# 以下内容为原创，转载请注明出处
1 import xlrd # 读xlsx
import xlsxwriter # 写xlsx
import urllib.request # url请求，Python3自带，Python2与3中urllib的区别见：http://blog.****.net/Jurbo/article/details/52313636
import os # 创建output文件夹
import glob # 获取文件夹下文件名称
import time # 记录时间
import json # 读取json格式文件 # 本函数完成文件合并。单独保存是为了1.方便不同的用途；2.减少内存；3.在应用到其他网站时，可以断点续爬，降低中断风险
def xlsx_merge(folder,header,filename):
fileList = []
for fileName in glob.glob(folder + "*.xlsx"):
fileList.append(fileName)
fileNum = len(fileList)
matrix = [None] * fileNum
for i in range(fileNum):
fileName = fileList[i]
workBook = xlrd.open_workbook(fileName)
try:
sheet = workBook.sheet_by_index(0)
except Exception as e:
print(e)
nRows = sheet.nrows
matrix[i] = [0]*(nRows - 1)
nCols = sheet.ncols
for m in range(nRows - 1):
matrix[i][m] = [""]* nCols
for j in range(1,nRows):
for k in range(nCols):
matrix[i][j-1][k] = sheet.cell(j,k).value
fileName = xlsxwriter.Workbook(folder + filename + ".xlsx")
sheet = fileName.add_worksheet("merged")
for i in range(len(header)):
sheet.write(0,i,header[i])
rowIndex = 1
for fileIndex in range(fileNum):
for j in range(len(matrix[fileIndex])):
for colIndex in range (len(matrix[fileIndex][j])):
sheet.write(rowIndex,colIndex,matrix[fileIndex][j][colIndex])
rowIndex += 1
print("已完成%d个文件的合并"%fileNum)
fileName.close() # 本函数完成获取POI
def poi_by_adcode_poicode(folder,city_file = "city",poi_file = "poi",result_file = "result",merge_or_not = 1):
'''要求：文件为XLSX格式表格。
列表均在表格的第一页，且第一列为名称，第二列为编码。
因为是创建目录，folder要求不为根目录。
要求输入表在目录的input文件夹中，本函数将结果输出到目录下的output文件夹下
'''
city_file = city_file
poi_file = poi_file
result_file = result_file
merge_or_not = merge_or_not
header_full = ["id","name","type","typecode","biz_type","address","location","tel","pname","cityname","adname","rating","cost"]
header = ["id","name","type","typecode","biz_type","address","location","tel","pname","cityname","adname"]
offset = 25 # 实例设置每页展示10条POI（官方限定25条）
output_folder = folder + "output/"
# 创建输出路径
if os.path.isdir(output_folder):
pass
else:
os.makedirs(output_folder)
# 读取列表
city_sheet = xlrd.open_workbook(folder+ "input/" + city_file + ".xlsx").sheet_by_index(0)
poi_type_sheet = xlrd.open_workbook(folder+ "input/" + poi_file + ".xlsx").sheet_by_index(0)
city_list =city_sheet.col_values(0)
city_code_list = city_sheet.col_values(1)
poi_type_list = poi_type_sheet.col_values(1)
# 指示工作完成量
total_work = (city_sheet.nrows - 1) * (poi_type_sheet.nrows - 1)
work_index = 1
print(time.strftime('%Y-%m-%d %H:%M:%S',time.localtime(time.time())) + "：抓取开始！")
for city_index in range(1,len(city_list)):
for poi_type_index in range(1,len(poi_type_list)):
workbook =xlsxwriter.Workbook(output_folder + str(city_list[city_index]) + str(poi_type_list[poi_type_index]) + ".xlsx") # 新建工作簿
sheet = workbook.add_worksheet("result") # 新建“poiResult”的工作表
for col_index in range(len(header_full)):
sheet.write(0,col_index,header_full[col_index]) # 写表头
row_index = 1
for page_index in range(1, 101):
try:
url = "http://restapi.amap.com/v3/place/text?&keywords=&types=" + str(poi_type_list[poi_type_index]) + "&city=" + city_code_list[city_index] + "&citylimit=true&offset=" + str(offset) + "&page="+ str(page_index) + "&key=你的key&extensions=all"
# 请求的结构化url地址如上，见：http://lbs.amap.com/api/webservice/guide/api/search/
data = json.load(urllib.request.urlopen(url))["pois"]
for i in range(offset):
for col_index in range(len(header)):
sheet.write(row_index, col_index, str(data[i][header[col_index]]))
sheet.write(row_index,len(header),str(data[i]["biz_ext"]["rating"]))
sheet.write(row_index,len(header) + 1,str(data[i]["biz_ext"]["cost"]))
row_index += 1
except Exception: break
workbook.close()
print(time.strftime('%Y-%m-%d %H:%M:%S',time.localtime(time.time())) + "：" + city_list[city_index] + " " + poi_type_list[poi_type_index] + " 已获取!进度：%.2f%%" %(work_index / total_work *100))
work_index += 1
print(time.strftime('%Y-%m-%d %H:%M:%S',time.localtime(time.time())) + "：所有地区各类别POI获取完毕")
if merge_or_not == 1:
xlsx_merge(output_folder, header_full, result_file)
print(time.strftime('%Y-%m-%d %H:%M:%S',time.localtime(time.time())) + "：已对文件进行合并！")
else:
print(time.strftime('%Y-%m-%d %H:%M:%S',time.localtime(time.time())) + "：未进行合并！")
print(time.strftime('%Y-%m-%d %H:%M:%S',time.localtime(time.time())) + "：所有工作完成！") # 使用
poi_by_adcode_poicode("E:/test/","city", "poi", "result", 1)