topic_spider/find_source/crawler/qcc.py

from common.execptions import QccError
from common.tools import html2element
from crawler.download import Downloader


class QccService(Downloader):

    def get_site(self, name: str):
        site = '-'
        headers = {
            "authority": "www.qcc.com",
            "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=0.9",
            "accept-language": "zh-CN,zh;q=0.9,en;q=0.8",
            "cache-control": "no-cache",
            "pragma": "no-cache",
            "upgrade-insecure-requests": "1",
            "user-agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/100.0.4896.127 Safari/537.36"
        }
        cookies = {
            "CNZZDATA1254842228": "1319079473-1648702017-https%253A%252F%252Fwww.google.com%252F%7C1650962497",
        }
        url = "https://www.qcc.com/web/search"
        params = {"key": name.strip()}
        response = self.get(url, headers=headers, cookies=cookies, params=params)
        if response.status_code != 200:
            raise QccError(reason='企查查搜索接口调用失败', code=response.status_code)
        element = html2element(response.text)
        nodes = element.xpath('//table[@class="ntable ntable-list"]//tr[1]/td[3]/div[1]/div[4]/div[2]/span[3]/span/child::*')
        if len(nodes) > 0:
            sub_node = nodes[0]
            site = "".join("".join(sub_node.xpath('./text()')).split())
        return site