scrapy 设置cookie池

Posted 2020-10-15 dahu的菜园子

代码已经很详细了，可以直接拿来使用了。

包含了：

• 从网页获取cookie
• 存入mongodb
• 定期删除cookie
• scrapy中间件对cookie池的取用

#!/usr/bin/python
#coding=utf-8
#__author__=‘dahu‘
#data=2017-
# 
import requests
import time
from pymongo import MongoClient
import cookielib
import urllib2
from bson.objectid import ObjectId
url = ‘https://www.so.com‘
# url = ‘https://cn.bing.com/translator‘
client = MongoClient(‘localhost‘, 27017)
db = client[‘save_cookie‘]
collection = db[‘san60cookie‘]

def get_header():
    header={
        "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
        "Accept-Encoding": "gzip, deflate, br",
        "Accept-Language": "en-US,en;q=0.8,zh-CN;q=0.6,zh;q=0.4",
        "Cache-Control": "max-age=0",
        "Connection": "keep-alive",
        "Host": "www.so.com",
        "Upgrade-Insecure-Requests": "1",
        "User-Agent": "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3112.101 Safari/537.36",
    }
    return headerdef get_cookie_lib():
    cookie = cookielib.CookieJar()
    handler = urllib2.HTTPCookieProcessor(cookie)
    opener = urllib2.build_opener(handler)
    response = opener.open(url)
    # for item in cookie:
    #     print "%s : %s" % (item.name, item.value)
    cookie_dict = {}
    for cook in cookie:
        cookie_dict[cook.name] = cook.value
    return cookie_dict


def save_cookie_into_mongodb(cookie):
    print ‘insert‘
    insert_data = {}
    insert_data[‘cookie‘] = cookie
    insert_data[‘insert_time‘] = time.strftime(‘%Y-%m-%d %H:%M:%S‘)
    insert_data[‘request_url‘]=url
    insert_data[‘insert_timestamp‘] = time.time()
    collection.insert(insert_data)


def delete_timeout_cookie(request_url):
    time_out = 300
    for data in collection.find({‘request_url‘:request_url}):
        if (time.time() - data.get(‘insert_timestamp‘)) > time_out:
            print ‘delete: %s‘ % data.get(‘_id‘)
            collection.delete_one({‘_id‘: ObjectId(data.get(‘_id‘))})
　　　　　　　#这里有疑问的话可以参考http://api.mongodb.com/python/current/tutorial.html#querying-by-objectid
　

def get_cookie_from_mongodb():
    cookies = [data.get(‘cookie‘) for data in collection.find()]
    return cookies

if __name__ == ‘__main__‘:
    num=0
    while 1:
        if num == 2:
            print ‘deleting‘
            delete_timeout_cookie(url)
            num = 0
        else:
            cookie = get_cookie_lib()
            save_cookie_into_mongodb(cookie)
            num += 1
            time.sleep(5)

 

对应的middleware文件，可以写成这样

import random
class CookiesMiddleware(object):
    def process_request(self,request,spider):
        cookie = random.choice(get_cookie_from_mongodb())
        request.cookies = cookie