python爬虫

爬虫：一段自动抓取互联网信息的程序，从互联网上抓取对于我们有价值的信息。

提取网页数据

# 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

字典定义请求头

# requests
# 导入
import requests
# url = 'https://www.baidu.com'
# url = '[图片]https://www.taobao.com/'
# url = '[图片]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)


#  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)

当当网图书爬虫实例

import requests
from lxml import html
import pandas as pd
import re
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
        price1 = li.xpath('./p[@class="price"]/span[@class="search_now_price"]/text()')[0]
        strinfo = re.compile('¥')
        price = float(strinfo.sub('', price1))
        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')

豆瓣网重庆地区上映电影爬虫

要求：

1、电影名，上映日期，类型，上映国家，想看人数
2、根据想看人数进行排序
3、绘制即将上映电影国家的占比图
4、绘制top5最想看的电影

import requests
import jieba
from lxml import html
from wordcloud import WordCloud
from matplotlib import pyplot as plt
plt.rcParams["font.sans-serif"] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False
def spider_movie(address):
    movie_list = []
    url = 'https://movie.douban.com/cinema/later/{}'.format(address)
    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)
    div_list = selector.xpath('//div[@id="showing-soon"]/div')
    print('共有{}部电影即将上映'.format(len(div_list)))

    for div in div_list:
        # 电影名
        name = div.xpath('./div[@class="intro"]/h3/a/text()')[0]
        # print(name)

        # 上映日期
        day = div.xpath('./div[@class="intro"]/ul/li/text()')[0]
        # print(day)

        # 类型
        type = div.xpath('./div[@class="intro"]/ul/li/text()')[1]
        # print(type)

        # 上映国家
        country = div.xpath('./div[@class="intro"]/ul/li/text()')[2]
        # print(country)

        # 想看人数
        div_three = div.xpath('./div[@class="intro"]/ul/li')[3]
        number = div_three.xpath('./span/text()')[0]
        number = str(number).replace('人想看', '')
        number = int(number)
        # print(number)

        # 添加电影信息
        movie_list.append({
            'name':name,
            'day':day,
            'type':type,
            'country':country,
            'number':number
        })

    # 排序
    movie_list.sort(key=lambda x:x['number'], reverse=True)

    # 遍历
    for movie in movie_list:
        print(movie)

    # 绘制即将上映电影最想看前五人数占比图
    top5_movie = [movie_list[i] for i in range(4)]
    labels = [x['name'] for x in top5_movie]
    # print(labels)
    counts = [x['number'] for x in top5_movie]
    # print(counts)
    colors = ['red', 'purple', 'yellow', 'gray', 'green']
    plt.pie(counts, labels=labels, autopct='%1.2f%%', colors=colors)
    plt.legend(loc=2)
    plt.axis('equal')
    plt.show()

     # 绘制即将上映电影国家的占比图
    total = [x['country'] for x in movie_list]
    text = ''.join(total)
    print(text)
    words_list = jieba.lcut(text)
    print(words_list)
    counts = {}
    excludes ={"大陆"}
    for word in words_list:
        if len(word) <= 1:
            continue
        else:
            counts[word] = counts.get(word, 0) + 1
    print(counts)
    for word in excludes:
        del counts[word]
    items = list(counts.items())
    print(items)
    items.sort(key=lambda x: x[1], reverse=True)
    print(items)
    numm = [] # 数量
    labels = [] # 国家
    for i in range(len(items)):
        x, y = items[i]
        numm.append(y)
        if(x == "中国"):
            x = "中国大陆"
        labels.append(x)
    plt.pie(numm, labels=labels, autopct='%1.2f%%')
    plt.legend(loc=2)
    plt.axis('equal')
    plt.show()

    # top5.png
    text = ' '.join(labels)
    WordCloud(
        font_path='MSYH.TTC',
        background_color='white',
        width=800,
        height=600,
        collocations=False
    ).generate(text).to_file('top5.png')

spider_movie('chongqing')