCookieJar()
else:
out_cookiejar = cookielib.MozillaCookieJar()
filter_cookiejar(cookiejar, out_cookiejar, args.domain, args.name,
args.path, args.value)
if args.format == 'json':
print(
json.dumps([cookie.__dict__ for cookie in out_cookiejar],
indent=4))
elif args.format in ('netscape', 'lwp'):
out_cookiejar.save(filename='/dev/stdout',
ignore_expires=args.ignore_expires)
elif args.format == 'value-only':
for cookie in out_cookiejar:
print(cookie.value)
def load_cookie(self):
"""load cookies from file or browser."""
cookies = [
i for i in browsercookie.load() if i.domain.find("xueqiu") > 0
]
# load cookies from file
if os.path.exists(api.cookie_file):
sess.cookies.load(ignore_discard=True, ignore_expires=True)
self.logined = True
# load cookies from browser
elif cookies and 'xq_is_login' in [i.name for i in cookies]:
[sess.cookies.set_cookie(ck) for ck in cookies]
self.logined = True
return self.logined
def get_apple_cookie(as_string=False):
"""
Extracts necessary cookies to retrieve Apple API endpoints from
the local user's browsers. This method requires authentication
through keychain, to gain access to the browser cookies.
"""
# Check live cache first
global APPLE_COOKIES_CACHE
if APPLE_COOKIES_CACHE == None:
# Grab cookie jar from all local browsers (will invoke keychain)
# (extra surrounding code to avoid msgs module writes carelessly to stdout)
devnull = open(os.devnull, 'w')
old_stdout = sys.stdout
sys.stdout = devnull
full_cj = browsercookie.load()
sys.stdout = old_stdout
# Retrieve the Apple cookies
apple_cj = [
cookie for cookie in full_cj if cookie.name in APPLE_COOKIES
]
# Update cache
APPLE_COOKIES_CACHE = apple_cj
else:
apple_cj = APPLE_COOKIES_CACHE
# Return as cookie list or string
if as_string:
return "; ".join(
map(lambda c: "{}={}".format(c.name, c.value), apple_cj))
return apple_cj
urlgroup = read_pic_url(bs)
download_pic(urlgroup, path)
if "&page=" in url and int(url[-1]) < maxpagenumber:
print("Ready to download page No.", int(url[-1]) + 1)
read_topic_and_download(url[:-1] + str(int(url[-1]) + 1), path)
else:
print("All pages download COMPLETED")
return
if maxpagenumber > 1:
print("Ready to download page No.2")
read_topic_and_download(url + "&page=2", path)
if __name__ == "__main__":
try:
cookie = browsercookie.load()
except browsercookie.BrowserCookieError:
print("No supported browser found (Chrome or Firefox)")
time.sleep(300)
sys.exit(-1)
while True:
counter += 1
print("\nThe No.%d loop" % counter)
response = requests.get("https://bbs.nga.cn/thread.php?fid=-7",
cookies=cookie)
if not response.ok:
print("Cookie invalid")
time.sleep(300)
continue
def cookies_test3():
get_title = lambda html: re.findall('<title>(.*?)</title>', html, flags=re.DOTALL)[0].strip()
cj = browsercookie.load() # 获取 all available browser cookies
r = requests.get(URL, cookies=cj)
print get_title(r.content)
import logicoma
@logicoma.crawler()
def crawler(urls):
return urls
# To do something eg. on the facebook we need to be logged in...
@crawler.handler(r'//www\.facebook\.com/')
def facebook(client, url):
pass
if __name__ == '__main__':
# Create crawler client with cookies loaded from browser.
import browsercookie
crawler.client = logicoma.Client(cookies=browsercookie.load())
crawler([])