Logging in to LinkedIn with python requests sessions

Question

I\'m trying to log into LinkedIn using Python requests:

import sys
import requests
from BeautifulSoup import BeautifulSoup


payload={
    \'session-key\' :          


        

Answer 1

2020 version of @garromark's accepted solution:

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

username = ""
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/5.0')
        ]

        # 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)
            content = ''.join([str(l) for l in response.readlines()])
            print("Page loaded: %s \n Content: %s \n" % (url, content))
            return content
        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
            print("Exception on %s load: %s" % (url, e))
            # 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/login")
        loginCsrfParam = soup.find("input", {"name": "loginCsrfParam"})['value']
        csrfToken = soup.find("input", {"name": "csrfToken"})['value']
        sIdString = soup.find("input", {"name": "sIdString"})['value']
        print("loginCsrfParam: %s" % loginCsrfParam)
        print("csrfToken: %s" % csrfToken)
        print("sIdString: %s" % sIdString)
        login_data = urllib.parse.urlencode({
            'session_key': self.login,
            'session_password': self.password,
            'loginCsrfParam': loginCsrfParam,
            'csrfToken': csrfToken,
            'sIdString': sIdString
        }).encode('utf8')

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

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


parser = LinkedInParser(username, password)