python - BeautifulSoup 登录 - 如何获取具有特定属性和值的 crsf 字段

Question

我正在使用以下脚本对登录 LinkedIn 进行身份验证，然后使用 Beautiful Soup 抓取 HTML。

登录验证没有问题(我看到我的帐户信息)但是当我尝试加载页面时我收到“fs.config({"failureRedirect})”错误。

import cookielib
import os
import urllib
import urllib2
import re
import string
import sys
from bs4 import BeautifulSoup

username = "MY USERNAME"
password = "PASSWORD"

ofile = open('Text_Dump.txt', "wb")

cookie_filename = "parser.cookies.txt"

class LinkedInParser(object):

    def __init__(self, login, password):
        """ Start up... """
        self.login = login
        self.password = password

        # Simulate browser with cookies enabled
        self.cj = cookielib.MozillaCookieJar(cookie_filename)
        if os.access(cookie_filename, os.F_OK):
            self.cj.load()
        self.opener = urllib2.build_opener(
            urllib2.HTTPRedirectHandler(),
            urllib2.HTTPHandler(debuglevel=0),
            urllib2.HTTPSHandler(debuglevel=0),
            urllib2.HTTPCookieProcessor(self.cj)
        )
        self.opener.addheaders = [
            ('User-agent', ('Mozilla/4.0 (compatible; MSIE 6.0; '
                           'Windows NT 5.2; .NET CLR 1.1.4322)'))
        ]

        # Login
        title = self.loginPage()

        sys.stderr.write("Login"+ str(self.login) + "\n")

        #title = self.loadTitle()
        ofile.write(title)

    def loadPage(self, url, data=None):
        """
        Utility function to load HTML from URLs for us with hack to continue despite 404
        """
        # We'll print the url in case of infinite loop
        # print "Loading URL: %s" % url
        try:
            if data is not None:
                response = self.opener.open(url, data)
            else:
                response = self.opener.open(url)
            return ''.join(response.readlines())
        except:
            # If URL doesn't load for ANY reason, try again...
            # Quick and dirty solution for 404 returns because of network problems
            # However, this could infinite loop if there's an actual problem
            return self.loadPage(url, data)

    def loginPage(self):
        """
        Handle login. This should populate our cookie jar.
        """
        html = self.loadPage("https://www.linkedin.com/")
        soup = BeautifulSoup(html)
        csrf = soup.find(id="csrfToken-postModuleForm")['value']

        login_data = urllib.urlencode({
            'session_key': self.login,
            'session_password': self.password,
            'loginCsrfParam': csrf,
        })

        html = self.loadPage("https://www.linkedin.com/uas/login-submit", login_data)

        return

    def loadTitle(self):
        html = self.loadPage("https://www.linkedin.com/")
        soup = BeautifulSoup(html)
        return soup.get_text().encode('utf-8').strip()

parser = LinkedInParser(username, password)
ofile.close()

登录脚本来自: Logging in to LinkedIn with python requests sessions

有什么想法吗？

Answer 1

你的语法错误

首先 - crsf 是一个输入字段而不是 div 标签/检查元素，你会看到

第二 - 要查找具有指定属性和值的标签，您需要使用 .find('type_of_tag' :{'tag_attribute':'value'})

第三种方法是访问指定标签内特定属性的值，您需要使用方括号语法或 .get()

这是您必须替换的代码

html = self.loadPage("https://www.linkedin.com/")
soup = BeautifulSoup(html)
csrf = soup.find('input', {"name" : "csrfToken"})
csrf_token = csrf['value']
print csrf_token