整体思路是从8684公交网上抓取城市的公交名列表,然后在高德中利用api交互来抓包获取站点的数据,有{ UID,线路,站点名,站点x坐标,站点y坐标 }。
这里爬8684用了requests和BeautifulSoup,比较简单就不阐述了。最后的存储同时存了csv和xlsx两种格式。
import requests from bs4 import BeautifulSoup import pandas as pd import xlrd #城市总列表 citys = ["hefei","wuhu","bengbu","huainan","maanshan","huaibei","tongling","anqing","huangshan","chuzhou","fuyang","suzhou2","liuan","bozhou","chizhou","xuancheng"] #获取首字母 def getInitial(cityName): url = \'https://{}.8684.cn/list1\'.format(cityName) headers = {\'User-Agent\':"自己的UA"} data = requests.get(url,headers=headers) soup = BeautifulSoup(data.text, \'lxml\') initial = soup.find_all(\'div\',{\'class\':\'tooltip-inner\'})[3] initial = initial.find_all(\'a\') ListInitial = [] for i in initial: ListInitial.append(i.get_text()) return ListInitial #ListInitial = [\'1\', \'2\', \'3\', \'4\', \'5\', \'6\', \'7\', \'8\', \'9\', #\'A\', \'B\', \'C\', \'D\', \'F\', \'G\', \'H\', \'K\', \'L\', \'M\', \'N\', \'P\', #\'Q\', \'S\', \'T\', \'W\', \'X\', \'Y\', \'Z\'] #根据ListInitial的各项爬取各项的首字母公交 def getLine(cityName,n): url = \'https://{}.8684.cn/list{}\'.format(cityName,n) headers = {\'User-Agent\':"自己的UA"} data = requests.get(url,headers=headers) soup = BeautifulSoup(data.text, \'lxml\') busline = soup.find(\'div\',{\'class\':\'list clearfix\'}) busline = busline.find_all(\'a\') for i in busline: lines.append(i.get_text()) #存储,传参lines,csv转xlsx def storageCsv(listBus,cityName): result = pd.DataFrame(listBus) result.to_csv("{}.csv".format(cityName),index=False,na_rep="NULL",) def csv_to_xlsx_pd(cityName): csv = pd.read_csv(\'{}.csv\'.format(cityName), encoding=\'utf-8\') csv.to_excel(\'{}.xlsx\'.format(cityName),header=False,index=False) #对citys列表中的每一个城市i for i in citys: #创建公交线路空列表 lines = [] #爬取首字母列表,返回首字母列表ListInitial ListInitial = getInitial(i) #根据首字母列表for循环爬取1-Z首字母线路,append入全局变量lines for n in ListInitial: getLine(i,n) #存储lines进入csv和xlsx storageCsv(lines,i) csv_to_xlsx_pd(i) print(i,"中了")
得到的csv如图: