114 lines
4.8 KiB
Python
114 lines
4.8 KiB
Python
import sys, os
|
||
|
||
project_root = os.path.abspath(os.path.join(os.path.dirname(__file__), "..", ".."))
|
||
if project_root not in sys.path:
|
||
sys.path.insert(0, project_root)
|
||
|
||
from web.Requests_Except import MR
|
||
|
||
base_url = 'www.zhrczp.com'
|
||
protocol = 'https'
|
||
default_headers = {
|
||
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7',
|
||
'Accept-Language': 'zh-CN,zh;q=0.9',
|
||
'Cache-Control': 'no-cache',
|
||
'Connection': 'keep-alive',
|
||
'Pragma': 'no-cache',
|
||
'Referer': 'https://www.zhrczp.com/member/index.php?c=resume&jobin=76&jobclass_search=76&cityin=&cityclass_search=&keyword=&minsalary=&maxsalary=&minage=&maxage=&exp=&edu=&uptime=&sex=&type=',
|
||
'Sec-Fetch-Dest': 'document',
|
||
'Sec-Fetch-Mode': 'navigate',
|
||
'Sec-Fetch-Site': 'same-origin',
|
||
'Sec-Fetch-User': '?1',
|
||
'Upgrade-Insecure-Requests': '1',
|
||
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/134.0.0.0 Safari/537.36',
|
||
'sec-ch-ua': '"Chromium";v="134", "Not:A-Brand";v="24", "Google Chrome";v="134"',
|
||
'sec-ch-ua-mobile': '?0',
|
||
'sec-ch-ua-platform': '"Windows"',
|
||
}
|
||
Requests = MR(base_url, protocol)
|
||
Requests.set_default_headers(default_headers)
|
||
|
||
|
||
def data_cleaning(xpathobj) -> dict:
|
||
# name_xlist = xpathobj.xpath('//h1/a/text()')
|
||
# name = name_xlist[0] if name_xlist else ""
|
||
# compary_info_xlist = xpathobj.xpath('//div[@class="com_details_info"]/text()')
|
||
# if compary_info_xlist:
|
||
# compary_info_list = [info.strip() for info in compary_info_xlist if info.strip()]
|
||
# category = compary_info_list[1]
|
||
# company_type = compary_info_list[2]
|
||
# size = compary_info_list[3]
|
||
# if len(compary_info_list) > 4:
|
||
# founded_date = compary_info_list[4]
|
||
# else:
|
||
# founded_date = ""
|
||
# else:
|
||
# category = ""
|
||
# company_type = ""
|
||
# size = ""
|
||
# founded_date = ""
|
||
# benefits_xlist = xpathobj.xpath('//div[@class="com_welfare "]/span/text()')
|
||
# if benefits_xlist:
|
||
# benefits_str = " | ".join(benefits_xlist)
|
||
# else:
|
||
# benefits_str = ""
|
||
# introduction_xlist = xpathobj.xpath('//div[@class="company_img_auto"]/p/text()')
|
||
# if not introduction_xlist:
|
||
# introduction_xlist = xpathobj.xpath('//div[@class="company_img_auto"]/text()')
|
||
# if not introduction_xlist:
|
||
# introduction_xlist = xpathobj.xpath('//div[@class="company_img_auto"]/p/span/text()')
|
||
# if introduction_xlist:
|
||
# introduction = "\r\n".join([info.strip() for info in introduction_xlist if info.strip()])
|
||
# else:
|
||
# introduction = ""
|
||
# address_xlist = xpathobj.xpath('//div[@class="com_details_tel_me"]/div/text()')
|
||
# if address_xlist:
|
||
# address = address_xlist[0].strip()
|
||
# else:
|
||
# address = ""
|
||
# if name != "" and introduction != "":
|
||
# company_data = {
|
||
# "name": name,
|
||
# "category": category,
|
||
# "size": size,
|
||
# "company_type": company_type,
|
||
# "founded_date": founded_date,
|
||
# "introduction": introduction,
|
||
# "address": address,
|
||
# "benefits": benefits_str,
|
||
# "website": 1,
|
||
# }
|
||
# else:
|
||
# company_data = None
|
||
# return company_data
|
||
name = xpathobj.xpath('//h1[@class="company-header-top-detail-name hide-txt"]/text()')[0].strip()
|
||
category = xpathobj.xpath('//div[@class="company-header-bottom-item-text hide-txt"]/text()')[0].strip()
|
||
size = xpathobj.xpath('//div[@class="company-header-bottom-item-text hide-txt"]/text()')[0].strip()
|
||
# data = {
|
||
# "name": name, # 公司名称，例如 "字节跳动"
|
||
# "category": category, # 行业类别，例如 "互联网/软件/信息技术"
|
||
# "size": size, # 公司规模，例如 "1000人以上"
|
||
# "company_type": company_type, # 公司性质，例如 "民营", "外企", "国企"
|
||
# "founded_date": founded_date, # 成立时间，推荐格式 "YYYY-MM-DD" 或 "2010年"
|
||
# "introduction": introduction, # 公司简介/介绍，字符串类型
|
||
# "address": address, # 公司地址，完整的办公地点描述
|
||
# "benefits": benefits_str, # 员工福利，例如 "五险一金, 带薪年假, 免费下午茶"
|
||
# "website": 1, # 是否有官网，1 表示有，0 表示无（注意：这里可能是布尔值标志，不是真正的网址）
|
||
# }
|
||
|
||
print(name)
|
||
print(category)
|
||
print(size)
|
||
|
||
def get_company_page(page: int):
|
||
url = f"/company/{page}.html"
|
||
res = Requests.get(url, timeout=10)
|
||
with open("zhrczp_com_company.html", "w", encoding="utf-8") as f:
|
||
f.write(res.text)
|
||
return data_cleaning(res.xpath())
|
||
|
||
|
||
if __name__ == '__main__':
|
||
# for page in range(1, 1000):
|
||
print(get_company_page(3273))
|