Python爬取和分析旅游数据
Python爬取和分析旅游数据
01 数据爬取
最近几天朋友圈被大家的旅行足迹刷屏了，惊叹于那些把全国所有省基本走遍的朋友。与此同时，也萌生了写一篇旅行相关的内容，本次数据来源于一个对于爬虫十分友好的旅行攻略类网站：马蜂窝。
1. 获得城市编号
马蜂窝中的所有城市、景点以及其他的一些信息都有一个专属的5位数字编号，我们第一步要做的就是获取城市（直辖市+地级市）的编号，进行后续的进一步分析。
以上两个页面就是我们的城市编码来源，需要首先从目的地页面获得各省编码，之后进入各省城市列表获得编码。过程中需要Selenium进行动态数据爬取，部分代码如下：（可左右滑动查看、复制编辑）
[*]
def find_cat_url(url):
[*]
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:23.0) Gecko/20100101 Firefox/23.0'}
[*]
req=request.Request(url,headers=headers)
[*]
html=urlopen(req)
[*]
bsObj=BeautifulSoup(html.read(),"html.parser")
[*]
bs = bsObj.find('div',attrs={'class':'hot-list clearfix'}).find_all('dt')
[*]
[*]
cat_url = []
[*]
cat_name = []
[*]
for i in range(0,len(bs)):
[*]
for j in range(0,len(bs.find_all('a'))):
[*]
cat_url.append(bs.find_all('a').attrs['href'])
[*]
cat_name.append(bs.find_all('a').text)
[*]
cat_url = ['http://www.mafengwo.cn'+cat_url for i in range(0,len(cat_url))]
[*]
return cat_url
[*]
[*]
def find_city_url(url_list):
[*]
city_name_list = []
[*]
city_url_list = []
[*]
[*]
for i in range(0,len(url_list)):
[*]
driver = webdriver.Chrome()
[*]
driver.maximize_window()
[*]
url = url_list.replace('travel-scenic-spot/mafengwo','mdd/citylist')
[*]
driver.get(url)
[*]
[*]
while True:
[*]
try:
[*]
time.sleep(2)
[*]
bs = BeautifulSoup(driver.page_source,'html.parser')
[*]
url_set = bs.find_all('a',attrs={'data-type':'目的地'})
[*]
city_name_list = city_name_list +.text.replace('\n','').split()[0] for i in range(0,len(url_set))]
[*]
city_url_list = city_url_list+.attrs['data-id'] for i in range(0 ,len(url_set))]
[*]
js="var q=document.documentElement.scrollTop=800"
[*]
driver.execute_script(js)
[*]
time.sleep(2)
[*]
driver.find_element_by_class_name('pg-next').click()
[*]
except：
[*]
break
[*]
driver.close()
[*]
return city_name_list,city_url_list
[*]
[*]
url = 'http://www.mafengwo.cn/mdd/'
[*]
url_list = find_cat_url(url)
[*]
city_name_list,city_url_list=find_city_url(url_list)
[*]
city = pd.DataFrame({'city':city_name_list,'id':city_url_list})
2. 获得城市信息城市数据分别从以下几个页面获取：我们将每个城市获取数据的过程封装成函数，每次传入之前获得的城市编码，部分代码如下：
[*]
def get_city_info(city_name,city_code):
[*]
[*]
this_city_base = get_city_base(city_name,city_code)
[*]
[*]
this_city_jd = get_city_jd(city_name,city_code)
[*]
[*]
this_city_jd['city_name'] = city_name
[*]
[*]
this_city_jd['total_city_yj'] = this_city_base['total_city_yj']
[*]
[*]
try:
[*]
[*]
this_city_food = get_city_food(city_name,city_code)
[*]
[*]
this_city_food['city_name'] = city_name
[*]
[*]
this_city_food['total_city_yj'] = this_city_base['total_city_yj']
[*]
[*]
except:
[*]
[*]
this_city_food=pd.DataFrame()
[*]
[*]
return this_city_base,this_city_food,this_city_jd
[*]
[*]
def get_city_base(city_name,city_code):
[*]
[*]
url = 'http://www.mafengwo.cn/xc/'+str(city_code)+'/'
[*]
[*]
bsObj = get_static_url_content(url)
[*]
[*]
node = bsObj.find('div',{'class':'m-tags'}).find('div',{'class':'bd'}).find_all('a')
[*]
[*]
tag = .text.split()[0] for i in range(0,len(node))]
[*]
[*]
tag_node = bsObj.find('div',{'class':'m-tags'}).find('div',{'class':'bd'}).find_all('em')
[*]
[*]
tag_count = for k in tag_node]
[*]
[*]
par = 'href'][1:3] for k in node]
[*]
[*]
tag_all_count = sum() for i in range(0,len(tag_count))])
[*]
[*]
tag_jd_count = sum() for i in range(0,len(tag_count)) if par=='jd'])
[*]
[*]
tag_cy_count = sum() for i in range(0,len(tag_count)) if par=='cy'])
[*]
[*]
tag_gw_yl_count = sum() for i in range(0,len(tag_count)) if par in ['gw','yl']])
[*]
[*]
url = 'http://www.mafengwo.cn/yj/'+str(city_code)+'/2-0-1.html '
[*]
[*]
bsObj = get_static_url_content(url)
[*]
[*]
total_city_yj = int(bsObj.find('span',{'class':'count'}).find_all('span')[1].text)
[*]
[*]
return {'city_name':city_name,'tag_all_count':tag_all_count,'tag_jd_count':tag_jd_count,
[*]
[*]
'tag_cy_count':tag_cy_count,'tag_gw_yl_count':tag_gw_yl_count,
[*]
[*]
'total_city_yj':total_city_yj}
[*]
[*]
def get_city_food(city_name,city_code):
[*]
[*]
url = 'http://www.mafengwo.cn/cy/'+str(city_code)+'/gonglve.html'
[*]
[*]
bsObj = get_static_url_content(url)
[*]
[*]
food=for k in bsObj.find('ol',{'class':'list-rank'}).find_all('h3')]
[*]
[*]
food_count=for k in bsObj.find('ol',{'class':'list-rank'}).find_all('span',{'class':'trend'})]
[*]
[*]
return pd.DataFrame({'food':food[0:len(food_count)],'food_count':food_count})
[*]
[*]
def get_city_jd(city_name,city_code):
[*]
[*]
url = 'http://www.mafengwo.cn/jd/'+str(city_code)+'/gonglve.html'
[*]
[*]
bsObj = get_static_url_content(url)
[*]
[*]
node=bsObj.find('div',{'class':'row-top5'}).find_all('h3')
[*]
[*]
jd = '\n')[2] for k in node]
[*]
[*]
node=bsObj.find_all('span',{'class':'rev-total'})
[*]
[*]
jd_count=' 条点评','')) for k in node]
[*]
[*]
return pd.DataFrame({'jd':jd[0:len(jd_count)],'jd_count':jd_count})
02 数据分析：
1. 城市数据首先我们看一下游记数量最多的TOP10城市：
游记数量TOP10数量基本上与我们日常所了解的热门城市相符，我们进一步根据各个城市游记数量获得全国旅行目的地热力图：
看到这里，是不是有种似曾相识的感觉，如果你在朋友圈晒的足迹图与这幅图很相符，那么说明马蜂窝的数据与你不谋而合。最后我们看一下大家对于各个城市的印象是如何的，方法就是提取标签中的属性，我们将属性分为了休闲、饮食、景点三组，分别看一下每一组属性下大家印象最深的城市：
看来对于马蜂窝的用户来说，厦门给大家留下的印象是非常深的，不仅游记数量充足，并且能从中提取的有效标签也非常多。重庆、西安、成都也无悬念的给吃货们留下了非常深的印象，部分代码如下：
[*]
bar1 = Bar("餐饮类标签排名")
[*]
[*]
bar1.add("餐饮类标签分数", city_aggregate.sort_values('cy_point',0,False)['city_name'][0:15],
[*]
[*]
city_aggregate.sort_values('cy_point',0,False)['cy_point'][0:15],
[*]
[*]
is_splitline_show =False,xaxis_rotate=30)
[*]
[*]
bar2 = Bar("景点类标签排名",title_top="30%")
[*]
[*]
bar2.add("景点类标签分数", city_aggregate.sort_values('jd_point',0,False)['city_name'][0:15],
[*]
[*]
city_aggregate.sort_values('jd_point',0,False)['jd_point'][0:15],
[*]
[*]
legend_top="30%",is_splitline_show =False,xaxis_rotate=30)
[*]
[*]
bar3 = Bar("休闲类标签排名",title_top="67.5%")
[*]
[*]
bar3.add("休闲类标签分数", city_aggregate.sort_values('xx_point',0,False)['city_name'][0:15],
[*]
[*]
city_aggregate.sort_values('xx_point',0,False)['xx_point'][0:15],
[*]
[*]
legend_top="67.5%",is_splitline_show =False,xaxis_rotate=30)
[*]
[*]
grid = Grid(height=800)
[*]
[*]
grid.add(bar1, grid_bottom="75%")
[*]
[*]
grid.add(bar2, grid_bottom="37.5%",grid_top="37.5%")
[*]
[*]
grid.add(bar3, grid_top="75%")
[*]
[*]
grid.render('城市分类标签.html')
[*]
2. 景点数据
我们提取了各个景点评论数，并与城市游记数量进行对比，分别得到景点评论的绝对值和相对值，并据此计算景点的人气、代表性两个分数，最终排名TOP15的景点如下：
马蜂窝网友对于厦门真的是情有独钟，鼓浪屿也成为了最具人气的景点，在城市代表性方面西塘古镇和羊卓雍措位列前茅。小长假来临之际，如果担心上排的景点人太多，不妨从下排的景点中挖掘那些人少景美的旅游地。
3. 小吃数据
最后我们看一下大家最关注的的与吃相关的数据，处理方法与PART2景点数据相似，我们分别看一下最具人气和最具城市代表性的小吃：出乎意料，马蜂窝网友对厦门果真爱得深沉，让沙茶面得以超过火锅、烤鸭、肉夹馍跻身最具人气的小吃。在城市代表性方面，海鲜的出场频率非常高，这点与大（ben）家（ren）的认知也不谋而合，PART2与3的部分代码如下：
[*]
bar1 = Bar("景点人气排名")
[*]
[*]
bar1.add("景点人气分数", city_jd_com.sort_values('rq_point',0,False)['jd'][0:15],
[*]
[*]
city_jd_com.sort_values('rq_point',0,False)['rq_point'][0:15],
[*]
[*]
is_splitline_show =False,xaxis_rotate=30)
[*]
[*]
bar2 = Bar("景点代表性排名",title_top="55%")
[*]
[*]
bar2.add("景点代表性分数", city_jd_com.sort_values('db_point',0,False)['jd'][0:15],
[*]
[*]
city_jd_com.sort_values('db_point',0,False)['db_point'][0:15],
[*]
[*]
is_splitline_show =False,xaxis_rotate=30,legend_top="55%")
[*]
[*]
grid=Grid(height=800)
[*]
[*]
grid.add(bar1, grid_bottom="60%")
[*]
[*]
grid.add(bar2, grid_top="60%",grid_bottom="10%")
[*]
[*]
grid.render('景点排名.html')
厉害了，感觉很深奥 看不懂啊
页:
[1]