建筑兔零基础自学记录49|python爬取百度地图POI实战-3

    本次利用python进行爬取，目前暂时只能实现全市信息的部分爬取，信息不全。有待继续补充其他方式建筑兔零基础自学记录45|获取高德/百度POI-1-CSDN博客但之前查到的工具POIKIT又对搜索分类有限制，不知道大家有没有什么更好的方式？
  本次是基于一个现有代码的改造，省略了获取不同区域的经纬度坐标的步骤，仅以地名来限制范围，不知是否会造成获取数据不全或者超出范围的问题。
   原始代码是还需导入一个不同区域的经纬度坐标这样的文件：

以下为尝试代码:

import urllib.request
import urllib.error
from urllib.parse import quote
import json
import time
import math

baseURL = 'https://api.map.baidu.com/place/v2/search?query=&output=json&'
ak = 'XXXXXXXXXXXXXXXXXXXXXXXX'#申请的码
query = quote('烧烤店')
scope = '2'
region = quote('北京')  # 对 region 进行 URL 编码
path = 'M:/python/workspace/PythonProject2_POI/json output/'
outputFile = path + 'BaiduPOI_1.txt'


def fetch(url):
    try:
        feedback = urllib.request.urlopen(url)
        data = feedback.read()
        response = json.loads(data)
        time.sleep(2)
        return response
    except (urllib.error.URLError, ValueError) as e:
        print(f"请求失败: {e}")
        return None


poiList = []

# 构建基于地区的初始请求URL
initialURL = f"{baseURL}ak={ak}&query={query}&scope={scope}&region={region}&page_size=20&page_num=0"
response = fetch(initialURL)
if not response or 'total' not in response:
    print("未获取到有效数据")
else:
    totalNum = response['total']
    numPages = math.ceil(totalNum / 20.0)  # 修正页码计算
    print(f"{numPages} pages in Total")

    for i in range(numPages):
        print(f"Fetching page {i}")
        URL = f"{baseURL}ak={ak}&query={query}&scope={scope}&region={region}&page_size=20&page_num={i}"
        page_response = fetch(URL)
        if not page_response or 'results' not in page_response:
            continue

        for content in page_response['results']:
            # 爬取店名，经纬度，uid，地址
            name = content.get('name', '')
            location = content.get('location', {})
            lat = location.get('lat', '')
            lng = location.get('lng', '')
            uid = content.get('uid', '')
            address = content.get('address', '')  # 提取地址信息
            poiInfo = f"{name};{lat};{lng};{uid};{address}"  # 更新 poiInfo 字符串
            poiList.append(poiInfo)

# 统一写入文件
try:
    with open(outputFile, 'w', encoding='utf-8') as f:
        for poiInfo in poiList:
            f.write(poiInfo + '\n')
except Exception as e:
    print(f"写入文件时出错: {e}")

注：在content部分可以根据自己的需求增添字段。其中的uid是 Unique Identifier（唯一标识符） 的缩写，用于唯一标识每个 POI（兴趣点）。每个 POI 在百度地图中都有唯一的uid，可避免重复记录或混淆相同名称的不同地点。在数据清洗或合并时，uid可作为主键用于去重或关联其他数据集。

获得的POI数据是这样的：

 全市只获得了84条数据，肯定不全。
原始代码如下：

import urllib.request
import urllib.error
from urllib.parse import quote
import json
import time
import math

baseURL = 'https://api.map.baidu.com/place/v2/search?query=&output=json&'
ak = 'XXXXXXXXXXXXXXXXXXXXXXXXXXXXX'
query = quote('车')
scope = '2'
region = quote('北京')  # 对 region 进行 URL 编码
path = 'M:/python/workspace/PythonProject2_POI/json output/'
outputFile = path + 'BaiduPOI_1.txt'


def fetch(url):
    try:
        feedback = urllib.request.urlopen(url)
        data = feedback.read()
        response = json.loads(data)
        time.sleep(2)
        return response
    except (urllib.error.URLError, ValueError) as e:
        print(f"请求失败: {e}")
        return None


# 读取坐标文件
poiList = []
try:
    with open(path + 'BaiduCoord.txt', 'r') as coordinateFile:
        coordinates = coordinateFile.readlines()
except FileNotFoundError:
    print(f"未找到文件: {path + 'BaiduCoord.txt'}")#这里的BaiduCoord.txt就是坐标范围
else:
    for c in range(0, 10):
        # for c in range(len(coordinates)):
        coord_parts = coordinates[c].split(',')
        if len(coord_parts) < 3:
            continue  # 跳过无效行
        current_lat = coord_parts[1].strip()
        current_lng = coord_parts[2].strip()
        locator = coord_parts[0]
        print(f"This is {locator} of {len(coordinates)}")

        initialURL = f"{baseURL}ak={ak}&query={query}&scope={scope}&location={current_lat},{current_lng}&radius=700&page_size=20&page_num=0"  # 半径取700，一页返回20个数据
        # print(initialURL)
        response = fetch(initialURL)
        if not response or 'total' not in response:
            continue

        totalNum = response['total']
        numPages = math.ceil(totalNum / 20.0)  # 修正页码计算
        print(f"{numPages} pages in Total")

        for i in range(numPages):
            print(f"Fetching page {i}")
            URL = f"{baseURL}ak={ak}&query={query}&scope={scope}&location={current_lat},{current_lng}&radius=70&page_size=20&page_num={i}"
            page_response = fetch(URL)
            if not page_response or 'results' not in page_response:
                continue

            for content in page_response['results']:
                # 爬取店名，经纬度，uid，地址
                name = content.get('name', '')
                location = content.get('location', {})
                lat = location.get('lat', '')
                lng = location.get('lng', '')
                uid = content.get('uid', '')
                address = content.get('address', '')  # 提取地址信息
                poiInfo = f"{name};{lat};{lng};{uid};{address}"  # 更新 poiInfo 字符串
                poiList.append(poiInfo)

# 统一写入文件
try:
    with open(outputFile, 'w', encoding='utf-8') as f:
        for poiInfo in poiList:
            f.write(poiInfo + '\n')
except Exception as e:
    print(f"写入文件时出错: {e}")

哎头秃如何获取完整数据呢o(╥﹏╥)o