import time from common.search import Search class Bing(Search): def __init__(self, domain): Search.__init__(self) self.domain = domain self.module = 'Search' self.source = 'BingSearch' self.init = 'https://www.bing.com/' self.addr = 'https://www.bing.com/search' self.limit_num = 1000 # 限制搜索条数 def search(self, domain, filtered_subdomain=''): """ 发送搜索请求并做子域匹配 :param str domain: 域名 :param str filtered_subdomain: 过滤的子域 """ self.page_num = 0 # 二次搜索重新置0 self.header = self.get_header() self.proxy = self.get_proxy(self.source) resp = self.get(self.init) if not resp: return self.cookie = resp.cookies # 获取cookie bing在搜索时需要带上cookie while True: time.sleep(self.delay) self.proxy = self.get_proxy(self.source) query = 'site:.' + domain + filtered_subdomain params = {'q': query, 'first': self.page_num, 'count': self.per_page_num} resp = self.get(self.addr, params) subdomains = self.match_subdomains(resp, fuzzy=False) if not self.check_subdomains(subdomains): break self.subdomains.update(subdomains) # 搜索页面没有出现下一页时停止搜索 if '