# 目标站点地址
url = 'http://search.dangdang.com/?key={}&act=input'.format(isbn)
# print(url)
# 获取站点str类型的响应
headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.142 Safari/537.36"}
resp = requests.get(url, headers=headers)
html_data = resp.text
# 将html页面写入本地
# with open('dangdang.html', 'w', encoding='utf-8') as f:
# f.write(html_data)
# 提取目标站的信息
selector = html.fromstring(html_data)
ul_list = selector.xpath('//div[@id="search_nature_rg"]/ul/li')
print('您好，共有{}家店铺售卖此图书'.format(len(ul_list)))
# 遍历 ul_list
for li in ul_list:
# 图书名称
title = li.xpath('./a/@title')[0].strip()
print(title)
# 图书购买链接
link = li.xpath('a/@href')[0]
print(link)
# 图书价格
price = li.xpath('./p[@class="price"]/span[@class="search_now_price"]/text()')[0]
price = float(price.replace('￥',''))
print(price)
# 图书卖家名称
store = li.xpath('./p[@class="search_shangjia"]/a/text()')
# if len(store) == 0:
# store = '当当自营'
# else:
# store = store[0]
store = '当当自营' if len(store) == 0 else store[0]
print(store)
-- coding: utf-8 --
@Time : 2019/7/31 11:28
@Author : Eric Lee
@Email : li.yan_li@neusoft.com
@File : spider_dangdang.py
@Software: PyCharm
import requests
from lxml import html
import pandas as pd
from matplotlib import pyplot as plt
plt.rcParams["font.sans-serif"] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False
def spider_dangdang(isbn):
book_list = []
# 目标站点地址
url = 'http://search.dangdang.com/?key={}&act=input'.format(isbn)
# print(url)
# 获取站点str类型的响应
headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.142 Safari/537.36"}
resp = requests.get(url, headers=headers)
html_data = resp.text
# 将html页面写入本地
# with open('dangdang.html', 'w', encoding='utf-8') as f:
# f.write(html_data)
# 提取目标站的信息
selector = html.fromstring(html_data)
ul_list = selector.xpath('//div[@id="search_nature_rg"]/ul/li')
print('您好，共有{}家店铺售卖此图书'.format(len(ul_list)))
# 遍历 ul_list
for li in ul_list:
# 图书名称
title = li.xpath('./a/@title')[0].strip()
# print(title)
# 图书购买链接
link = li.xpath('a/@href')[0]
# print(link)
# 图书价格
price = li.xpath('./p[@class="price"]/span[@class="search_now_price"]/text()')[0]
price = float(price.replace('￥',''))
# print(price)
# 图书卖家名称
store = li.xpath('./p[@class="search_shangjia"]/a/text()')
# if len(store) == 0:
# store = '当当自营'
# else:
# store = store[0]
store = '当当自营' if len(store) == 0 else store[0]
# print(store)
# 添加每一个商家的图书信息
book_list.append({
'title':title,
'price':price,
'link':link,
'store':store
})
# 按照价格进行排序
book_list.sort(key=lambda x:x['price'])
# 遍历booklist
for book in book_list:
print(book)
# 展示价格最低的前10家 柱状图
# 店铺的名称
top10_store = [book_list[i] for i in range(10)]
# x = []
# for store in top10_store:
# x.append(store['store'])
x = [x['store'] for x in top10_store]
print(x)
# 图书的价格
y = [x['price'] for x in top10_store]
print(y)
# plt.bar(x, y)
plt.barh(x, y)
plt.show()
# 存储成csv文件
df = pd.DataFrame(book_list)
df.to_csv('dangdang.csv')
爬虫
1、爬虫基础
1.1、获取网址
url='https://www.baidu.com'
response=requests.get(url)
1.2、获取str类型的响应
print(response.text)
1.3、获取bytes类型的响应
print(response.content)
1.4、获取响应头
print(response.headers)
1.5、获取状态码
print(response.status_code)
1.6、返回200成功，400未找到，500服务器错误
1.7、响应头用以伪装成浏览器
#没有添加响应头
# resp=requests.get('https://www.zhihu.com/')
# print(resp.status_code)
#运行返回400
#使用字典定义请求头
headers={"User-Agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36"}
resp=requests.get('https://pvp.qq.com/')
print(resp.status_code)
#运行返回200
2、静态网页爬虫
2.1、导入lxml库
from lxml import html
2.2、打开并读取本地html文件
with open('./index.html','r',encoding='utf-8') as f:
html_data=f.read()
print(html_data)
2.3、解析html文件，获取selector对象
selector =html.fromstring(html_data)
#要获取标签内容，末尾要添加text（）
h1=selector.xpath('/html/body/h1/text()')
print(h1[0])
2.4、//表示可以代表任意位置出发
#//标签1[@属性=属性值]/标签2[@属性=属性值]..../text（）
a=selector.xpath('//div[@id="container"]/a/text()')
print(a)
