不怀才的有志青年

import requestsfrom lxml import etreeimport threadingfrom queue import Queuethreads=[]headers={"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chro...

主程序hy.py:# -*- coding: utf-8 -*-import scrapyfrom ..items import sortItem,gameInfo,gameSonSort,houseInfofrom scrapy import Requestimport refrom time import sleepclass HySpider(scrapy.Spider):...

# -*- coding: utf-8 -*-import scrapyimport refrom scrapy import Requestimport jsondef convert(s): if s is str and s.isdigit: return int(s.resplace(',')) else: return 0c...

import requestsimport threadingfrom queue import Queuefrom lxml import etreeimport timeimport wgetimport osurlQueue=Queue()#链接队列threads_num=100 #线程数threads=[]urList=[]skin=[]def getUrl...

第二章：BeautifulSoup的使用下行遍历：.contents:子节点的列表.children:子节点的迭代类型，循环遍历儿子节点。.descendants:子孙节点的迭代类型，循环遍历子孙节点上行遍历：.parent:节点的父亲标签.parents:节点的先辈标签的迭代类型，用于循环遍历先辈节点平行遍历：.next_sibing:返回以HTML顺序的下一个平行节点.pr...

import requestsfrom bs4 import BeautifulSoupimport bs4def getHTMLText(url): try: r=requests.get(url,timeout=30) r.raise_for_status() r.encoding=r.apparent_encoding return r.text...

一篇煎蛋的python爬虫，爬取优快云文章，借助免费的代理IP网站，分析出IP地址，使用代理IP访问,阔以去玩一下import osimport timeimport randomimport requestsfrom lxml import etree#准备部分#1.headersheaders={'User-Agent':'Mozilla/5.0 (Windows NT 10...