├── .gitignore ├── README.md ├── POI_Spider.py └── LICENSE /.gitignore: -------------------------------------------------------------------------------- 1 | *.DS_Store 2 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # Python-POI-Spider 2 | Python兴趣点（POI）爬虫，通过百度地图API爬取指定城市兴趣点列表，包含其：坐标、名称、联系方式 3 | 4 | 5 | 6 | ## 特色 7 | 8 | - 可指定城市 9 | - 可查询轮流多个兴趣点 10 | - 可获得详细JSON信息，包含经纬度、名称、联系号码等内容 11 | - 自动翻页查询（百度接口每次最多只返回20条数据） 12 | - 自动整理合并 13 | - 自动生成POI结果目录 14 | - 自动针对POI生成JSON文件 15 | - 自动异常处理（并行达到上限重新查询） 16 | 17 | ## 使用步骤 18 | 19 | 1. 进入[百度地图开放平台](http://lbsyun.baidu.com/)，注册进入控制台，创建应用，基础服务选择地点检索 20 | 2. 完成创建后，可以在应用管理查看是否有应用Key（AK） 21 | 3. 打开**POI_Spider.py**并进入编辑 22 | 4. 更改**ak**，估计在第39行上下，更改为你的应用的ak 23 | 5. 运行程序 24 | 6. 输入想要查询的城市 25 | 7. 输入不在打印出来的列表里的兴趣 26 | 8. 程序自动运行 27 | 9. 项目目录查看结果 28 | 29 | ## 运行结果 30 | 31 | 运行后，会针对指定城市各个兴趣点进行爬取及整理，保存到JSON文件里 32 | 33 | 运行时可能会出现错误，显示到达日限额，这就是需要给百度充钱了~ 34 | 35 | 下面就是会输出的内容（指定的城市是北京，兴趣点是地产） 36 | 37 | ```json 38 | [ 39 | { 40 | "address": "北京市大兴区黄村西大街99号", 41 | "area": "大兴区", 42 | "city": "北京市", 43 | "detail": 1, 44 | "location": { 45 | "lat": 39.737639, 46 | "lng": 116.333112 47 | }, 48 | "name": "龙熙房地产", 49 | "province": "北京市", 50 | "street_id": "49d959383f8ac442c61e5172", 51 | "telephone": "(010)69258681", 52 | "uid": "49d959383f8ac442c61e5172" 53 | }, 54 | { 55 | "address": "北京市海淀区安宁庄前街与清上园东路交叉路口西南侧(清上园)", 56 | "area": "海淀区", 57 | "city": "北京市", 58 | "detail": 1, 59 | "location": { 60 | "lat": 40.045964, 61 | "lng": 116.337601 62 | }, 63 | "name": "麦田房产", 64 | "province": "北京市", 65 | "street_id": "7b17dcbee42d831776e5b6b4", 66 | "uid": "7b17dcbee42d831776e5b6b4" 67 | } 68 | ] 69 | ``` 70 | 71 | 72 | 73 | ## 环境配置 74 | 75 | - 系统 76 | 77 | MacOS/Windows/Linux 都支持 78 | - 环境 79 | 80 | Python3.x都支持 81 | - 网络 82 | 83 | 能进百度就行 84 | -------------------------------------------------------------------------------- /POI_Spider.py: -------------------------------------------------------------------------------- 1 | import urllib.request 2 | import json 3 | import os 4 | 5 | 6 | def mkdir(path): 7 | # 去除首位空格 8 | path=path.strip() 9 | # 去除尾部 \ 符号 10 | path=path.rstrip("\\") 11 | # 判断路径是否存在 12 | isExists=os.path.exists(path) 13 | # 判断结果 14 | if not isExists: 15 | # 如果不存在则创建目录,创建目录操作函数 16 | #此处路径最好使用utf-8解码，否则在磁盘中可能会出现乱码的情况 17 | os.makedirs(path) 18 | else: 19 | return False 20 | 21 | 22 | if __name__ == '__main__': 23 | # 开始信息 24 | print("========================================") 25 | print("欢迎使用通过百度地图分析某城市POI（兴趣点）") 26 | print("使用本程序，可自动爬取指定城市指定类型类别的建筑/坐标/电话等信息") 27 | print("========================================") 28 | 29 | # 地址和类别 30 | city = input("请输入想要分析的城市：") 31 | all_poi_type = ["美食", "酒店", "购物", "生活服务", "丽人", "旅游景点", "休闲娱乐", "运动健身", "教育培训", "文化传媒", "医疗", "汽车服务", "交通设施", "金融", 32 | "房地产", "公司企业", "政府机构"] 33 | print("目前POI类型已包含：{}".format(all_poi_type)) 34 | other_type = input("添加其他POI类型（留空结束）：") 35 | while (other_type): 36 | all_poi_type.append(other_type) 37 | other_type = input("添加其他POI类型（留空结束）：") 38 | 39 | ak = ""#百度API应用Key 40 | # 百度API接口 41 | url = "http://api.map.baidu.com/place/v2/search?page_size=20&query={}®ion={}&output=json&page_num={}&ak={}" 42 | 43 | # 爬虫header 44 | headers = { 45 | 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36'} 46 | 47 | allResults = [] 48 | 49 | #创建结果路径 50 | mkdir("{}的POI分析".format(city)) 51 | 52 | # 循环获取 53 | for poi_type in all_poi_type: 54 | print("====================") 55 | print("正在查询{}的{}".format(city, poi_type)) 56 | # 爬虫访问 57 | page_num = 0 # 第几页（百度API一页给20个数据） 58 | total_num = 20 # 最多多少数据（20数据一页） 59 | poi_result = [] # 全部结果 60 | while (total_num == 20): # 只有当前页有20条数据，才会查下一页 61 | # 爬虫获得数据 62 | req = urllib.request.Request( 63 | url=url.format(urllib.parse.quote(poi_type), urllib.parse.quote(city), str(page_num), ak), 64 | headers=headers) 65 | res = urllib.request.urlopen(req) 66 | json_result = res.read().decode('utf-8') 67 | # 转json 68 | result = json.loads(json_result) 69 | # 如果包含结果 70 | if ("results" in result): 71 | # 获取总数 72 | total_num = len(result["results"]) 73 | # 插入当前POI数据列表 74 | for res in result["results"]: 75 | poi_result.append(res) 76 | # 打印总数 77 | print("第{}页有{}个结果".format(str(page_num + 1), str(total_num))) 78 | else: # 如果不包含结果 79 | if (result["status"] == 401): # 如果是401错误码，代表爬太快了 80 | # 重新查询 81 | total_num = 20 82 | page_num -= 1 83 | elif (result["status"] == 302): # 如果是302错误码，代表API到限额了 84 | print("百度API到达本日限额，无法继续查询") 85 | total_num = 0 86 | else: 87 | # 其他错误就代表查完了 88 | total_num = 0 89 | # 换一页查 90 | page_num += 1 91 | print("{}的{}共有{}个结果".format(city, poi_type, str(len(poi_result)))) # 显示结果总数 92 | json_to_save = json.dumps(poi_result, sort_keys=True, indent=2, ensure_ascii=False).encode('utf-8') # 需要存的数据 93 | try: 94 | with open("{}的POI分析/{}的{}POI数据.txt".format(city, city, poi_type), "wb+") as fo: # 读取文件 95 | fo.write(json_to_save) # 存本地 96 | print("保存文件成功 ==========> {}的POI分析/{}的{}POI数据.txt".format(city, city, poi_type)) 97 | except: 98 | print("保存文件失败") 99 | 100 | print("====================") 101 | print("查询完毕！") -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "[]" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright [yyyy] [name of copyright owner] 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | --------------------------------------------------------------------------------