微信sougo中风景关键字搜索文章爬取

最新推荐文章于 2024-04-12 01:44:19 发布

Tina_053

最新推荐文章于 2024-04-12 01:44:19 发布

阅读量724

点赞数 1

分类专栏： Python_爬虫初级

本文链接：https://blog.youkuaiyun.com/weixin_42983055/article/details/88537948

版权

####config 文件的参数

#mongodb的参数
MONGO_URL = 'localhost'
MONGO_DB = 'weixin'
MONGO_TABLE = 'article_data'

POOL_PROXY_URL = 'http://127.0.0.1:5000/get'   # 初始化代理
KEYWORDS= '风景'  # 搜索的内容
base_url = 'https://weixin.sogou.com/weixin?'

MAX_COUNT = 5

from pyquery import PyQuery as pq
import requests
from urllib.parse import urlencode
import pymongo
from config import *

# 设置cookies 保证自己处于登陆状态
headers = {
    'Cookie': 'SMYUV=1543916558046770; IPLOC=CN3210; SUID=824A933D2E18960A000000005C064C19; usid=xOxPgW3N3IoHtGbK; SUV=00EC55C13D934A825C064C1975830150; ld=ZZllllllll2tx6ZPlllllVZpFj9lllll5B23kkllll9lllllxllll5@@@@@@@@@@; LSTMV=247%2C70; LCLKINT=3969; ABTEST=0|1543916582|v1; weixinIndexVisited=1; SNUID=C008D27C41443EE5E68EBAC74227C258; sct=3; JSESSIONID=aaapI9Xh-AseD_U-Nw_Cw; ppinf=5|1544421555|1545631155|dHJ1c3Q6MToxfGNsaWVudGlkOjQ6MjAxN3x1bmlxbmFtZTo0OlRpbmF8Y3J0OjEwOjE1NDQ0MjE1NTV8cmVmbmljazo0OlRpbmF8dXNlcmlkOjQ0Om85dDJsdUJYcHpaSHVCXzRoMG5rQ2tQdS00bGdAd2VpeGluLnNvaHUuY29tfA; pprdig=NsDEAzGvJ1re-8nnesvi4j3YCyLTG05BToQzQjD1RX5uGMNh3s53s1UDapzy3GV_GmE6xp51ZvYjLa1QquTvsy8WOu3WeqMxzq6cHiQy3YsFnn31696RjyfBmDK_uyA1tb