weixin_38310652的博客

import requestsfrom bs4 import BeautifulSoupimport reurl = ‘https://www.kanunu8.com/book3/7562/150394.html’res = requests.get(url)html = (res.content).decode(‘gbk’)soup = BeautifulSoup(html,‘lxm...

import requestsfrom bs4 import BeautifulSoupfrom urllib.parse import urlparseimport timeimport threadingdef spider(num,keyword):for sum in range(0, 800, 100):urlSearch = ‘https://www.baidu.com/...

import requestsimport jsonfrom urllib import requestimport osimport timefor pn in range(1,182): #共1-100章 pn = '%03d' %pn #三位数补零 ...

import requestsfrom bs4 import BeautifulSoupimport refile = open('titles.txt','r',encoding='utf8') #titles.txt是一开始就更新目录的档案title_list = file.read() #旧的储存的标题#以下找到新的标题url = 'https://tw.app...

#下面这行一定要加不会会报错#coding=utf-8import requests,json,timedef baidu_map(keyword): #city_code是 全国城市代码 37-373 for city_code in range(265,266): #页数设成最多翻20页 for pn in range(0,30):...

import requestsimport time,jsonfile = open('mapbar.txt','w',encoding='utf-8')def mapbar(keyword): time_now = int(time.time() * 1000) for pn in range(1,30): parameter = { ...

import requests,timefrom bs4 import BeautifulSoupfile = open(‘go007.txt’,‘w’,encoding=‘utf-8’)header = {‘Accept’:‘text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,/;q=0....

import geoip2.databasereader = geoip2.database.Reader(r’C:\Users\name\PycharmProjects\test\GeoLite2-City.mmdb’)response = reader.city(‘103.235.46.39’)print(response.country.iso_code)#GeoLite2-City...

#注意爬取太频繁IP会被封锁好几天#因为有的页面因为游戏停止买卖 所以range会跳空很多号码import requests,timefrom bs4 import BeautifulSoupfile = open(“8591.txt”,‘a+’)header ={‘Accept’:‘text/html,application/xhtml+xml,application/xml;q=0...

import requestsimport reimport jsonfrom bs4 import BeautifulSoup#微博要用cookies登入#一个知识点 有script里的内容用正则取出再处理headers = { 'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,im...