requests爬虫搜狗微信公众号

# -*- coding: utf-8 -*-
"""
Spyder Editor

This is a temporary script file.
"""

import requests
from requests.exceptions import ConnectionError
from pyquery import PyQuery as pq

#keyword = '风景'

base_url = 'https://weixin.sogou.com/weixin?query={}&s_from=input&type=2&page={}&ie=utf8'

headers = {
        'Cookie':'SMYUV=156867c543fede325; sct=2',
        'Host':'weixin.sogou.com',
        'Upgrade-Insecure-Requests':'1',
        'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/77.0.3865.120 Safari/537.36'
        }

#def get_proxy()

def get_html(url):
    try:
        response =requests.get(url,allow_redirects=False,headers=headers)
        if response.status_code == 200:
            return response.text
            print('200')
        if response.status_code == 302:
            print('302')
        if response.status_code == 404:
            print('404')
        
    except ConnectionError:
        return get_html(url)
        

def get_index(keyword,page):
#    data = {
#           'query':keyword,
#           'type':2,
#           'page':page
#            }
#    queries = urlencode(data)
    url = base_url.format(keyword,page)
    html = get_html(url)
    doc = pq(html)
    items = doc('.news-list li .txt-box h3 a').items()
    for i in items:
        print(i.attr('data-share'))
#    items1 = doc('.txt-box h3 p').text()
    print(items)
#def parse_index(html):
#    doc = pq(html)
#    items = doc('.news-box .news-list li .txt-box h3 a').text()
##    for item in items:
##        yield item.attr('href')
#    return{
#            'item':items}
    
if __name__ == '__main__':
    get_index('风景',10)
    
    
    
    
    
  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值