Question

我一直在尝试使用pythons请求模块登录https://angel.co/users/login。问题是，每次运行代码时，我都会收到404状态代码，即使我知道url存在。我认为问题是url中的表单有一个带有相对链接的action属性。我不知道如何解决这个问题，我没有找到解决方案的运气。

以下是我正在使用的代码：

import requests

with requests.Session() as s:
    url = 'https://angel.co/users/login'
    payload = { 'user[email]'    : 'username_here', 
                'user[password]' : 'password_here'}           

    r = s.post(url, data=payload)
    print r.status_code # This is printing 404

以下是我最终使用的代码：

import requests
from bs4 import BeautifulSoup
from login_details import username, password  # This is just a script with my username and password

s=requests.session()

main_url="https://angel.co/login?utm_source=top_nav_home"

s.headers = {'Content-Type'              : 'application/x-www-form-urlencoded',
             'Host'                      : 'angel.co',
             'Origin'                    : 'https://angel.co',
             'User-Agent'                : 'Mozilla/5.0 (Windows NT 6.1; WOW64)' \
                                           'AppleWebKit/537.36 (KHTML, like Gecko) ' \
                                           'Chrome/44.0.2403.157 ' \
                                           'Safari/537.36',
             'Referer'                   : main_url,
             'Upgrade-Insecure-Requests' : '1'} 

response = s.get(main_url)
soup = BeautifulSoup(response.content)

payload={'login_only'         : 'true',
         'user[email]'        : username,
         'user[password]'     : password,
         'authenticity_token' : soup.find(attrs={'name' : 'authenticity_token'})['value'], 
         'utf8'               : '%25E2%259C%2593'} 
#the value of utf8  gets urlencoded once you send the request.

response = s.post("https://angel.co/users/login", data = payload)
print response.status_code

感谢Thothadri和Blackjack。

Answer 1

import re,requests

s=requests.session()

main_url="https://angel.co/login?utm_source=top_nav_home"
headers={"Content-Type":"application/x-www-form-urlencoded","Host":"angel.co","Origin":"https://angel.co"\
,"User-Agent":"Mozilla/5.0 (Windows NT 6.1; WOW64)AppleWebKit/537.36 (KHTML, like Gecko) Chrome/44.0.2403.157 Safari/537.36"} # Mostly you need to pass the headers . Default headers don't work always.  So be careful here

r1=s.get(main_url,headers=headers) #authenticity token is extracted from this page using the regex i mentioned below. This is required when you login to the page
token=re.search("""<input name="authenticity_token" type="hidden" value="(.*?)"[^>]*?>""",r1.text,re.S|re.I)
print token.group(1)
headers["Referer"]="https://angel.co/login?utm_source=top_nav_home"
headers["Upgrade-Insecure-Requests"]="1"
payload={"login_only":"true","user[email]":"youremail","user[password]":"yourpassword","authenticity_token":token.group(1),"utf8":"%25E2%259C%2593"} # the value of utf8  gets urlencoded once you send the request. 
r2=s.post("https://angel.co/users/login",headers=headers,data=payload,cookies=r1.cookies)
print r2.status_code

无法使用请求登录网站

1 个答案: