爬虫

1.当当网根据书籍ibsn截取数据

from lxml import html
import requests
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
    # 酱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('当前共有{}家店铺在售卖此书'.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=price.replace('￥','')
        print(price)
        #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)
        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 = [x['store'] for x in top10_store]
    # print(x)
    y = [x['price'] for x in top10_store]
    # print(y)
    plt.barh(x, y)
    plt.show()

    # 存储成为csv文件
    df = pd.DataFrame(book_list)
    df.to_csv('dangdang.csv')
spider_dangdang('9787115428028')

2.做受欢迎预播电影排序

from lxml import html
import  requests
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():
    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
    # print(html_data)
    selector = html.fromstring(html_data)
    ul_list = selector.xpath('//div[@id="showing-soon"]/div')
    print('当前共有{}场即将上映的电影'.format(len(ul_list)))


    for li in ul_list:
        name = li.xpath('./div[@class="intro"]/h3/a/text()')[0]
        # print(name)
        date = li.xpath('./div[@class="intro"]/ul/li/text()')[0]
        # print(date)
        type = li.xpath('./div[@class="intro"]/ul/li/text()')[1]
        # print(type)
        country =li.xpath('./div[@class="intro"]/ul/li/text()')[2]
        # print(country)
        user =li.xpath('./div[@class="intro"]/ul/li/span/text()')[0]
        # print(user)
        user=int(user.replace("人想看",""))

        movie_list.append({
                'name': name,
                'date': date,
                'type': type,
                'country': country,
                'user':user
            })
    movie_list.sort(key=lambda x: x['user'],reverse=True)
    # for name_c in movie_list:
    #     print(name_c)
    for  movie in movie_list:
        print(movie)
    top5 = [movie_list[i] for i in range(5)]
    x = [x['name'] for x in top5]
        # print(x)
    y = [x['user'] for x in top5]
    # print(y)
    plt.title("最想看的电影")
    plt.bar(x, y)
    plt.show()

    country = []
    for city in movie_list:
        country.append((city['country']))
    c = {}
    # 将国家信息汇总
    for city in country:
        c[city] = c.get(city, 0) + 1
    print(c)
    items = list(c.items())
    # 分别提取国家名和次数
    baifeibi = []
    guojia = []
    for i in range(len(items)):
        city, bai = items[i]
        baifeibi.append(bai)
        guojia.append(city)
    plt.pie(baifeibi, labels=guojia, autopct='%1.1f%%')
    plt.show()

    plt.show()
    df = pd.DataFrame(movie_list)
    df.to_csv("douban.txt")




    # count=[]
    # label=[]
    # for i in range(len(movie_list)):
    #     counts.append(movie_list[i]['count'])
    #     labels.append(peo_li[i]['name'])
    # # 距离圆心点距离
spider_douban()