| 去哪儿网旅游信息可视化 | 您所在的位置：网站首页 › 去哪儿网网址 › 去哪儿网旅游信息可视化 |
去哪儿网旅游信息可视化
|
去哪儿网旅游信息可视化 一、摘要该项目爬取去哪儿网旅游数据进行数据可视化，使用pyecharts库进行实现。 二、选题背景：我国旅游行业的极速发展，因为疫情原因，使得国内旅游成为新风潮，由于国内疫情控制得当，使得中国成为最先开放旅游的国家， 本次项目可视化就是分析国内旅游的数据，分析适合出行旅游的时间与地点信息。 三、过程及代码： 1.设计爬取去哪儿网网页代码 import requests from bs4 import BeautifulSoup import re import time import csv import random #爬取每个网址的分页 fb = open(r'url.txt','w') url = 'http://travel.qunar.com/travelbook/list.htm?page={}&order=hot_heat&avgPrice=1_2' #请求头，cookies在电脑网页中可以查到 headers={'user-agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.87 Safari/537.360', 'cookies':'JSESSIONID=5E9DCED322523560401A95B8643B49DF; QN1=00002b80306c204d8c38c41b; QN300=s%3Dbaidu; QN99=2793; QN205=s%3Dbaidu; QN277=s%3Dbaidu; QunarGlobal=10.86.213.148_-3ad026b5_17074636b8f_-44df|1582508935699; QN601=64fd2a8e533e94d422ac3da458ee6e88; _i=RBTKSueZDCmVnmnwlQKbrHgrodMx; QN269=D32536A056A711EA8A2FFA163E642F8B; QN48=6619068f-3a3c-496c-9370-e033bd32cbcc; fid=ae39c42c-66b4-4e2d-880f-fb3f1bfe72d0; QN49=13072299; csrfToken=51sGhnGXCSQTDKWcdAWIeIrhZLG86cka; QN163=0; Hm_lvt_c56a2b5278263aa647778d304009eafc=1582513259,1582529930,1582551099,1582588666; viewdist=298663-1; uld=1-300750-1-1582590496|1-300142-1-1582590426|1-298663-1-1582590281|1-300698-1-1582514815; _vi=6vK5Gry4UmXDT70IFohKyFF8R8Mu0SvtUfxawwaKYRTq9NKud1iKUt8qkTLGH74E80hXLLVOFPYqRGy52OuTFnhpWvBXWEbkOJaDGaX_5L6CnyiQPPOYb2lFVxrJXsVd-W4NGHRzYtRQ5cJmiAbasK8kbNgDDhkJVTC9YrY6Rfi2; viewbook=7562814|7470570|7575429|7470584|7473513; QN267=675454631c32674; Hm_lpvt_c56a2b5278263aa647778d304009eafc=1582591567; QN271=c8712b13-2065-4aa7-a70b-e6156f6fc216', 'referer':'http://travel.qunar.com/travelbook/list.htm?page=1&order=hot_heat&avgPrice=1'} count = 1 #共200页 for i in range(1,201): url_ = url.format(i) try: response = requests.get(url=url_,headers = headers) response.encoding = 'utf-8' html = response.text soup = BeautifulSoup(html,'lxml') #print(soup) all_url = soup.find_all('li',attrs={'class': 'list_item'}) #print(all_url[0]) ''' for i in range(len(all_url)): #p = re.compile(r'data-url="/youji/\d+">') url = re.findall('data-url="(.*?)"', str(i), re.S) #url = re.search(p,str(i)) print(url) ''' print('正在爬取第%s页' % count) for each in all_url: each_url = each.find('h2')['data-bookid'] #print(each_url) fb.write(each_url) fb.write('\n') #last_url = each.find('li', {"class": "list_item last_item"})['data-url'] #print(last_url) time.sleep(random.randint(3,5)) count+=1 except Exception as e: print(e) url_list = [] with open('url.txt','r') as f: for i in f.readlines(): i = i.strip() url_list.append(i) the_url_list = [] for i in range(len(url_list)): url = 'http://travel.qunar.com/youji/' the_url = url + str(url_list[i]) the_url_list.append(the_url) last_list = [] def spider(): headers = { 'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.87 Safari/537.360', 'cookies': 'QN1=00002b80306c204d8c38c41b; QN300=s%3Dbaidu; QN99=2793; QN205=s%3Dbaidu; QN277=s%3Dbaidu; QunarGlobal=10.86.213.148_-3ad026b5_17074636b8f_-44df|1582508935699; QN601=64fd2a8e533e94d422ac3da458ee6e88; _i=RBTKSueZDCmVnmnwlQKbrHgrodMx; QN269=D32536A056A711EA8A2FFA163E642F8B; QN48=6619068f-3a3c-496c-9370-e033bd32cbcc; fid=ae39c42c-66b4-4e2d-880f-fb3f1bfe72d0; QN49=13072299; csrfToken=51sGhnGXCSQTDKWcdAWIeIrhZLG86cka; QN163=0; Hm_lvt_c56a2b5278263aa647778d304009eafc=1582513259,1582529930,1582551099,1582588666; viewdist=298663-1; uld=1-300750-1-1582590496|1-300142-1-1582590426|1-298663-1-1582590281|1-300698-1-1582514815; viewbook=7575429|7473513|7470584|7575429|7470570; QN267=67545462d93fcee; _vi=vofWa8tPffFKNx9MM0ASbMfYySr3IenWr5QF22SjnOoPp1MKGe8_-VroXhkC0UNdM0WdUnvQpqebgva9VacpIkJ3f5lUEBz5uyCzG-xVsC-sIV-jEVDWJNDB2vODycKN36DnmUGS5tvy8EEhfq_soX6JF1OEwVFXk2zow0YZQ2Dr; Hm_lpvt_c56a2b5278263aa647778d304009eafc=1582603181; QN271=fc8dd4bc-3fe6-4690-9823-e27d28e9718c', 'Host': 'travel.qunar.com' } count = 1 for i in range(len(the_url_list)): try: print('正在爬取第%s页'% count) response = requests.get(url=the_url_list[i],headers = headers) response.encoding = 'utf-8' html = response.text soup = BeautifulSoup(html,'lxml') information = soup.find('p',attrs={'class': 'b_crumb_cont'}).text.strip().replace(' ','') info = information.split('>') if len(info)>2: location = info[1].replace('\xa0','').replace('旅游攻略','') introduction = info[2].replace('\xa0','') else: location = info[0].replace('\xa0','') introduction = info[1].replace('\xa0','') other_information = soup.find('ul',attrs={'class': 'foreword_list'}) when = other_information.find('li',attrs={'class': 'f_item when'}) time1 = when.find('p',attrs={'class': 'txt'}).text.replace('出发日期','').strip() howlong = other_information.find('li',attrs={'class': 'f_item howlong'}) day = howlong.find('p', attrs={'class': 'txt'}).text.replace('天数','').replace('/','').replace('天','').strip() howmuch = other_information.find('li',attrs={'class': 'f_item howmuch'}) money = howmuch.find('p', attrs={'class': 'txt'}).text.replace('人均费用','').replace('/','').replace('元','').strip() who = other_information.find('li',attrs={'class': 'f_item who'}) people = who.find('p',attrs={'class': 'txt'}).text.replace('人物','').replace('/','').strip() how = other_information.find('li',attrs={'class': 'f_item how'}) play = how.find('p',attrs={'class': 'txt'}).text.replace('玩法','').replace('/','').strip() Look = soup.find('span',attrs={'class': 'view_count'}).text.strip() if time1: Time = time1 else: Time = '-' if day: Day = day else: Day = '-' if money: Money = money else: Money = '-' if people: People = people else: People = '-' if play: Play = play else: Play = '-' last_list.append([location,introduction,Time,Day,Money,People,Play,Look]) #设置爬虫时间 time.sleep(random.randint(3,5)) count+=1 except Exception as e : print(e) #写入csv with open('Travel.csv', 'a', encoding='utf-8-sig', newline='') as csvFile: csv.writer(csvFile).writerow(['地点', '短评', '出发时间', '天数','人均费用','人物','玩法','浏览量']) for rows in last_list: csv.writer(csvFile).writerow(rows) if __name__ == '__main__': spider()
根据网页结构获取所需要的数据值,将数据插入csv文件，共爬取了1603个页面的数据
2.设计数据可视化代码
(1)读取爬取到的The_Travel.csv文件 import pandas as pd data = pd.read_csv('The_Travel.csv') data
(2)查看数据框的所有信息 data.info()
(3)根据条件把数据进行清洗 data = data[~data['地点'].isin(['攻略'])] data = data[~data['天数'].isin(['99+'])] data['天数'] = data['天数'].astype(int) data = data[data['人均费用'].values>200] data = data[data['天数']') 74 if len(info)>2: 75 location = info[1].replace('\xa0','').replace('旅游攻略','') 76 introduction = info[2].replace('\xa0','') 77 else: 78 location = info[0].replace('\xa0','') 79 introduction = info[1].replace('\xa0','') 80 other_information = soup.find('ul',attrs={'class': 'foreword_list'}) 81 when = other_information.find('li',attrs={'class': 'f_item when'}) 82 time1 = when.find('p',attrs={'class': 'txt'}).text.replace('出发日期','').strip() 83 howlong = other_information.find('li',attrs={'class': 'f_item howlong'}) 84 day = howlong.find('p', attrs={'class': 'txt'}).text.replace('天数','').replace('/','').replace('天','').strip() 85 howmuch = other_information.find('li',attrs={'class': 'f_item howmuch'}) 86 money = howmuch.find('p', attrs={'class': 'txt'}).text.replace('人均费用','').replace('/','').replace('元','').strip() 87 who = other_information.find('li',attrs={'class': 'f_item who'}) 88 people = who.find('p',attrs={'class': 'txt'}).text.replace('人物','').replace('/','').strip() 89 how = other_information.find('li',attrs={'class': 'f_item how'}) 90 play = how.find('p',attrs={'class': 'txt'}).text.replace('玩法','').replace('/','').strip() 91 Look = soup.find('span',attrs={'class': 'view_count'}).text.strip() 92 if time1: 93 Time = time1 94 else: 95 Time = '-' 96 if day: 97 Day = day 98 else: 99 Day = '-' 100 if money: 101 Money = money 102 else: 103 Money = '-' 104 if people: 105 People = people 106 else: 107 People = '-' 108 if play: 109 Play = play 110 else: 111 Play = '-' 112 last_list.append([location,introduction,Time,Day,Money,People,Play,Look]) 113 #设置爬虫时间 114 time.sleep(random.randint(3,5)) 115 count+=1 116 except Exception as e : 117 print(e) 118 #写入csv 119 with open('Travel.csv', 'a', encoding='utf-8-sig', newline='') as csvFile: 120 csv.writer(csvFile).writerow(['地点', '短评', '出发时间', '天数','人均费用','人物','玩法','浏览量']) 121 for rows in last_list: 122 csv.writer(csvFile).writerow(rows) 123 if __name__ == '__main__': 124 spider() 125 #读取爬取到的The_Travel.csv文件 126 import pandas as pd 127 data = pd.read_csv('The_Travel.csv') 128 data 129 #查看数据框的所有信息 130 data.info() 131 #根据条件把数据进行清洗 132 data = data[~data['地点'].isin(['攻略'])] 133 data = data[~data['天数'].isin(['99+'])] 134 data['天数'] = data['天数'].astype(int) 135 data = data[data['人均费用'].values>200] 136 data = data[data['天数'] |
【本文地址】
公司简介
联系我们