当当网图书爬虫

import requests
from lxml import html

1.获取目标站点的源代码

url = 'http://search.dangdang.com/?key=9787115428028&act=input'
html_data = requests.get(url).text

2.xpath提取

selector = html.fromstring(html_data)

#获取所有图书的价格
#price = selector.xpath('//div[@id="search_nature_rg"]/ul/li[1]/p[3]/span[1]/text()')
#print(price)

ul_list = selector.xpath('//div[@id="search_nature_rg"]/ul/li')
print(len(ul_list))

3.遍历

for li in ul_list:
    # 价格
    price = li.xpath('p[3]/span[1]/text()')
    print(price)

    # 书名
    name = li.xpath('p[1]/a[1]/text()')
    print(name)

    # 购买链接
    link = li.xpath('p[1]/a[1]/@href')
    print(link)

    # 店铺名称
    store = li.xpath('p[4]/a[1]/text()')
    print(store)

当当网爬虫2.0

import requests
from lxml import html
import pandas as pd

def spider(isbn):
    book_list = []
    # 获取目标站点的源代码
    # 如何格式化字符串-format方法
    url = 'http://search.dangdang.com/?key={}&act=input'.format(isbn)
    html_data = requests.get(url).text
    #  xpath提取
    selector = html.fromstring(html_data)
    ul_lsit = selector.xpath('//div[@id="search_nature_rg"]/ul/li')
    print('共有{}家售卖此书'.format(len(ul_lsit)))
    # 遍历
    for li in ul_lsit:
        # 价格
        price = li.xpath('p[3]/span[1]/text()')[0]
        price = price.replace('¥', '')
        price = float(price)
        # 书名
        book_name = li.xpath('p[@class="name"]/a/@title')[0]
        # 购买链接
        link = li.xpath('p[@class="name"]/a/@href')[0]
        # 店铺名称
        store = li.xpath('p[@class="search_shangjia"]/a[1]/text()')
        if len(store) == 0:
            store = '当当自营'
        else:
            store = store[0]
        book_list.append({
            'book_name': book_name,
            'link':link,
            'price':price,
            'store':store
        })
    # 排序
    book_list.sort(key=lambda x: x['price'], reverse=True)
    # 重新遍历显示每家商铺的信息
    for book in book_list:
        print(book)
    # 存储 csv
    df = pd.DataFrame(book_list)
    df.to_csv('dangdang.csv')
isbn = input('请输入书号')
# 9787115428028
spider(isbn)