简介：爬取“个人简历网”中的简历模板并存储到本地（http://www.gerenjianli.com/moban/index.html）
代码：

import requests
from lxml import etree
import os
if __name__ == '__main__':
    # 这是只爬取一页数据
    # url = 'http://www.gerenjianli.com/moban/index.html'
    #
    # headers = {
    #     'User-Agent':'这里放自己浏览器的UA就行啦'
    # }
    # # page_text = requests.get(url=url,headers=headers).text
    # response = requests.get(url=url, headers=headers)
    # # response.encoding = 'utf-8'
    # page_text = response.text
    #
    # tree = etree.HTML(page_text)
    # li_list = tree.xpath('//div[@class="list_boby"]/ul[@class="prlist"]/li')
    # # print(li_list)
    #
    # #创建文件夹
    # if not os.path.exists('./resumeLibs'):
    #     os.mkdir('./resumeLibs')
    # for li in li_list:
    #     a = li.xpath('./div/a/@href')[0]
    #     name = li.xpath('./div/a/img/@alt')[0]
    #     name = name.encode('iso-8859-1').decode('gbk')
    #     download_text = requests.get(url=a,headers=headers).text
    #     tree = etree.HTML(download_text)
    #     download_href = tree.xpath('//div[@class="donwurl2"]/a/@href')[0]
    #
    #     doc_data = requests.get(url=download_href,headers=headers).content
    #     doc_path = 'resumeLibs/' + name + '.docx'
    #     with open(doc_path,'wb') as fp:
    #         fp.write(doc_data)
    #         print(name,'下载成功！')

    # 爬取多页数据
    headers = {
        'User-Agent': '这里放自己浏览器的UA就行啦'
    }
    # 创建文件夹
    if not os.path.exists('./resumeLibs'):
        os.mkdir('./resumeLibs')

    for pagenum in range(1,4):#这里爬取了1-3页中的简历模板
        if pagenum == 1:
            url = 'http://www.gerenjianli.com/moban/index.html'
        else:
            url = 'http://www.gerenjianli.com/moban/index_' + str(pagenum) + '.html'

        # page_text = requests.get(url=url,headers=headers).text
        response = requests.get(url=url, headers=headers)
        # response.encoding = 'utf-8'
        page_text = response.text

        tree = etree.HTML(page_text)
        li_list = tree.xpath('//div[@class="list_boby"]/ul[@class="prlist"]/li')
        # print(li_list)

        for li in li_list:
            a = li.xpath('./div/a/@href')[0]
            name = li.xpath('./div/a/img/@alt')[0]
            name = name.encode('iso-8859-1').decode('gbk')
            download_text = requests.get(url=a, headers=headers).text
            tree = etree.HTML(download_text)
            download_href = tree.xpath('//div[@class="donwurl2"]/a/@href')[0]

            doc_data = requests.get(url=download_href, headers=headers).content
            doc_path = 'resumeLibs/' + name + '.docx'
            with open(doc_path, 'wb') as fp:
                fp.write(doc_data)
                print(name, '下载成功！')

• 1
• 2
• 3
• 4
• 5
• 6
• 7
• 8
• 9
• 10
• 11
• 12
• 13
• 14
• 15
• 16
• 17
• 18
• 19
• 20
• 21
• 22
• 23
• 24
• 25
• 26
• 27
• 28
• 29
• 30
• 31
• 32
• 33
• 34
• 35
• 36
• 37
• 38
• 39
• 40
• 41
• 42
• 43
• 44
• 45
• 46
• 47
• 48
• 49
• 50
• 51
• 52
• 53
• 54
• 55
• 56
• 57
• 58
• 59
• 60
• 61
• 62
• 63
• 64
• 65
• 66
• 67
• 68
• 69
• 70
• 71
• 72