python爬站长素材中的免费简历

仅做学习用，不对相关网站抱有任何恶意或不良影响。

网站：站长素材-分享综合设计素材免费下载的平台

目标是爬取一些简历，在这里选中简历

随便挑一个类别：

import requests
from lxml import etree
import os

header = {
 把你自己的搞进去啊
}

if not os.path.exists('d:/jianli'):
    os.mkdir('d:/jianli')
# 进行翻页下载
for page in range(0, 4):
    if page == 0: 
        url = 'https://sc.chinaz.com/tag_jianli/GongChengShi.html' # 首页不带数字下标
    else:
        url = 'https://sc.chinaz.com/tag_jianli/GongChengShi_' + str(page) + '.html'
    response = requests.get(url, headers=header).text
    # response.encode('utf-8')
    tree = etree.HTML(response)
    resume_list = tree.xpath('//div[@id="main"]/div/div/a/@href')  # 这个很重要，要定位准确
    #  对一个简历详情进行查找下载
    for deatil in resume_list:
        every_url = 'https://sc.chinaz.com' + deatil

        info = requests.get(every_url, headers=header).content  # 乱码解决方案1
        little_tree = etree.HTML(info)
        try:  # 存在付费情况，无相关链接会报错
            resume_name = little_tree.xpath('//div[@class="ppt_tit clearfix"]/h1/text()')[0]  # 列表取出字符
            download_url = little_tree.xpath('//div[@class="down_wrap"]/div[2]/ul/li[1]/a/@href')[0]
            resume_get = requests.get(download_url, headers=header).content

            with open("d:/jianli/" + resume_name + '.rar', 'wb') as f:
                f.write(resume_get)
            print(resume_name + '下载成功')
        except:
            continue