摘要：
1 #!/usr/bin/env python 2 # -*- coding:utf-8 -*- 3 4 import urllib2 5 import json 6 from lxml import etree 7 8 url = "http://www.qiushibaike.com/8hr/page/2/" 9 headers = {"User-Agent" : "M... 阅读全文
摘要：
阅读全文
摘要：
# -*- coding:utf-8 -*- from bs4 import BeautifulSoup import requests import time def captcha(captcha_data): with open("captcha.jpg", "wb") as f: f.write(captcha_data) text = raw_inp... 阅读全文
摘要：
1 #!/usr/bin/env python 2 # -*- coding:utf-8 -*- 3 4 import urllib 5 import urllib2 6 7 def loadPage(url, filename): 8 """ 9 作用：根据url发送请求，获取服务器响应文件 10 url: 需要爬取的url地址 1... 阅读全文
摘要：
1 import re 2 import requests 3 4 class Spider(): 5 def __init__(self): 6 self.page=self.page 7 #self.switch=True 8 9 10 def loadpage(self,page): 11 url='h... 阅读全文
摘要：
1 import requests 2 from lxml import etree 3 4 def loadpage(url): 5 headers={"User-Agent":"Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/61.0.3163.1... 阅读全文