如何使用python爬取當(dāng)當(dāng)網(wǎng)所有數(shù)據(jù)分析書籍信息

urls = ['http://search.dangdang.com/?key=%CA%FD%BE%DD%B7%D6%CE%F6&act=input&page_index={}'.format(i) for i in range(1,101)]

html=requests.get(url,headers=headers)# html.encoding = "utf-8"# print('第一層調(diào)用是否返回正常：',html)html.encoding = html.apparent_encoding  # 將亂碼進(jìn)行編碼selector=etree.HTML(html.text)# print(selector)datas=selector.xpath('//div[@class="con shoplist"]')# print(datas)
for data in datas:   Classs = data.xpath('div/ul/li/@class')                        #line1-line60   IDDs = data.xpath('div/ul/li/@id')                              #id   titles = data.xpath('div/ul/li/a/@title')                      #標(biāo)題   prices = data.xpath('div/ul/li/p[3]/span[1]/text()')           #書籍價(jià)格   source_prices = data.xpath('div/ul/li/p[3]/span[2]/text()')    #書籍原價(jià)   discounts = data.xpath('div/ul/li/p[3]/span[3]/text()')        #書籍折扣   # dian_prices = data.xpath('div/ul/li/p[3]/a[2]/i/text()')       #電子書價(jià)格   authors = data.xpath('div/ul/li/p[5]/span[1]/a[1]/@title')     #作者   publish_times = data.xpath('div/ul/li/p[5]/span[2]/text()')    #出版時(shí)間   publishs = data.xpath('div/ul/li/p[5]/span[3]/a/text()')       #出版社   comments = data.xpath('div/ul/li/p[4]/a/text()')               #書籍評(píng)論量   urls=data.xpath('div/ul/li/a/@href')

db = pymysql.connect(host='localhost', user='root', passwd='庫(kù)密碼', db='庫(kù)名稱:Learn_data', port=3306, charset='utf8')print("數(shù)據(jù)庫(kù)連接")cursor = db.cursor()cursor.execute("DROP TABLE IF EXISTS Learn_data.dangdangweb_info_detail")sql = """CREATE TABLE IF not EXISTS Learn_data.dangdangweb_info_detail (   id int auto_increment primary key,   Class CHAR(100),   IDD CHAR(100),   title CHAR(100),   price CHAR(100),   source_price CHAR(100),   discount CHAR(100),   author CHAR(100),   publish_time CHAR(100),   publish CHAR(100),   comment CHAR(100),   dian_price CHAR(100))DEFAULT CHARSET=utf8"""cursor.execute(sql)

cursor.execute("insert into dangdangweb_info_detail (Class,IDD,title,price,source_price,discount,author,publish_time,publish,comment,dian_price)"              "values(%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s)",       (str(Class),str(IDD),str(title),str(price),str(source_price),str(discount),str(author)        ,str(publish_time),str(publish),str(comment),str(dian_price[0])))