python模拟Facebook的requests方式登录（python采集帖子信息）

需求

工作中需要采集FB上的帖子信息，目前FB只有小组中的帖子支持公开采集，其它个人的帖子需要登录上FB后方能采集，而分析登录的过程发现，post的请求体中有一段加密的信息，如下所示：

1. 请求的url为：https://www.facebook.com/
2. 输入用户名密码后会跳转到 https://www.facebook.com/login/device-based/regular/login/?login_attempt=1&lwv=110
3. 通过上面的url，可以发现是一个post请求，然后需要的参数为：
   
   发现只有email参数，并没有发现password，但是通过分析第一步的url的html，可以发现这样一段：
   

开始处理

# -*- coding: utf-8 -*-

import requests
import re
from bs4 import BeautifulSoup
from urllib.parse import urljoin

base_url = 'https://www.facebook.com'

user_agent = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) " \
             "Chrome/76.0.3809.87 Safari/537.36"
cookie = 'locale=en_US;'
headers = {
    'user-agent': user_agent,
    'accept-language': 'en-US,en;q=0.5',
    'cookie': cookie
}

session = requests.session()
session.headers.update(headers)
response = session.get(url=base_url)
html = response.text
pattern = re.compile(r'<form.*?action=\"(.*?)\"')
action = pattern.findall(html, re.S)
action_url = [url for url in action if 'login/device-based' in url]
if action_url:
    action_url = action_url[0].replace('&amp;','&')
else:
    soup = BeautifulSoup(html, 'html.parser')
    form = soup.find('form', attrs={'method': 'post', 'id': 'login_form', 'action':True})
    if form:
        action_url = form['action'].replace('&amp;','&')
if not action_url:
    print('Get Login Url Error')
    action_url = 'https://www.facebook.com/login/device-based/regular/login/?login_attempt=1&lwv=110'
login_url = urljoin(base_url, action_url)
data = {
    'email': '你的邮箱或者手机号',
    'pass': '密码'
}
r = session.post(login_url, data=data)
cookies = requests.utils.dict_from_cookiejar(session.cookies)
print(cookies)

可以通过访问m.facebook.com来登录，与上面的方式一模一样：

# -*- coding: utf-8 -*-

from bs4 import BeautifulSoup
from urllib.parse import urljoin
import requests
import re

base_url = 'https://m.facebook.com'

user_agent = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) " \
             "Chrome/76.0.3809.87 Safari/537.36"
cookie = 'locale=en_US;'
headers = {
    'user-agent': user_agent,
    'accept-language': 'en-US,en;q=0.5',
    'cookie': cookie
}

session = requests.session()
session.headers.update(headers)
response = session.get(url=base_url)
html = response.text
pattern = re.compile(r'<form.*?action=\"(.*?)\"')
action = pattern.findall(html, re.S)
action_url = [url for url in action if 'login/device-based' in url]
if action_url:
    action_url = action_url[0].replace('&amp;','&')
else:
    soup = BeautifulSoup(html, 'html.parser')
    form = soup.find('form', attrs={'method': 'post', 'id': 'login_form', 'action':True})
    if form:
        action_url = form['action'].replace('&amp;','&')
if not action_url:
    print('Get Login Url Error')
    action_url = '/login/device-based/regular/login/?refsrc=https%3A%2F%2Fm.facebook.com%2F&lwv=100&refid=8'
login_url = urljoin(base_url, action_url)
data = {
    'email': '你的邮箱或者手机号',
    'pass': '密码'
}
r = session.post(login_url, data=data)
cookies = requests.utils.dict_from_cookiejar(session.cookies)
print(cookies)

本文地址：https://blog.csdn.net/minghao2164/article/details/107077621