将网络·爬取的数据存入excel

• 需要导入三个包，requests,re,xlwt

import requests
import re
import xlwt


def main():
    workbook = xlwt.Workbook(encoding='utf-8')
    mysheet = workbook.add_sheet('mysheet')
    mysheet.write(0, 0, '排名')
    mysheet.write(0, 1, '图片地址')
    mysheet.write(0, 2, '书名')
    mysheet.write(0, 3, '评论数量')
    mysheet.write(0, 4, '推荐指数')
    mysheet.write(0, 5, '作者')
    mysheet.write(0, 6, '出版社')
    mysheet.write(0, 7, '价格')
    i = 1
    for page in range(1, 4):
        url = 'http://bang.dangdang.com/books/bestsellers/1-' + str(page)
        html = getHTMLText(url)
        items = parse_result(html)
        print(items)
        for item in items:
            No = item[0]  # 排名
            image = item[1]  # 图片地址
            book_title = item[2]  # 书名
            reviews = item[3]  # 评论数量
            recommend = item[4]  # 推荐指数
            writer = item[5]  # 作者
            press = item[6]  # 出版社
            price = item[7]  # 价格

            mysheet.write(i, 0, No)
            mysheet.write(i, 1, image)
            mysheet.write(i, 2, book_title)
            mysheet.write(i, 3, reviews)
            mysheet.write(i, 4, recommend)
            mysheet.write(i, 5, writer)
            mysheet.write(i, 6, press)
            mysheet.write(i, 7, price)
            i += 1
    workbook.save('dangdang.xls')


def getHTMLText(url):
    try:
        r = requests.get(url, timeout=30)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text
    except:
        return "异常"


def parse_result(html):
    pattern = re.compile(
        '<li>.*?list_num.*?>(.*?).</div>.*?<img.*?src="(.*?)".*?class="name".*?title="(.*?)".*?class="level".*?target="_blank">(.*?)</a>.*?class="tuijian">(.*?)</span>.*?class="publisher_info".*?title="(.*?)".*?</a>.*?class="publisher_info".*?target="_blank">(.*?)</a>.*?class="price_n">&yen;(.*?)</span>.*?</li>',
        re.S)
    items = re.findall(pattern, html)
    return items


if __name__ == '__main__':
    main()