爬取站长之家免费简历

爬取站长之家免费简历

import os
import requests
from lxml import etree
dir_name = './简历模板'
if not os.path.exists(dir_name):
    os.mkdir(dir_name)
url = 'http://sc.chinaz.com/jianli/free_%d.html'
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.105 Safari/537.36',
}
for page in range(1, 21):
    if page == 1:
        new_url = 'http://sc.chinaz.com/jianli/free.html'
    else:
        new_url = format(url%page)
    page_text = requests.get(new_url,headers=headers).text
    tree = etree.HTML(page_text)
    detail_url_list = tree.xpath('//div[@id="container"]/div')
    for detail_url in detail_url_list:
        detail_url = detail_url.xpath('./a/@href')[0]
        detail_page = requests.get(detail_url, headers=headers).text
        tree = etree.HTML(detail_page)
        resume_name = tree.xpath('//div[@class="bgwhite"]/div[1]/h1/text()')[0].encode('iso-8859-1').decode('utf-8')
        resume_url = tree.xpath('//div[@id="down"]/div[2]//li[6]/a/@href')[0]
        file_path = dir_name + '/' + resume_name + '.rar'
        print(resume_name,'开始下载')
        rar_content = requests.get(resume_url, headers=headers).content
        with open(file_path, 'wb') as f:
            f.write(rar_content)
        print(resume_name, '下载完成')
print('全部下载完成')