python从网站抓取特定内容

背景

测试需要模拟浏览器的userAgent，从网站上找到一批 http://www.fynas.com/ua

分析

非常普通的table元素维护
约有8K多条，为防止中途中断导致数据丢失选择读取一页写一页，单个文件可能吃力，选择100页数据放入一个文件的方式

运行后发现 其实抓取结果放入一个文件即可~，总共才2MB左右 -_-!

实现

# -*- coding:utf8 -*-  
import string
import urllib2
import re
import time
import random
import math

class GetUserAgent:

    def __init__(self,url):
        self.myUrl = url
        self.datas = []
        print u"useragent starting...."

    def fynas(self):
        url = "http://www.fynas.com/ua"

        user_agents = [ 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36']
        agent = random.choice(user_agents) 
        req = urllib2.Request(url) 
        req.add_header('User-Agent', agent)
        req.add_header('Host', 'www.fynas.com')
        req.add_header('Accept', '*/*')
        req.add_header('GET', url)

        mypage = urllib2.urlopen(req).read().decode("utf8")
        #print mypage
        Pagenum = self.page_counter(mypage)
        #print Pagenum
        self.find_data(self.myUrl,Pagenum)

    def page_counter(self,mypage):
        myMatch = re.search(u'共(\d+?)条',mypage,re.S) 
        print myMatch
        if myMatch: 
            Pagenum = int(math.ceil(int(myMatch.group(1))/10.0))
            print u"info:一共%d页" %Pagenum 
        else: 
            Pagenum = 0 
            print u"info:none" 

        return Pagenum 
    def find_data(self,myurl,Pagenum):

        name = myurl.split("/")


        for i in range(1,Pagenum+1):
            f = open('userAgent'+str(i/100)+'.txt','a+') 
            mypage=''
            self.datas=[]
            print i
            print u"info:第%d页正在加载中......" % i

            url = myurl + "/search?d=&b=&k=&page=" + str(i)


            user_agents = [ 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36']
            agent = random.choice(user_agents)

            req = urllib2.Request(url) 

            req.add_header('User-Agent', agent)
            req.add_header('Host', 'www.fynas.com')
            req.add_header('Accept', '*/*')

            req.add_header('GET', url)

            mypage = urllib2.urlopen(req).read()
            #time.sleep(2)

            #MQQBrowser
            #Opera
            #Mozilla
            myItems = re.findall(u'<td>(Mozilla.*?)</td>',mypage,re.S)

            #print myItems

            for item in myItems:
                self.datas.append(item+"\n")

            time.sleep(1)
            #self.datas.append(mypage+"\n")


            f.writelines(self.datas)  
            f.close() 

        #print self.datas

        print u"info:文件已下载"


url = "http://www.fynas.com/ua"

mySpider = GetUserAgent(url)  
mySpider.fynas()

……
info:第245页正在加载中......
246
info:第246页正在加载中......
247
info:第247页正在加载中......
248
info:第248页正在加载中......
249
info:第249页正在加载中......
250
info:第250页正在加载中......
251
info:第251页正在加载中......
252
info:第252页正在加载中......
253
info:第253页正在加载中......
254
……