使用python请求会话登录LinkedIn

Question

我正在尝试使用Python请求登录LinkedIn:

import sys
import requests
from BeautifulSoup import BeautifulSoup


payload={
    'session-key' : 'user@email.com',
    'session-password' : 'password'
}

URL='https://www.linkedin.com/uas/login-submit'
s=requests.session()
s.post(URL,data=payload)

r=s.get('http://www.linkedin.com/nhome')
soup = BeautifulSoup(r.text)
print soup.find('title')

我似乎无法使用此方法登录.我甚至尝试在有效载荷中使用csrf等,但不是会话应该为你处理吗？

关于最后一行的注意事项:我使用标题来检查我是否已成功登录.(如果我已登录,我应该看到"欢迎!| LinkedIn",而不是我看到"世界上最大的专业网络| LinkedIn"

我错过了什么吗？

Answer 1

我修改了一个网页抓取模板,用于我的大多数基于Python的抓取需求,以满足您的需求.已验证它可以使用我自己的登录信息.

它的工作方式是模仿浏览器并维护存储用户会话的cookieJar.得到它也可以和BeautifulSoup一起使用.

注意:这是Python2版本.我在下面通过请求添加了一个有效的Python3示例.

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

username = "user@email.com"
password = "password"

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
        self.loginPage()

        title = self.loadTitle()
        print title

        self.cj.save()


    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="loginCsrfParam-login")['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/feed/")
        soup = BeautifulSoup(html)
        return soup.find("title")

parser = LinkedInParser(username, password)

2014年6月19日更新:从主页添加了CSRF令牌解析,以便在更新的登录过程中使用.

2015年7月23日更新:在此处添加Python 3示例.基本上需要替换库位置并删除已弃用的方法.它没有完美的格式或任何东西,但它的功能.对不起急事.最后,原则和步骤是相同的​​.

import http.cookiejar as cookielib
import os
import urllib
import re
import string
from bs4 import BeautifulSoup

username = "user@email.com"
password = "password"

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 = urllib.request.build_opener(
            urllib.request.HTTPRedirectHandler(),
            urllib.request.HTTPHandler(debuglevel=0),
            urllib.request.HTTPSHandler(debuglevel=0),
            urllib.request.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
        self.loginPage()

        title = self.loadTitle()
        print(title)

        self.cj.save()


    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([str(l) for l in response.readlines()])
        except Exception as e:
            # 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 loadSoup(self, url, data=None):
        """
        Combine loading of URL, HTML, and parsing with BeautifulSoup
        """
        html = self.loadPage(url, data)
        soup = BeautifulSoup(html, "html5lib")
        return soup

    def loginPage(self):
        """
        Handle login. This should populate our cookie jar.
        """
        soup = self.loadSoup("https://www.linkedin.com/")
        csrf = soup.find(id="loginCsrfParam-login")['value']
        login_data = urllib.parse.urlencode({
            'session_key': self.login,
            'session_password': self.password,
            'loginCsrfParam': csrf,
        }).encode('utf8')

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

    def loadTitle(self):
        soup = self.loadSoup("https://www.linkedin.com/feed/")
        return soup.find("title")

parser = LinkedInParser(username, password)

Answer 2

这是一个更简单的版本.

import requests
from bs4 import BeautifulSoup

client = requests.Session()

HOMEPAGE_URL = 'https://www.linkedin.com'
LOGIN_URL = 'https://www.linkedin.com/uas/login-submit'

html = client.get(HOMEPAGE_URL).content
soup = BeautifulSoup(html, "html.parser")
csrf = soup.find(id="loginCsrfParam-login")['value']

login_information = {
    'session_key':'Login',
    'session_password':'Password',
    'loginCsrfParam': csrf,
}

client.post(LOGIN_URL, data=login_information)

client.get('Any_Linkedin_URL')