爬虫
# 大数据
# 提取本地html中的数据
# 1. 新建html文件
# 2. 读取
# 3. 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)
# 获取 p标签的内容
requests
# 导入
import requests
url = 'https://www.baidu.com'
url = 'https://www.taobao.com/'
url = 'http://www.dangdang.com/'
response = requests.get(url)
print(response)
# 获取str类型的响应
print(response.text)
# 获取bytes类型的响应
print(response.content)
# 获取响应头
print(response.headers)
# 获取状态码
print(response.status_code)
print(response.encoding)
# resp = requests.get('https://www.zhihu.com/')
# print(resp.status_code)
# 使用字典定义请求头
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('https://www.zhihu.com/', headers = headers)
print(resp.status_code)
提取当当网数据
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):
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')
抓取豆瓣网
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()
上映国家占比图
top5最想看的电影
