爬虫当当网后将数据写入excel的两种方式

爬虫后将数据写入excel的两种方式：
第一种是用xlwt模块，这个写的代码比较多，也比较繁琐，但是一点问题都没有的。
第一种方式源代码

# ！/user/bin/env ptyhon

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()

第二种是用pandas模块，这个写的代码比较少，但是一问题有点多。我之前写的时候后面的会把前面的覆盖掉，所以我最终用了with open 用了csv模块
第二种方式源代码

import requests
from lxml import etree
import csv

def get_info(url):
    headers = {
        'user-agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.87 Safari/537.36'
    }
    response = requests.get(url, headers=headers).text
    result = etree.HTML(response)

    #  xpath解析获取内容

    bookname = result.xpath('//div[@class="name"]/a/@title')[0]
    image = result.xpath('//div[@class="pic"]/a/img/@src')[0]
    recommend = result.xpath('//div[@class="star"]/a/text()')[0]
    writer = result.xpath('//div[@class="publisher_info"]/a/text()')[0]
    price = result.xpath('//div[@class="price"]/p/span[@class="price_n"]/text()')[0]

    with open('dangdang.csv','w',newline='',encoding='utf-8') as f:
        writer = csv.writer(f)
        writer.writerow([bookname,image,recommend, writer, price])
        for value in zip(bookname,image,recommend, writer, price):
            writer.writerow(value)


def run():
    page = 0
    while 1:
        url = 'http://bang.dangdang.com/books/bestsellers/1-' + str(page)
        get_info(url)
        page += 1
        break


if __name__ == '__main__':
    run()