对python抓取需要登录网站数据的方法详解

scrapy.FormRequest

login.py

class LoginSpider(scrapy.Spider):
name = 'login_spider'
start_urls = ['http://www.login.com']
def parse(self, response):
 return [
  scrapy.FormRequest.from_response(
    response,
    # username和password要根据实际页面的表单的name字段进行修改
    formdata={'username': 'your_username', 'password': 'your_password'},
    callback=self.after_login)]
def after_login(self, response):
 # 登录后的代码
 pass

selenium登录获取cookie

get_cookie_by_selenium.py

import pickle
import time
from selenium import webdriver
def get_cookies():
url = 'https://www.test.com'
web_driver = webdriver.Chrome()
web_driver.get(url)
username = web_driver.find_element_by_id('login-email')
username.send_keys('username')
password = web_driver.find_element_by_id('login-password')
password.send_keys('password')
login_button = web_driver.find_element_by_id('login-submit')
login_button.click()
time.sleep(3)
cookies = web_driver.get_cookies()
web_driver.close()
return cookies
if __name__ == '__main__':
cookies = get_cookies()
pickle.dump(cookies, open('cookies.pkl', 'wb'))

获取浏览器cookie(以Ubuntu的Firefox为例)

get_cookie_by_firefox.py

import sqlite3
import pickle
def get_cookie_by_firefox():
cookie_path = '/home/name/.mozilla/firefox/bqtvfe08.default/cookies.sqlite'
with sqlite3.connect(cookie_path) as conn:
 sql = 'select name,value from moz_cookies where baseDomain="test.com"'
 cur = conn.cursor()
 cookies = [{'name': name, 'value': value} for name, value in cur.execute(sql).fetchall()]
 return cookies
if __name__ == '__main__':
cookies = get_cookie_from_firefox()
pickle.dump(cookies, open('cookies.pkl', 'wb'))

scrapy使用获取后的cookie

cookies = pickle.load(open('cookies.pkl', 'rb'))
yield scrapy.Request(url, cookies=cookies, callback=self.parse)

requests使用获取后的cookie

cookies = pickle.load(open('cookies.pkl', 'rb'))
s = requests.Session()
for cookie in cookies:
s.cookies.set(cookie['name'], cookie['value'])

selenium使用获取后的cookie

from selenium import webdriver
cookies = pickle.load(open('cookies.pkl', 'rb'))
w = webdriver.Chrome()
# 直接添加cookie会报错，下面是一种解决方案，可能有更好的
# -- start --
w.get('http://www.test.com')
w.delete_all_cookies()
# -- end --
for cookie in cookies:
w.add_cookie(cookie)

来源：https://blog.csdn.net/wppkind/article/details/53991523