ding1991as的博客

# -*- coding=utf-8 -*-import requestsfrom lxml import etreeheaders = { 'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/59.0.3071.86 Safari/537.

# !/usr/bin/env python3# -*- coding: utf-8 -*-'''Required- requests (必须)- pillow (可选)Info- author : "xchaoinfo"- email : "xchaoinfo@qq.com"- date : "2016.2.4"Update- name : "wangmengcn

# -*- coding:utf8 -*-import requestsfrom lxml import etreeheaders = { # 'Accept':'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8', # 'Accept-Encoding

session  获取cookies=session运行get请求s.cookies   即是cookie对象#实例化一个LWPCookieJar对象load_cookiejar = cookielib.LWPCookieJar()#从文件中加载cookies(LWP格式)load_cookiejar.load('cookies/' + self.username

#coding:utf-8from flask import Flaskimport requestsfrom lxml import etreeapp= Flask(__name__)app.debug =True#爬取小说并返回到前台@app.route('/',methods=['GET','POST'])def index(): r = requests.get

基于Python3.5 的asyncio 的 异步爬虫案例：我们会实现以下功能：    1： 单进程 实现并发 异步爬虫    2： 解决并发过多报错  too many file descriptors in select    3: 实现异步 master-worker 主从模式以下是具体代码实现：1：    #coding:utf-8import time,asyncio,aiohttp...