第四篇 - 爬取前程无忧python相关工作

            #
             import requests
            import re         #用于正则匹配
# import xlwt     #excel表格需要用到import urllib.request

#1.用requests模块获取网页html源码
# def get_content(page):
#     url = ‘‘.format(page)
#     html = requests.get(url).content.decode(‘gbk‘)
#     return html#1.用urllib模块获取源代码def get_content(page):
    url = ‘‘.format(page)      ------------1
    html = urllib.request.urlopen(url).read().decode(‘gbk‘)
    return html

#2.获取职位，薪资，公司名称def get_Data(html):
    reg = re.compile(r‘class="t1 ".*?<a target="_blank" title="(.*?)".*?<span class="t2"><a target="_blank" ‘
                     r‘title="(.*?)".*?<span class="t3">(.*?)</span>.*?<span class="t4">(.*?)</span>.*?‘
                     r‘<span class="t5">(.*?)</span>‘,re.S)
    items = re.findall(reg,html)
    return items

#3.存储到.csv文件中def save_file_csv(items):
    import csv
    csv_file = open(‘job.csv‘, ‘w‘, newline=‘‘)
    writer = csv.writer(csv_file)
    writer.writerow((‘职位名称‘,‘公司名称‘,‘公司地址‘,‘薪资‘,‘日期‘))
    for item in items:
        writer.writerow(item)

#3.存储到excel表格中
# def save_file_excel(items):
#     newTable = ‘jobs.xls‘
#     wb = xlwt.Workbook(encoding=‘utf-8‘)#创建excel文件
#     ws = wb.add_sheet(‘job‘)#去创建表
#     headData = [‘职位名称‘,‘公司名称‘,‘公司地址‘,‘薪资‘,‘日期‘]
#     index = 1
#     for colnum in range(5):
#         ws.write(0,colnum,headData[colnum],xlwt.easyxf(‘font:bold on‘))
#     for item in items:
#         for j in range(len(item)):
#                 ws.write(index,j,item[j])
#         index += 1
#     wb.save(newTable)#3.存储到txt文件中
# def save_file_txt(items):
#     with open(‘job.txt‘,‘w‘) as f:
#         for item in items:
#             for j in range(len(item)):
#                 f.write(item[j])
#                 f.write(‘        ‘)
#             f.write(‘n‘)if__name__ == ‘__main__‘:
    for i in range(1,3):     ---------------2
        html = get_content(i)
        items = get_Data(html)
        save_file_csv(items)