python爬取前程无忧_Python爬取前程无忧网址，并保存为txt文件

开发工具Python版本：3.6

相关模块：

import urllib.request

import re

完整代码

import urllib.request

import re

'''

遇到不懂的问题？Python学习交流群：821460695满足你的需求，资料都已经上传群文件，可以自行下载！

'''

def get_html(page): #获取网页的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): #获取需要的征文内容

reg = re.compile(r'class="t1 ">.*?(.*?).*?(.*?)',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) #调用获取源码

for i in get_you_want(htmls):

print(i[0],i[1],i[2],i[3])

with open('前程无忧.txt','a') as f:

f.write(i[0]+'\t'+i[1]+'\t'+i[2]+'\t'+i[3]+'\n\n')