Python实战作业1-2：获取本地网页数据

任务：

Snip20170521_5.png

成果：

{'Title': 'EarPod', 'PicLink': 'http://localhost:63342/1_2/1_2answer_of_homework/img/pic_0000_073a9256d9624c92a05dc680fc28865f.jpg', 'GradeStar': 5, 'Price': '$24.99', 'GradeNum': '65'}
{'Title': 'New Pocket', 'PicLink': 'http://localhost:63342/1_2/1_2answer_of_homework/img/pic_0005_828148335519990171_c234285520ff.jpg', 'GradeStar': 4, 'Price': '$64.99', 'GradeNum': '12'}
{'Title': 'New sunglasses', 'PicLink': 'http://localhost:63342/1_2/1_2answer_of_homework/img/pic_0006_949802399717918904_339a16e02268.jpg', 'GradeStar': 4, 'Price': '$74.99', 'GradeNum': '31'}
{'Title': 'Art Cup', 'PicLink': 'http://localhost:63342/1_2/1_2answer_of_homework/img/pic_0008_975641865984412951_ade7a767cfc8.jpg', 'GradeStar': 3, 'Price': '$84.99', 'GradeNum': '6'}
{'Title': 'iphone gamepad', 'PicLink': 'http://localhost:63342/1_2/1_2answer_of_homework/img/pic_0001_160243060888837960_1c3bcd26f5fe.jpg', 'GradeStar': 4, 'Price': '$94.99', 'GradeNum': '18'}
{'Title': 'Best Bed', 'PicLink': 'http://localhost:63342/1_2/1_2answer_of_homework/img/pic_0002_556261037783915561_bf22b24b9e4e.jpg', 'GradeStar': 4, 'Price': '$214.5', 'GradeNum': '18'}
{'Title': 'iWatch', 'PicLink': 'http://localhost:63342/1_2/1_2answer_of_homework/img/pic_0011_1032030741401174813_4e43d182fce7.jpg', 'GradeStar': 4, 'Price': '$500', 'GradeNum': '35'}
{'Title': 'Park tickets', 'PicLink': 'http://localhost:63342/1_2/1_2answer_of_homework/img/pic_0010_1027323963916688311_09cc2d7648d9.jpg', 'GradeStar': 4, 'Price': '$15.5', 'GradeNum': '8'}

代码：

from bs4 import BeautifulSoup

path = './index.html'
url = 'http://localhost:63342/1_2/1_2answer_of_homework/'

with open(path,'r')as f:
    soup = BeautifulSoup(f.read(),'lxml')

PicLinks = soup.select('body > div > div > div.col-md-9 > div > div > div > img')
Prices = soup.select('body > div > div > div.col-md-9 > div > div > div > div.caption > h4.pull-right')
Titles = soup.select('body > div > div > div.col-md-9 > div > div > div > div.caption > h4 > a')
GradeNums = soup.select('body > div > div > div.col-md-9 > div > div > div > div.ratings > p.pull-right')
GradeStars = soup.select('body > div > div > div.col-md-9 > div > div > div > div.ratings > p')

#使用函数对数据进行分割并统计星星数量
def GetStar (GradeStar):
        a = str(GradeStar)           #将数据类型转换成字符串
        b = a.split('\"')       #按双引号规则进行分割
        num = 0           #设定起始星星数
        for c in b:
            if c == 'glyphicon glyphicon-star':
                num += 1
        return num


for PicLink,Price,Title,GradeNum,GradeStar in zip(PicLinks,Prices,Titles,GradeNums,GradeStars[1::2]):        #通过GradeStars[1::2]筛选出奇数列数据
    data = {
        'PicLink': url + PicLink.get('src'),
        'Price': Price.get_text(),
        'Title': Title.get_text(),
        'GradeNum': GradeNum.get_text().split()[0],     #采用split方法去除reviews，取数字部分
        'GradeStar':GetStar(GradeStar)
    }
    print(data)

星星统计思路：

第一步对获取的数据列表按奇数进行遍历；
第二步对遍历的数据进行分割；
第三步对分割的数据进行比对，同时进行计数