topic_spider/find_source/crawler/engines.py

from abc import abstractmethod, ABCMeta

from common.execptions import QccError
from common.tools import html2element
from constants import (
    ORGANIZATION,
    KEYWORD
)
from crawler.analysis import parse_urls
from crawler.download import Downloader
from crawler.utils import get_url
from settings import ENGINE_FEATURE_RETRIEVES


class JySearchEngine(Downloader, metaclass=ABCMeta):

    def __init__(self):
        super(JySearchEngine, self).__init__()

    @staticmethod
    def rubbish_url(url: str):
        for feature in ENGINE_FEATURE_RETRIEVES:
            if feature in url:
                return True
        return False

    @abstractmethod
    def search(self, keyword: str, page: int):
        raise NotImplementedError


class BingSearchEngine(JySearchEngine):
    site = "https://cn.bing.com/"
    usage = KEYWORD

    def __init__(self):
        super(BingSearchEngine, self).__init__()
        self.headers = {
            "authority": "cn.bing.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",
            "referer": "https://cn.bing.com/?scope=web",
            "upgrade-insecure-requests": "1",
            "user-agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/100.0.4896.75 Safari/537.36"
        }

    def downloader(self, url, **kwargs):
        response = self.get(url, headers=self.headers, **kwargs)
        return response

    def parser(self, response):
        urls = []
        if response.status_code == 200:
            urls = parse_urls(response.text, self.site)
        return urls

    def percolator(self, urls, retrieve_urls):
        """url过滤器"""
        for url in urls:
            if not self.rubbish_url(url) and url not in retrieve_urls:
                retrieve_urls.append(url)

    def search(self, keyword, page):
        retrieve_urls = []
        base_url = "https://cn.bing.com/search"
        first = (page - 1) * 10 + 1
        params = {
            "q": 'intitle:{}'.format(keyword),
            "first": first,
            'FORM': 'PERE',
            'pq': 'intitle:{}'.format(keyword)
        }
        url = get_url(base_url, params)
        # 下载
        response = self.downloader(url)
        # 解析
        urls = self.parser(response)
        # 过滤
        self.percolator(urls, retrieve_urls)
        return retrieve_urls


class QccSearchEngine(JySearchEngine):
    site = "https://www.qcc.com/"
    usage = ORGANIZATION

    def search(self, name: str, page=None):
        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