Simple python crawler crawls boss jobs and writes to Excel

1, the default city is Hangzhou, the code is as follows

#! -*-coding:utf-8-*-

From Urllib import request, parse

From BS4 import BeautifulSoup

Import datetime

Import XLWT

StartTime = Datetime.datetime.now ()

url = R ' https://www.zhipin.com/job_detail/?scity=101210100 '

# boss directly hires the URL address, default Hangzhou

def read_page (URL, page_num, keyword): # mimic browser

Page_headers = {

' Host ': ' www.zhipin.com ',

' User-agent ': ' mozilla/5.0 (Windows NT 10.0; WOW64) applewebkit/537.36 (khtml, like Gecko) chrome/66.0.3359.181 safari/537.36 '

' chrome/45.0.2454.85 safari/537.36 115browser/6.0.3 ',

' Connection ': ' Keep-alive '

}

Page_data = Parse.urlencode ([# Browser request parameter

(' ka ', ' page-' +str (page_num)),

(' page ', page_num),

(' query ', keyword)

])

req = Request. Request (URL, headers=page_headers)

page = Request.urlopen (req, Data=page_data.encode (' Utf-8 ')). Read ()

page = Page.decode (' Utf-8 ')

Return page

if __name__ = = ' __main__ ':

Print (' ********************************** is about to crawl ********************************** ')

Keyword = input (' Please enter the position you want to search for: ')

Workbook = xlwt. Workbook ()

Sheet = workbook.add_sheet (' Sheet1 ')

I=0

For j in Range (1,5):

Soup=beautifulsoup (Read_page (URL, j, keyword))

For link in soup.select ('. Company-text '):

Sheet.write (I,0,link.get_text ())

I=i+1

Workbook.save ("D:\\resultslatest.xls")

Endtime = Datetime.datetime.now ()

Time = (endtime-starttime). seconds

Print (' Total time:%s s '% time)

2, crawl results

Simple python crawler crawls boss jobs and writes to Excel