爬虫
读取本地html文件数据
# 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
1.导入lxml
from lxml import html
- 读取html文件
with open('./index.html','r',enconding='utf-8') as f:
html_data = f.read()
- 解析html文件，获得selector对象,selector中调用xpath方法
h1 = selector.xpath('/html/body/h1/text()') #要获取标签中的内容，末尾要加上text()
# // 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()
读取网站数据
# 200 ok 404 500
# 没有添加请求头的知乎网站
# 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)
1.需要加入请求头
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"}
- 访问
resp = requests.get('https://www.zhihu.com/', headers = headers)
3.返回值为200标识成功
4.提取当当网书籍信息，可以将html页面写入本地
import requests
def spider_dangdang(isbn):
# 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
spider_dangdang('9787115428028')
.eg 读取网站https://movie.douban.com/cinema/later/chongqing/最近上映电影信息，并且根据国家比例做饼图，以及人们想看数做条形统计图
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 movie():
movie_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
# 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="showing-soon"]/div')
print('您好，共有{}部电影'.format(len(ul_list)))
# 遍历 ul_list
for li in ul_list:
# 电影名称
title = li.xpath('//div[@id="showing-soon"]/div/div[@class="intro"]/h3/a/text()')
# print(title)
# 上映日期
link = li.xpath('//div[@id="showing-soon"]/div/div[@class="intro"]/ul/li[1]/text()')
# print(link)
# 类型
price = li.xpath('//div[@id="showing-soon"]/div/div[@class="intro"]/ul/li[2]/text()')
#国家
country = li.xpath('//div[@id="showing-soon"]/div/div[@class="intro"]/ul/li[3]/text()')
coNum = country
# 想看人数
store = li.xpath('//div[@id="showing-soon"]/div/div[@class="intro"]/ul/li[@class="dt last"]/span/text()')
want = []
for i in store:
# print(i)
i = int(i.replace('人想看',''))
want.append(i)
# 添加每一个电影的信息
for i in range(22):
movie_list.append({
'name':title[i],
'type':price[i],
'date':link[i],
'want':want[i],
'country':country[i]
})
counts = {}
lk = []
ll =[]
print(coNum)
for word in coNum:
counts[word] = counts.get(word, 0) + 1
print(len(counts))
count = list(counts.items())
for i in range(len(counts)):
countrys, cons = count[i]
cons = int(cons)
countrys = str(countrys)
lk.append(countrys)
ll.append(cons)
print(countrys)
print(cons)
explode = [0.1, 0, 0, 0]
# colors = ['red', 'purple','blue', 'yellow','gray','green','bl']
plt.pie(ll, shadow=True, explode=explode, labels=lk, autopct='%1.1f%%')
plt.legend(loc=2)
plt.axis('equal')
plt.show()
# 按想看人数进行排序
movie_list.sort(key=lambda x:x['want'] ,reverse=True)
# # 遍历booklist
# for movie in movie_list:
# print(movie)
#
# # 展示最想看的前5个电影 柱状图
# 电影名称
top5_movie = [movie_list[i] for i in range(5)]
# x = []
# for store in top10_store:
# x.append(store['store'])
x = [x['name'] for x in top5_movie]
# print(x)
# 想看人数
y = [x['want'] for x in top5_movie]
# print(y)
# for i in range(5):
# print(top5_movie[i])
plt.barh(x, y)
plt.show()
# # 存储成csv文件
df = pd.DataFrame(movie_list)
df.to_csv('dangdang.csv')
movie()
- 统计国家出现次数,并且制作饼图，饼图以及条形统计图在上一篇文章讲过
counts = {}
lk = []
ll =[]
print(coNum)
for word in coNum:
counts[word] = counts.get(word, 0) + 1
print(len(counts))
count = list(counts.items())
for i in range(len(counts)):
countrys, cons = count[i]
cons = int(cons)
countrys = str(countrys)
lk.append(countrys)
ll.append(cons)
print(countrys)
print(cons)
explode = [0.1, 0, 0, 0]
# colors = ['red', 'purple','blue', 'yellow','gray','green','bl']
plt.pie(ll, shadow=True, explode=explode, labels=lk, autopct='%1.1f%%')
plt.legend(loc=2)
plt.axis('equal')
plt.show()
- 根据想看人数前五进行话条形统计图
top5_movie = [movie_list[i] for i in range(5)]
# x = []
# for store in top10_store:
# x.append(store['store'])
x = [x['name'] for x in top5_movie]
# print(x)
# 想看人数
y = [x['want'] for x in top5_movie]
# print(y)
# for i in range(5):
# print(top5_movie[i])
plt.barh(x, y)
plt.show()
# # 存储成csv文件
df = pd.DataFrame(movie_list)
df.to_csv('dangdang.csv')