0基础python实战：1_2homework

作者: 翀Chen翀 | 来源:发表于2016-11-09 23:45 被阅读0次

0基础python实战：1_2homework
Python网络爬虫实战之十四：Scrapy结合scrapy-s
Python网络爬虫实战之七：动态网页爬取案例实战 Seleni
Python网络爬虫实战之八：动态网页爬取案例实战 Seleni
Python网络爬虫实战之九：Selenium进阶操作与爬取京东
Python网络爬虫实战之十一：Scrapy爬虫框架入门介绍
Python网络爬虫实战之十三：Scrapy爬取名侦探柯南漫画集
Python网络爬虫实战之六：静态网页爬取案例实战
Python网络爬虫实战之二：环境部署、基础语法、文件操作
Python网络爬虫实战之一：网络爬虫理论基础

程序部分：

def bubble_sort(data):

#冒泡排序

for i in range(0,len(data)):#注意不是len(data)-1,因为(a,b)表示从a到b-1

for j in range(0,len(data)):

if i>j:

if data[j]>data[i]:

tmp1=data[i]

data[i]=data[j]

data[j]=tmp1

return data

from bs4 import BeautifulSoup

path='D:/课程源码及作业参考答案/Plan-for-combating-master/week1/1_2/1_2answer_of_homework/1_2_homework_required/index.html'

info0=[]

with open(path,'r') as wb_data:

soup=BeautifulSoup(wb_data,'lxml')

stars=soup.select('body > div > div > div.col-md-9 > div > div > div > div.ratings > p:nth-of-type(2)')

addres = 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')

reviews = soup.select('body > div > div > div.col-md-9 > div > div > div > div.ratings > p.pull-right')

titles = soup.select('body > div > div > div.col-md-9 > div > div > div > div.caption > h4 > a')

#list(stars.stripped_strings)

import re

for star,addre, price, review, title in zip(stars,addres,prices,reviews,titles):

data0=[

'star: '+str(len(star.find_all('span',class_='glyphicon glyphicon-star'))),

'price: ' + price.get_text(),

'review: ' + str(re.findall(r'\d+', review.get_text())), # 正则表达式,目标输出结果为review：[65]

'addre: '+addre.get('src'),

#'review: '+review.get_text(),

'title: '+title.get_text()

]

print(data0)

info0.append(data0)

#以下程序根据星星数、价格、评论数进行排序

infos=[]

infop=[]

infor=[]

for k in range(0,len(info0)):

s=int(re.sub(r'\D+','',info0[k][0]))#将非字符串找到并用空格替换

p=float(re.sub(r'\D+','',info0[k][1]))#将非字符串找到并用空格替换

r=int(re.sub(r'\D+','',info0[k][2]))#将非字符串找到并用空格替换

infos.append(s)

infop.append(p)

infor.append(r)

print(bubble_sort(infos))

print(bubble_sort(infop))

print(bubble_sort(infor))

print('根据星星数排列：')

for i in range(0,len(info0)):

for j in range(0,len(info0)):

if int(re.sub(r'\D+', '', info0[i][0]))==int(infos[j]):

tmp=info0[i]

info0[i]=info0[j]

info0[j]=tmp

for i in range(0,len(info0)):

print(info0[i])

print('根据价格排列：')

for i in range(0,len(info0)):

for j in range(0,len(info0)):

if int(re.sub(r'\D+', '', info0[i][1]))==int(infop[j]):

tmp=info0[i]

info0[i]=info0[j]

info0[j]=tmp

for i in range(0,len(info0)):

print(info0[i])

print('根据评论数排列：')

for i in range(0,len(info0)):

for j in range(0,len(info0)):

if int(re.sub(r'\D+', '', info0[i][2]))==int(infor[j]):

tmp=info0[i]

info0[i]=info0[j]

info0[j]=tmp

for i in range(0,len(info0)):

print(info0[i])

运行结果：

根据星星数排列：

['star: 4', 'price: $15.5', "review: ['8']", 'addre: img/pic_0010_1027323963916688311_09cc2d7648d9.jpg', 'title: Park tickets']

['star: 4', 'price: $500', "review: ['35']", 'addre: img/pic_0011_1032030741401174813_4e43d182fce7.jpg', 'title: iWatch']

['star: 4', 'price: $214.5', "review: ['18']", 'addre: img/pic_0002_556261037783915561_bf22b24b9e4e.jpg', 'title: Best Bed']

['star: 4', 'price: $94.99', "review: ['18']", 'addre: img/pic_0001_160243060888837960_1c3bcd26f5fe.jpg', 'title: iphone gamepad']

['star: 4', 'price: $74.99', "review: ['31']", 'addre: img/pic_0006_949802399717918904_339a16e02268.jpg', 'title: New sunglasses']

['star: 4', 'price: $64.99', "review: ['12']", 'addre: img/pic_0005_828148335519990171_c234285520ff.jpg', 'title: New Pocket']

['star: 3', 'price: $84.99', "review: ['6']", 'addre: img/pic_0008_975641865984412951_ade7a767cfc8.jpg', 'title: Art Cup']

['star: 5', 'price: $24.99', "review: ['65']", 'addre: img/pic_0000_073a9256d9624c92a05dc680fc28865f.jpg', 'title: EarPod']

根据价格排列：