baidu_weibo.py 文件源码

def __init__(self,*args,**kwargs):
        super(scrapy.Spider,self).__init__(*args,**kwargs)
        self.Flag_List = []
        self.Maxpage_List = []
        self.MAX_PAGE_NUM = 76
        self.site_id =  1   #?????
        self.site_name = u'baidu_weibo'
        self.base_url = 'https://www.baidu.com/s?wd=%s&pn=0&cl=2&tn=baiduwb&ie=utf-8&f=3&rtt=2'
        self.topic_kws = None
        self.pa = re.compile('&pn=(\d+)&') 
        self.pa_time = re.compile('\d+')
        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',
        }

        self.headers_weibo = {
                'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:51.0) Gecko/20100101 Firefox/51.0',
                'Host': 'weibo.com',
                'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
                'Accept-Encoding': 'gzip, deflate',
                'Accept-Language': 'zh-CN,zh;q=0.8,en-US;q=0.5,en;q=0.3',
                'Connection': 'keep-alive',
                'Upgrade-Insecure-Requests': '1'
        }