Python爬虫_城市公交、地铁站点和线路数据采集实例

def main():
 df = pd.read_excel("线路名称.xlsx",)
 BaseUrl = "https://ditu.amap.com/service/poiInfo?query_type=TQUERY&pagesize=20&pagenum=1&qii=true&cluster_state=5&need_utd=true&utd_sceneid=1000&div=PC1000&addr_poi_merge=true&is_classify=true&"
 for bus in df[u"线路"]:
 params = {
  'keywords':'11路',
  'zoom': '11',
  'city':'610100',
  'geoobj':'107.623|33.696|109.817|34.745'
 }
 print(bus)
 paramMerge = urllib.parse.urlencode(params) 
 #print(paramMerge)
 targetUrl = BaseUrl + paramMerge
 stationFile = "./busStation/" + bus + ".csv"
 lineFile = "./busLine/" + bus + ".csv"
 
 req = urllib.request.Request(targetUrl)
 res = urllib.request.urlopen(req)
 content = res.read()
 jsonData = json.loads(content)
 if (jsonData["data"]["message"]) and jsonData["data"]["busline_list"]:
  busList = jsonData["data"]["busline_list"] ##busline 列表
  busListSlt = busList[0] ## busList共包含两条线，方向不同的同一趟公交,任选一趟爬取
  
  busStations = extratStations(busListSlt)
  busLine = extractLine(busListSlt)
  writeStation(busStations, stationFile)
  writeLine(busLine, lineFile)
  
  sleep(random.random() * random.randint(0,7) + random.randint(0,5)) #设置随机休眠
 else:
  continue

def extratStations(busListSlt):
 busName = busListSlt["name"]
 stationSet = []
 stations = busListSlt["stations"]
 for bs in stations:
 tmp = []
 tmp.append(bs["station_id"])
 tmp.append(busName)
 tmp.append(bs["name"])
 cor = bs["xy_coords"].split(";")
 tmp.append(cor[0])
 tmp.append(cor[1])
 wgs84cor1 = gcj02towgs84(float(cor[0]),float(cor[1]))
 tmp.append(wgs84cor1[0])
 tmp.append(wgs84cor1[1])
 stationSet.append(tmp)
 return stationSet

def extractLine(busListSlt):
 ## busList共包含两条线，备注名称
 keyName = busListSlt["key_name"]
 busName = busListSlt["name"] 
 fromName = busListSlt["front_name"]
 toName = busListSlt["terminal_name"]
 lineSet = []
 Xstr = busListSlt["xs"]
 Ystr = busListSlt["ys"]
 Xset = Xstr.split(",")
 Yset = Ystr.split(",")
 length = len(Xset)
 for i in range(length):
 tmp = []
 tmp.append(keyName)
 tmp.append(busName)
 tmp.append(fromName)
 tmp.append(toName)
 tmp.append(Xset[i])
 tmp.append(Yset[i])
 wgs84cor2 = gcj02towgs84(float(Xset[i]),float(Yset[i]))
 tmp.append(wgs84cor2[0])
 tmp.append(wgs84cor2[1])
 lineSet.append(tmp)
 return lineSet