提取网页中数据
#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])
获取响应
#导入
import requests
url='https://www.baidu.com'
response=requests.get(url)
print(response)
#获取str类型的响应
#response常用
print(response.text)
#获取bytes类型的响应,下载图片用到
print(response.content)
#获取响应头，
print(response.headers)
#获取状态码:200 404 500
print(response.status_code)
#获取编码
print(response.encoding)
当当网爬虫数据
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):
booklist=[]
#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)
#提取目标站点的信息
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)
#添加每一个商家信息
booklist.append({
'title':title,
'price':price,
'link':link,
'store':store
})
#按照价格进行排序
booklist.sort(key=lambda x:x['price'],reverse=True)
#遍历booklist
for book in booklist:
print(book)
#展示价格最低的前10家 柱状图
#店铺名称
top10_store=[booklist[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.barh(x,y)
plt.show()
#存储为CSV文件
df=pd.DataFrame(booklist)
df.to_csv('dangdang.csv')
spider_dangdang('9787115428028')
豆瓣网爬虫
#练习：https://movie.douban.com/cinema/later/chongqing/
#电影名，上映日期，类型，上映国家，想看人数
#根据想看人数进行排序
#绘制即将上映电影国家的占比图
#绘制top5最想看的电影
#请求远程端站点
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
counts={}
# 目标站点地址
def spider_douban():
movie_list=[]
url = 'https://movie.douban.com/cinema/later/chongqing/'
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)
#提取目标站信息
selector = html.fromstring(html_data)
ul_list = selector.xpath('//div[@id="showing-soon"]/div/div')
print('您好，共有{}部电影即将在重庆上映'.format(len(ul_list)))
# 遍历ul_list
for li in ul_list:
# 电影名称
title = li.xpath('./h3/a/text()')[0].strip()
print(title)
# 上映日期
date = li.xpath('./ul/li/text()')[0]
print(date)
# 类型
type = li.xpath('./ul/li/text()')[1]
print(type)
# 上映国家
country = li.xpath('./ul/li/text()')[2]
print(country)
# 想看人数
num = li.xpath('./ul/li/span/text()')[0]
print(num)
num = int(num.replace('人想看', ''))
#添加电影信息
movie_list.append({
'title':title,
'date': date,
'type':type,
'country':country,
'num':num
})
#按照人数进行排序
movie_list.sort(key=lambda x:x['num'],reverse=True)
#遍历booklist
for movie in movie_list:
print(movie)
#画饼图，把国家提取出来
city=[]
# 提取国家信息
for country in movie_list:
city.append((country['country']))
# 将国家信息汇总
for country in city:
if len(country) <= 1:
continue
else:
counts[country] = counts.get(country, 0) + 1
items = list(counts.items())
print(items)
movie_name=[]
people=[]
for i in range(4):
role, count = items[i]
print(role, count)
movie_name.append(role)
people.append(count)
#绘制即将上映电影国家的占比图，饼图
explode = [0.1, 0, 0, 0]
plt.pie(people, explode=explode,labels=movie_name, shadow=True, autopct='%1.1f%%')
plt.axis('equal') # 保证饼状图是正圆，否则会有点扁
plt.show()
# 展示最想看的前5家，柱状图
# 电影名称
top5_movie = [movie_list[i] for i in range(5)]
print(top5_movie)
x = [x['title'] for x in top5_movie]
print(x)
# 想看人数
y = [x['num'] for x in top5_movie]
print(y)
plt.bar(x,y)
#plt.barh(x,y)
plt.show()
存储成csv文件
df = pd.DataFrame(movie_list)
df.to_csv('douban.csv')
spider_douban()
