python爬虫携程酒店_携程酒店爬取分享

该楼层疑似违规已被系统折叠 隐藏此楼查看此楼

import urllib.request

from bs4 import BeautifulSoup

import csv

import re

def openlink(link):

maxTryNum=20

for tries in range(maxTryNum):

try:

response = urllib.request.urlopen(link).read().decode('utf-8')

return response

except:

if tries < (maxTryNum-1):

continue

else:

print("Has tried %d times to access url %s, all failed!", maxTryNum, link)

return None

break

cityurl='http://hotels.ctrip.com/jiudian/neimenggu'

cityhtml = openlink(cityurl)

citysoup = BeautifulSoup(cityhtml, 'html.parser')

city_list = citysoup.find_all('ul', attrs={"class":"p_n_list grid_8"})

citysoup1 = BeautifulSoup(str(city_list), 'html.parser')

city_list1 = citysoup1.find_all('a', attrs={"href":True})

city_id=[]

for city in city_list1:

city_id1 = city['href']

city_id.append(city_id1)

print(city_id)

for cityid in city_id[13:14]:

cityname=re.findall(r"/([a-z]+?)[0-9]",cityid)

csvFile2 = open('Hotel'+str(cityname)+'.csv','w', newline='',encoding='utf-8-sig') # 设置newline，否则两行之间会空一行

writer = csv.writer(csvFile2)