# 以下内容为原创，转载请注明出处
1 import xlrd # 读xlsx
2 import xlsxwriter # 写xlsx
3 import urllib.request # url请求，Python3自带，Python2与3中urllib的区别见：http://blog.csdn.net/Jurbo/article/details/52313636
4 import os # 创建output文件夹
5 import glob # 获取文件夹下文件名称
6 import time # 记录时间
7 import json # 读取json格式文件
8
9 # 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
10 def xlsx_merge(folder,header,filename):
11 fileList = []
12 for fileName in glob.glob(folder + "*.xlsx"):
13 fileList.append(fileName)
14 fileNum = len(fileList)
15 matrix = [None] * fileNum
16 for i in range(fileNum):
17 fileName = fileList[i]
18 workBook = xlrd.open_workbook(fileName)
19 try:
20 sheet = workBook.sheet_by_index(0)
21 except Exception as e:
22 print(e)
23 nRows = sheet.nrows
24 matrix[i] = [0]*(nRows - 1)
25 nCols = sheet.ncols
26 for m in range(nRows - 1):
27 matrix[i][m] = ["0"]* nCols
28 for j in range(1,nRows):
29 for k in range(nCols):
30 matrix[i][j-1][k] = sheet.cell(j,k).value
31 fileName = xlsxwriter.Workbook(folder + filename + ".xlsx")
32 sheet = fileName.add_worksheet("merged")
33 for i in range(len(header)):
34 sheet.write(0,i,header[i])
35 rowIndex = 1
36 for fileIndex in range(fileNum):
37 for j in range(len(matrix[fileIndex])):
38 for colIndex in range (len(matrix[fileIndex][j])):
39 sheet.write(rowIndex,colIndex,matrix[fileIndex][j][colIndex])
40 rowIndex += 1
41 print("已完成%d个文件的合并"%fileNum)
42 fileName.close()
43
44 # 本函数完成获取POI
45 def poi_by_adcode_poicode(folder,city_file = "city",poi_file = "poi",result_file = "result",merge_or_not = 1):
46 '''要求：文件为XLSX格式表格。
47 列表均在表格的第一页，且第一列为名称，第二列为编码。
48 因为是创建目录，folder要求不为根目录。
49 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
50 '''
51 city_file = city_file
52 poi_file = poi_file
53 result_file = result_file
54 merge_or_not = merge_or_not
55 header_full = ["id","name","type","typecode","biz_type","address","location","tel","pname","cityname","adname","rating","cost"]
56 header = ["id","name","type","typecode","biz_type","address","location","tel","pname","cityname","adname"]
57 offset = 25 # 实例设置每页展示10条POI（官方限定25条）
58 output_folder = folder + "output/"
59 # 创建输出路径
60 if os.path.isdir(output_folder):
61 pass
62 else:
63 os.makedirs(output_folder)
64 # 读取列表
65 city_sheet = xlrd.open_workbook(folder+ "input/" + city_file + ".xlsx").sheet_by_index(0)
66 poi_type_sheet = xlrd.open_workbook(folder+ "input/" + poi_file + ".xlsx").sheet_by_index(0)
67 city_list =city_sheet.col_values(0)
68 city_code_list = city_sheet.col_values(1)
69 poi_type_list = poi_type_sheet.col_values(1)
70 # 指示工作完成量
71 total_work = (city_sheet.nrows - 1) * (poi_type_sheet.nrows - 1)
72 work_index = 1
73 print(time.strftime('%Y-%m-%d %H:%M:%S',time.localtime(time.time())) + "：抓取开始！")
74 for city_index in range(1,len(city_list)):
75 for poi_type_index in range(1,len(poi_type_list)):
76 workbook =xlsxwriter.Workbook(output_folder + str(city_list[city_index]) + str(poi_type_list[poi_type_index]) + ".xlsx") # 新建工作簿
77 sheet = workbook.add_worksheet("result") # 新建“poiResult”的工作表
78 for col_index in range(len(header_full)):
79 sheet.write(0,col_index,header_full[col_index]) # 写表头
80 row_index = 1
81 for page_index in range(1, 101):
82 try:
83 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"
84 # 请求的结构化url地址如上，见：http://lbs.amap.com/api/webservice/guide/api/search/
85 data = json.load(urllib.request.urlopen(url))["pois"]
86 for i in range(offset):
87 for col_index in range(len(header)):
88 sheet.write(row_index, col_index, str(data[i][header[col_index]]))
89 sheet.write(row_index,len(header),str(data[i]["biz_ext"]["rating"]))
90 sheet.write(row_index,len(header) + 1,str(data[i]["biz_ext"]["cost"]))
91 row_index += 1
92 except Exception: 94 break
95 workbook.close()
96 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))
97 work_index += 1
98 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")
99 if merge_or_not == 1:
100 xlsx_merge(output_folder, header_full, result_file)
101 print(time.strftime('%Y-%m-%d %H:%M:%S',time.localtime(time.time())) + "：已对文件进行合并！")
102 else:
103 print(time.strftime('%Y-%m-%d %H:%M:%S',time.localtime(time.time())) + "：未进行合并！")
104 print(time.strftime('%Y-%m-%d %H:%M:%S',time.localtime(time.time())) + "：所有工作完成！")
105
106 # 使用
107 poi_by_adcode_poicode("E:/test/","city", "poi", "result", 1)
