提取网页数据
#爬虫
#大数据
#提取本地html文件
#使用xpath语法进行提取
#使用lxml中的xpath
#使用lxml提取h1中的内容
from lxml import html #若报错找不到指定的模块，就卸载掉然后再安装
#提取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，获取selector对象
selector=html.fromstring(html_data)
#selector中调用xpath方法
#要获取标签中的内容，末尾要加text()
h1=selector.xpath('/html/body/h1/text()')
print(h1[0])
#//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]container
a=selector.xpath('//div[@class="container"]/a/text()')
print(a[0])
p=selector.xpath('//div[@class="container"]/p/text()')
print(p[0])
#获取属性值
link=selector.xpath('//div[@id="container"]/a/@href')
print(link[0])
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<title>王者荣耀</title>
</head>
<body>
<h1>欢迎来到王者荣耀</h1>
<ul>
<li><a href="https://pvp.qq.com/web201605/herodetail/508.shtml" ><img src="https://game.gtimg.cn/images/yxzj/img201606/heroimg/508/508.jpg"> 伽罗</a></li>
<li><a href="https://pvp.qq.com/web201605/herodetail/174.shtml"><img src="https://game.gtimg.cn/images/yxzj/img201606/heroimg/174/174.jpg"> 虞姬</a> </li>
<li><a href="https://pvp.qq.com/web201605/herodetail/135.shtml"><img src="https://game.gtimg.cn/images/yxzj/img201606/heroimg/135/135.jpg" > 项羽</a></li>
<li><a href="https://pvp.qq.com/web201605/herodetail/109.shtml"><img src="https://game.gtimg.cn/images/yxzj/img201606/heroimg/109/109.jpg"> 妲己</a> </li>
</ul>
<ol>
<li>坦克</li>
<li>法师</li>
<li>射手</li>
<li>刺客</li>
</ol>
<div>这是div标签</div>
<div class="container">
<p>被动：伽罗的普工与技能伤害将会有限对于表的护盾效果造成一次等额伤害</p>
<a href="https://www.baidu.com">点击跳转</a>
</div>
<div>这是第二个div标签</div>
</body>
</html>
image.png
爬虫当当网
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)]
# top10_store=[]
# for i in range(10):
# top10_store.append(book_list[i])
# x=[]
# for store in top10_store:
# x.append(store['store'])
x=[x['store'] for x in top10_store]
print(x)
#y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')
spider_dangdang('9787115428028')
image.png
爬虫豆瓣网
import jieba
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_douban():
move_list = []
# 目标站点地址
url = 'https://movie.douban.com/cinema/later/chongqing/'
# 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
selector = html.fromstring(html_data)
ul_list = selector.xpath('//div[@id="showing-soon"]/div')
print('您好，共有{}部电影即将上映'.format(len(ul_list)))
# 遍历 ul_list
for li in ul_list:
# 电影名称
title = li.xpath('./div/h3/a/text()')[0]
print(title)
# 电影链接
link = li.xpath('./div/h3/a/@href')[0]
# print(link)
# 上映日期
date = li.xpath('./div/ul/li/text()')[0]
# print(date)
# 类型
type_list = li.xpath('./div/ul/li/text()')[1]
# print(type_list)
# 上映国家
contry = li.xpath('./div/ul/li/text()')[2]
# print(contry)
# 想看人数
person_num = li.xpath('./div/ul/li[4]/span/text()')[0]
person_num =int(person_num.replace('人想看',''))
# print(person_num)
# 添加每一个电影的信息
move_list.append({
'title':title,
'date':date,
'link':link,
'type_list':type_list,
'contry':contry,
'person_num':person_num
})
# 根据想看人数进行排序
move_list.sort(key=lambda x:x['person_num'],reverse=True)
# 遍历move_list
contry1=[]
for move in move_list:
contry1.append(move['contry'])
print(move)
# 展示top5最想看的电影 柱状图
top5_store = [move_list[i] for i in range(5)]
x=[x['title'] for x in top5_store]
print(x)
#y图书的价格
y=[x['person_num'] for x in top5_store]
print(y)
# plt.bar(x,y)
plt.barh(x,y)
plt.show()
print(contry1)
counts = {}
# 2.分词
for word1 in contry1:
if len(word1) <= 1:
continue
else:
counts[word1] = counts.get(word1, 0) + 1
print(counts)
lab = counts.keys()
cou = counts.values()
print(lab)
print(cou)
plt.pie(cou, labels=lab, shadow=True, autopct='%1.1f%%')
plt.legend(loc=2)
plt.axis('equal')
plt.show()
spider_douban()
image.png
image.png
