parser.py 文件源码

def __init__(self, search_page_url):
        self.search_page_url = search_page_url
        req = Request(
            search_page_url,
            data=None,
            headers={
                'User-Agent': UserAgent().chrome
            }
        )
        self.html = urlopen(req).read().decode('utf-8')
        self.soup = BeautifulSoup(self.html, 'html.parser')
        self.num_results = None
        for f in self.soup.find_all('strong'):
            if '????????' in f.text:
                if f.text.split()[0].isdigit():
                    self.num_results = int(f.text.split()[0])