def get_data(city, keyword, coord, key):
# 1. 获取城市边界的最大、最小经纬度
max_lng, min_lng, max_lat, min_lat = area_boundary.getlnglat(city, key)
print('当前城市：', city, "max_lng, min_lng, max_lat, min_lat：", max_lng,
min_lng, max_lat, min_lat)
# 2. 生成网格切片格式：
'''
[[112.23, 23.23, 112.24, 23.22], [112.23, 23.22, 112.24, 23.21]]
'''
'''
grids_lib = []
grids_lib = get_drids(min_lng, max_lat, max_lng, min_lat, '170200', '4188efb67360681f89110ccdb11e563b',
pology_split_distance, grids_lib)
'''
grids_lib = city_grid.generate_grids(min_lng, max_lat, max_lng, min_lat,
pology_split_distance)
print('划分后的网格数：', len(grids_lib))
print(grids_lib)
all_data = []
begin_time = time.time()
print(
'==========================正式开始爬取啦！！！！！！！！！！！================================'
)
for grid in grids_lib:
# grid格式：[112.23, 23.23, 112.24, 23.22]
one_pology_data = getpois(grid, keyword, key)
print('===================================当前矩形范围：', grid, '总共：',
str(len(one_pology_data)) + "条数据.............................")
all_data.extend(one_pology_data)
end_time = time.time()
print('全部：',
str(len(grids_lib)) + '个矩形范围', '总的', str(len(all_data)), '条数据, 耗时：',
str(end_time - begin_time), '正在写入EXCEL中')
return write_to_excel(all_data, city, keyword, coord)
def get_data(city, keyword, coord):
# 1. 获取城市边界的最大、最小经纬度
amap_key = buffer_keys[0] # 总是获取队列中的第一个密钥
max_lng, min_lng, max_lat, min_lat = area_boundary.getlnglat(
city, amap_key)
print('当前城市：', city, "max_lng, min_lng, max_lat, min_lat：", max_lng,
min_lng, max_lat, min_lat)
# 2. 生成网格切片格式：
grids_lib = city_grid.generate_grids(min_lng, max_lat, max_lng, min_lat,
pology_split_distance)
print('划分后的网格数：', len(grids_lib))
print(grids_lib)
all_data = []
begin_time = time.time()
print(
'==========================正式开始爬取啦！！！！！！！！！！！================================'
)
for grid in grids_lib:
# grid格式：[112.23, 23.23, 112.24, 23.22]
one_pology_data = getpois(grid, keyword)
print('===================================当前矩形范围：', grid, '总共：',
str(len(one_pology_data)) + "条数据.............................")
all_data.extend(one_pology_data)
end_time = time.time()
print('全部：',
str(len(grids_lib)) + '个矩形范围', '总的', str(len(all_data)), '条数据, 耗时：',
str(end_time - begin_time), '正在写入CSV文件中')
file_folder, file_name = write_to_csv(all_data, city, keyword, coord)
# 写入shp
if file_folder is not None:
trans_point_to_shp(file_folder, file_name, 0, 1, pology_split_distance,
keyword)
def get_drids(min_lng, max_lat, max_lng, min_lat, keyword, key,
pology_split_distance, all_grids):
grids_lib = city_grid.generate_grids(min_lng, max_lat, max_lng, min_lat,
pology_split_distance)
print('划分后的网格数：', len(grids_lib))
print(grids_lib)
# 3. 根据生成的网格爬取数据，验证网格大小是否合适，如果不合适的话，需要继续切分网格
for grid in grids_lib:
one_pology_data = getpoi_page(grid, keyword, 1, key)
data = json.loads(one_pology_data)
print(data)
while int(data['count']) > 890:
get_drids(grid[0], grid[1], grid[2], grid[3], keyword, key,
pology_split_distance / 2, all_grids)
all_grids.append(grid)
return all_grids