Crawler demo, requests, beatuifulsoup
import os,re import pickle import requests import chardet import random import time from bs4 import BeautifulSoup from multiprocessing import Pool user_agent_list = [ "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/22.0.1207.1 Safari/537.1", "Mozilla/5.0 (X11; CrOS i686 2268.111.0) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.57 Safari/536.11", "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1092.0 Safari/536.6", "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1090.0 Safari/536.6", "Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/19.77.34.5 Safari/537.1", "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.9 Safari/536.5", "Mozilla/5.0 (Windows NT 6.0) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.36 Safari/536.5", "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3", "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3", "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_0) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3", "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3", "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3", "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3", "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3", "Mozilla/5.0 (Windows NT 6.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3", "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.0 Safari/536.3", "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24", "The Mozilla / 5.0 (the Windows NT 6.2; the WOW64) AppleWebKit / 535.24 (KHTML, like the Gecko) the Chrome / 19.0.1055.1 Safari / 535.24" ] the UA = The random.choice (user_agent_list) ## a random string withdrawn from the self.user_agent_list headers = { 'User-Agent' : UA} ## is configured into a complete User-Agent (UA behalf random string is taken out of the above-oh) URL0 = 'HTTP: //www.tjxqda.com/column/ xxdt ' with requests.get (URL0, headers = headers, timeout =. 5) AS Response: # Print (type (response.text), response.text) # Print (type (response.content), response.content) # Print (of the type (response.status_code), response.status_code) # Print (of the type (Response.Headers), Response.Headers) # Print (of the type (Response.Cookies), Response.Cookies) # Print (of the type (response.url), response.url) # print(type(response.history), response.history) # response.encoding = 'gb18030' soup = BeautifulSoup(response.text, 'lxml') print(soup.title.text) #打印title li_list=soup.find('ul', class_='list-main-style').find_all('li') # print(li_list) for li_quick in li_list: print('最灵活的查找方法:', li_quick.get_text()) print(li_quick.a.get('href')) # print(soup.prettify()) # print(soup.select('ul[class="list_16 mt10"]'))[0].text # for x in soup.select('li a'): # print(x.text)