Python爬取前程無憂網址，並保存為txt文件

import urllib.request
import re


def get_html(page):                 #獲取網頁的HTML
    url = 'http://search.51job.com/jobsearch/search_result.php?fromJs=1&jobarea=000000%2C00&district=000000&funtype=0000&industrytype=00&issuedate=9&providesalary=99&keyword=Python&keywordtype=2&curr_page=2&lang=c&stype=1&postchannel=0000&workyear=99&cotype=99&degreefrom=99&jobterm=99&companysize=99&lonlat=0%2C0&radius=-1&ord_field=0&list_type=0&fromType=14&dibiaoid=0&confirmdate=9'.format(page)
    html = urllib.request.urlopen(url).read()
    html = html.decode('gbk')
    return html

def get_you_want(html):         #獲取需要的征文內容
    reg = re.compile(r'class="t1 ">.*?<a target="_blank" title="(.*?)".*?<span class="t2"><a target="_blank" title="(.*?)".*?<span class="t3">(.*?)</span>.*?<span class="t4">(.*?)</span>',re.S)
    you_want = re.findall(reg,html)
    print(you_want)
    return you_want

for get_page in range(1,6):
    htmls = get_html(get_page) #調用獲取源碼
    for i in get_you_want(htmls):
        print(i[0],i[1],i[2],i[3])
        with open('前程無憂.txt','a') as f:
            f.write(i[0]+'\t'+i[1]+'\t'+i[2]+'\t'+i[3]+'\n\n')

 

我用的是Python 3 其實和Python 2 差不多 ，就是Python3沒有了urllib2,需要導入import urllib.requests來代替import urllib2,其他的都差不多


PS：
　　其實我是想保存為Excel來進行后續的分析的，但是發現比較麻煩就放棄了！（此處應該有表情的◔ ‸◔?）