爬虫
大数据
提取本地html中的数据
- 新建html文件
- 读取
- 使用xpath语法进行提取
使用 lxml 中的xpath
使用lxml提取 h1标签中的内容
from lxml import html
读取html文件
with open('./index.html', 'r', encoding='utf-8') as f:
html_data = f.read()
print(html_data)
解析html文件，获得selector对象
selector = html.fromstring(html_data)
selector中调用xpath方法
要获取标签中的内容，末尾要添加text()
h1 = selector.xpath('/html/body/h1/text()')
print(h1[0])
// 可以代表从任意位置出发、
//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)
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)
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)
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')
