1.爬虫

1. 大数据 , 提取本地hmtl中的数据
2. 步骤
   ①新建html文件
   ②读取
   ③使用lxml中的xpath语法进行提取

from lxml import html
# 读取html文件
with open('./index.html', 'r', encoding='utf-8') as f:
    html_data = f.read()
    # selector中调用xpath方法
    selector = html.fromstring(html_data)
    # 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[0])
    # 获取p标签内容
    p = selector.xpath('//div[@id="container"]/p/text()')
    print(p[0])
    # 获取属性 @属性名
    link = selector.xpath('//div[@id="container"]/a/@href')
    print(link[0])

image.png

2.关于requests

# 导入
import requests
url = 'https://www.baidu.com'
# url = 'https://www.taobao.com'
# url = 'https://www.jd.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)
# 编码方式
print(response.encoding)
# 没有添加请求头的知乎网网站
# 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)

image.png

3.爬当当网

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)]
    # 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')
spider_dangdang('9787115428028')

image.png
image.png
价格最低Top10

4.练习--爬重庆-影讯

import requests
from lxml import html
from matplotlib import pyplot as plt
plt.rcParams["font.sans-serif"] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False
people_list = []
counts = []
# 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
# 提取目标站的信息
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
    people = li.xpath('./ul/li/span/text()')[0]
    people = int(people.replace('人想看', ''))
    # print(people)
    people_list.append({
        'title': title,
        'date': date,
        'type': type,
        'country': country,
        'people': people
    })
    counts.append(country)
# 按照想看人数进行排序
people_list.sort(key=lambda x:x['people'], reverse=True)
# 遍历people_list
for num in people_list:
    print(num)
# 展示想看人数top5
top5 = [people_list[i] for i in range(5)]
x = [x['title'] for x in top5]
print(x)
y = [x['people'] for x in top5]
print(y)
plt.barh(x, y)
plt.show()
# 国家占比
china = 0
japan = 0
hongkong = 0
russia = 0
for i in range(22):
    if counts[i] == '中国大陆':
        china += 1
    elif counts[i] == '日本':
        japan += 1
    elif counts[i] == '香港':
        hongkong += 1
    else:
        russia += 1
count1 = ['中国大陆', '日本', '香港', '俄罗斯']
count2 = [china, japan, hongkong, russia]
plt.pie(count2, shadow=True, labels=count1, autopct='%1.1f%%')
plt.legend(loc=2)
plt.axis('equal')
plt.show()

image.png
展示想看人数top5
电影国家占比