python 爬取豆瓣電影案例

標籤：https   get   count   androi   mobile   ini   html_   html   擷取   

# conding=utf-8from  parse import parse_urlimport jsonclass DoubanSpider:    def __init__(self):        self.temp_url = "https://m.douban.com/rexxar/api/v2/subject_collection/filter_movie_occident_hot/items?os=android&for_mobile=1&callback=jsonp3&start={}&count=18&loc_id=108288&_=0"    def get_content_list(self,html_str): #提取資料        dict_data = json.loads(html_str)        content_list = dict_data["subject_collection_items"]        total =dict_data["total"]        return content_list,total    def save_content_list(self,content_list):        with open("db.json","a",encoding="utf-8") as f:            for content in content_list:                f.write(json.dumps(content,ensure_ascii=False))                f.write("\n")                print(‘添加成功‘)    def run(self): #實現主要邏輯        num = 0        total = 100        while num < total + 18:            # 1.start_url            start_url = self.temp_url.format(num)            # 2.發送請求,擷取響應            html_str = parse_url(start_url)            # 3.提取資料            content_list, total = self.get_content_list(html_str)            # 4.儲存            self.save_content_list(content_list)            # 5.構造下一頁的url地址,迴圈2-5步            num +=18if __name__== ‘__main__‘:        douban = DoubanSpider()        douban.run()

 

python 爬取豆瓣電影案例