因为期末考试的缘故，本打算一个星期结束的爬虫，拖了很久，不过，也有好处：之前写的时候总是被反爬，这几天复习之余写了些反爬取的py code 下面发出来和大家探讨
做了些反爬取的手段
随机获取一个headers
headers.py
__author__ = 'Lee'
import requests
import random #随机数模块
def requests_headers():
head_connection = ['Keep-Alive','close']
head_accept = ['text/html,application/xhtml+xml,*/*']
head_accept_language = ['zh-CN,fr-FR;q=0.5','en-US,en;q=0.8,zh-Hans-CN;q=0.5,zh-Hans;q=0.3']
head_user_agent = ['Mozilla/5.0 (Windows NT 6.3; WOW64; Trident/7.0; rv:11.0) like Gecko',
'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/28.0.1500.95 Safari/537.36',
'Mozilla/5.0 (Windows NT 6.1; WOW64; Trident/7.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; rv:11.0) like Gecko)',
'Mozilla/5.0 (Windows; U; Windows NT 5.2) Gecko/070208 Firefox/3.0.1',
'Mozilla/5.0 (Windows; U; Windows NT 5.1) Gecko/0309 Firefox/2.0.0.3',
'Mozilla/5.0 (Windows; U; Windows NT 5.1) Gecko/0803 Firefox/1.5.0.12',
'Opera/9.27 (Windows NT 5.2; U; zh-cn)',
'Mozilla/5.0 (Macintosh; PPC Mac OS X; U; en) Opera 8.0',
'Opera/8.0 (Macintosh; PPC Mac OS X; U; en)',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.12) Gecko/0219 Firefox/2.0.0.12 Navigator/9.0.0.6',
'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.1; Win64; x64; Trident/4.0)',
'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.1; Trident/4.0)',
'Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; WOW64; Trident/6.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; InfoPath.2; .NET4.0C; .NET4.0E)',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Maxthon/4.0.6.2000 Chrome/26.0.1410.43 Safari/537.1 ',
'Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; WOW64; Trident/6.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; InfoPath.2; .NET4.0C; .NET4.0E; QQBrowser/7.3.9825.400)',
'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:21.0) Gecko/0101 Firefox/21.0 ',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.92 Safari/537.1 LBBROWSER',
'Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; WOW64; Trident/6.0; BIDUBrowser 2.x)',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.11 TaoBrowser/3.0 Safari/536.11']
#header 为随机产生一套由上边信息的header文件
header = {
'Connection':head_connection[random.randrange(0,len(head_connection))],
'Accept':head_accept[0],
'Accept-Language':head_accept_language[random.randrange(0,len(head_accept_language))],
'User-Agent':head_user_agent[random.randrange(0,len(head_user_agent))],
}
print('headers.py connection Success!')
return header #返回值为 header这个字典
# for i in range(100): #随机产生100套信息
# print(requests_headers()) #打印
# #print(random.randrange(1,10))
从IP池随机选择个代理IP
ip_proxy.py
__author__ = 'Lee'
import random
ip_pool = [
'117.143.109.136:80'
]
def ip_proxy():
ip = ip_pool[random.randrange(0,len(ip_pool))]
proxy_ip = 'http://'+ip
proxies = {'http':proxy_ip}
print(proxies)
return proxies
items_combination.py
__author__ = 'Lee'
from bs4 import BeautifulSoup
import requests
import pymongo
import time
from headers import requests_headers
from ip_proxy import ip_proxy
client = pymongo.MongoClient('localhost',27017) #链接数据库
ceshi = client['ceshi']
url_list = ceshi['url_list']
item_list = ceshi['item_info']
url_list1 = []
channel = '/zufang/dongcheng/'
#spider1 爬取房屋信息链接并用mongodb存储
def get_pages_url(channel,pag):
url = str(channel+'pg'+ pag)
wb_data = requests.get(url,headers=requests_headers(),proxies=ip_proxy())
soup = BeautifulSoup(wb_data.text,'lxml')
time.sleep(1)
no_data = '呣..没有找到相关内容，请您换个条件试试吧~'
# 面包屑模块
# 面包屑 breadcrumbs
bread_crumbs =soup.select('#house-lst > li')
item_url = soup.select('#house-lst > li > div > h2 > a')
blank_url = str(soup.find(text = no_data))
if no_data != blank_url:
for url in item_url:
url1 = url.get('href')
url_list1.append(url1)
#url_list.insert_one({'url':url1})
print(url1)
else:
pass
#get_pages_url(channel,'2')
# spider2 爬取详细信息并用mongodb存储
def get_massages(url):
web_data = requests.get(url,headers=requests_headers(),proxies=ip_proxy())
soup = BeautifulSoup(web_data.text,'lxml')
title = (soup.title.text).split('|')[0] #房名
address = soup.select('div.zf-room > p > a')[0].text #地址
price = soup.select(' div.price > span.total')[0].text + '元'
area = (soup.select('div.zf-room > p ')[0].text).split('：')[-1]
home_url = url
print({'title':title ,
'address':address,
'price':price,
'area':area,
'home_url':home_url,
})
item_list.insert_one({'title':title ,
'address':address,
'price':price,
'area':area,
'home_url':home_url})
get_massages('/zufang/101101635089.html')
'''
#house-lst > li > p
list-no-data clear
'''
