Tieba_search.py 文件源码

def __init__(self, *args, **kwargs):
        super(scrapy.Spider,self).__init__(*args, **kwargs)
        super(TiebaSearchSpider,self).__init__()
        self.dig_pattern = re.compile('(\d+)')
        self.postid_pattern = re.compile('/p/(\d{10})')
        self.page_all=1
        self.site_id=2
        self.site_name = u'tieba_search'
        self.Flag_List = []
        self.Maxpage_List = []
        self.MAX_PAGE_NUM = 5
        self.headers = {
                'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:51.0) Gecko/20100101 Firefox/51.0',
                'Host': 'www.baidu.com',
                'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
                'Accept-Encoding': 'gzip, deflate, br',
                'Accept-Language': 'zh-CN,zh;q=0.8,en-US;q=0.5,en;q=0.3',
        }