├── .gitignore
├── .idea
├── UGC_analysis.iml
├── deployment.xml
├── encodings.xml
├── misc.xml
├── modules.xml
└── vcs.xml
├── LICENSE
├── README.md
├── RealTime_UGC_Analysis_GUI.py
├── data_source
├── data_source_description.txt
└── demo_resource.txt
├── pic
├── 1.jpeg
├── 7.jpeg
├── GUI_main.png
├── best_comment_analysis.png
├── data_collector.png
├── environment_analysis.png
├── label.png
├── meituan.png
├── rebook.png
├── sentiment_analysis.png
├── time_line.png
└── total_score.png
├── resource.txt
└── txt_analysis
├── picturing.py
├── spider_xiecheng.py
└── spider_zhenguo.py
/.gitignore:
--------------------------------------------------------------------------------
1 | # Byte-compiled / optimized / DLL files
2 | __pycache__/
3 | *.py[cod]
4 | *$py.class
5 |
6 | # C extensions
7 | *.so
8 |
9 | # Distribution / packaging
10 | .Python
11 | build/
12 | develop-eggs/
13 | dist/
14 | downloads/
15 | eggs/
16 | .eggs/
17 | lib/
18 | lib64/
19 | parts/
20 | sdist/
21 | var/
22 | wheels/
23 | pip-wheel-metadata/
24 | share/python-wheels/
25 | *.egg-info/
26 | .installed.cfg
27 | *.egg
28 | MANIFEST
29 |
30 | # PyInstaller
31 | # Usually these files are written by a python script from a template
32 | # before PyInstaller builds the exe, so as to inject date/other infos into it.
33 | *.manifest
34 | *.spec
35 |
36 | # Installer logs
37 | pip-log.txt
38 | pip-delete-this-directory.txt
39 |
40 | # Unit test / coverage reports
41 | htmlcov/
42 | .tox/
43 | .nox/
44 | .coverage
45 | .coverage.*
46 | .cache
47 | nosetests.xml
48 | coverage.xml
49 | *.cover
50 | *.py,cover
51 | .hypothesis/
52 | .pytest_cache/
53 |
54 | # Translations
55 | *.mo
56 | *.pot
57 |
58 | # Django stuff:
59 | *.log
60 | local_settings.py
61 | db.sqlite3
62 | db.sqlite3-journal
63 |
64 | # Flask stuff:
65 | instance/
66 | .webassets-cache
67 |
68 | # Scrapy stuff:
69 | .scrapy
70 |
71 | # Sphinx documentation
72 | docs/_build/
73 |
74 | # PyBuilder
75 | target/
76 |
77 | # Jupyter Notebook
78 | .ipynb_checkpoints
79 |
80 | # IPython
81 | profile_default/
82 | ipython_config.py
83 |
84 | # pyenv
85 | .python-version
86 |
87 | # pipenv
88 | # According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
89 | # However, in case of collaboration, if having platform-specific dependencies or dependencies
90 | # having no cross-platform support, pipenv may install dependencies that don't work, or not
91 | # install all needed dependencies.
92 | #Pipfile.lock
93 |
94 | # PEP 582; used by e.g. github.com/David-OConnor/pyflow
95 | __pypackages__/
96 |
97 | # Celery stuff
98 | celerybeat-schedule
99 | celerybeat.pid
100 |
101 | # SageMath parsed files
102 | *.sage.py
103 |
104 | # Environments
105 | .env
106 | .venv
107 | env/
108 | venv/
109 | ENV/
110 | env.bak/
111 | venv.bak/
112 |
113 | # Spyder project settings
114 | .spyderproject
115 | .spyproject
116 |
117 | # Rope project settings
118 | .ropeproject
119 |
120 | # mkdocs documentation
121 | /site
122 |
123 | # mypy
124 | .mypy_cache/
125 | .dmypy.json
126 | dmypy.json
127 |
128 | # Pyre type checker
129 | .pyre/
130 |
--------------------------------------------------------------------------------
/.idea/UGC_analysis.iml:
--------------------------------------------------------------------------------
1 |
2 |
3 |
4 |
8 |
9 |
12 |
--------------------------------------------------------------------------------
/.idea/deployment.xml:
--------------------------------------------------------------------------------
1 |
2 |
3 |
4 |
5 |
6 |
7 |
8 |
10 |
11 |
12 |
13 |
14 |
15 |
17 |
18 |
19 |
20 |
21 |
22 |
24 |
25 |
26 |
27 |
28 |
29 |
31 |
32 |
33 |
34 |
35 |
--------------------------------------------------------------------------------
/.idea/encodings.xml:
--------------------------------------------------------------------------------
1 |
2 |
3 |
4 |
6 |
--------------------------------------------------------------------------------
/.idea/misc.xml:
--------------------------------------------------------------------------------
1 |
2 |
3 |
4 |
6 |
--------------------------------------------------------------------------------
/.idea/modules.xml:
--------------------------------------------------------------------------------
1 |
2 |
3 |
4 |
5 |
7 |
8 |
--------------------------------------------------------------------------------
/.idea/vcs.xml:
--------------------------------------------------------------------------------
1 |
2 |
3 |
4 |
7 |
--------------------------------------------------------------------------------
/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 |
--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
1 |
2 | [](https://996.icu)
3 |
4 |
5 | ### Real_Time_DataMining_Sortware
6 |
7 |
8 | [](https://starchart.cc/CarryChang/Real_Time_DataMining_Software)
9 |
10 |
11 | #### [视频演示demo](https://github.com/CarryChang/C-CNN-for-Chinese-Sentiment-Analysis/blob/master/video/demo.mp4)
12 |
13 | #### 一款能实时进行文本挖掘的软件，不占用多余的存储空间，直接将采集后的数据集中存储在本地txt中，运用本软件无需进行大量的手动翻页操作，输入对应的店铺链接即可对民宿进行分析包含接结构化数据的可视化和非结构化UGC的情感分析，包含数据的实时采集/数据清洗/结构化保存/UGC数据主题提取/情感分析/后结构化可视化等技术的综合性演示demo。基于在线民宿UGC数据的意见挖掘项目，包含数据挖掘和NLP相关的处理，负责数据采集、整句切分、主题抽取、情感分析等任务。主要克服用户打分和评论不一致，实时对携程和美团在线民宿的满意度进行评测以及对额外数据进行可视化的综合性工具，多维度的对在线UGC进行数据挖掘并可视化，对比顾客直接打分的结果来看，运用机器学习的情感分析方法更能挖掘到详细的顾客意见和对应的合理评分。
14 |
15 | ##### 软件包含数据采集（txt_analysis/spiders）/清理/可视化（txt_analysis/picturing）部分组成，直接运行Python3 RealTime_UGC_Analysis_GUI.py 即可打开本软件的GUI界面，缺失的库按照提示进行安装即可。
16 |
17 | 1:
118 | if len(key[0])>2 and key[1]>0:
119 | label.append(key[0])
120 | label_number.append(key[1])
121 | plt.pie(label_number,labels=label,
122 | autopct="%1.2f%%", shadow=True, startangle=0)
123 | plt.title("民宿标签分析", loc="left", fontsize=20)
124 | plt.axis("equal")
125 | plt.show()
126 | plt.close()
127 | except:
128 | # 进行统计操作
129 | dict1 = {}
130 | for key in result['commentTextList']:
131 | for key1 in key:
132 | if key1 in dict1.keys():
133 | dict1[key1].append(1)
134 | else:
135 | dict1[key1] = []
136 | dict1[key1].append(1)
137 | label = []
138 | label_number = []
139 | for key2 in dict1.keys():
140 | if len(key2) > 2 and len(dict1[key2]) > 0:
141 | label.append(key2)
142 | label_number.append(len(dict1[key2]))
143 | plt.pie(label_number, labels=label,
144 | autopct="%1.2f%%", shadow=True, startangle=0)
145 | plt.title("民宿标签分析", loc="left", fontsize=20)
146 | plt.axis("equal")
147 | plt.show()
148 | plt.close()
149 | def cost_time(result):
150 | if result is not None:
151 | title = "民宿复住分析"
152 | # 统计二次以上的，没有为零，使用饼图
153 | dict1 = {}
154 | for key1 in result["guestId"]:
155 | if key1 in dict1.keys():
156 | dict1[key1].append(dict(url_str=key1))
157 | else:
158 | dict1[key1] = []
159 | dict1[key1].append(dict(url_str=key1))
160 | y = 0
161 | n = 0
162 | for key2 in dict1.keys():
163 | # 统计回头客的占比
164 | if len(dict1[key2]) > 1:
165 | n += 1
166 | else:
167 | y += 1
168 | labels = ['首次', '非首次']
169 | label_number = [y, n]
170 | plt.pie(label_number, labels=labels,
171 | autopct="%1.2f%%", shadow=True, startangle=0)
172 | plt.title(title, loc="left", fontsize=20)
173 | plt.axis("equal")
174 | plt.show()
175 | plt.close()
176 | def _test():
177 | from matplotlib import pyplot as plt
178 | plt.rcParams['font.sans-serif'] = ['SimHei'] # 解决中文乱码
179 | import json
180 | result = json.loads(open('resource.txt','r',encoding='utf-8').read())
181 | # 顾客意见完成
182 | # score_detail(result)
183 | # 顾客打分完成
184 | # average_score(result)
185 | # # 入住时间序列分析完成
186 | s_from(result)
187 | # # 顾客标签
188 | # recommend_dishes2(result)
189 | # #民宿复住分析完成
190 | # cost_time(result)
191 | if __name__ == "__main__":
192 | # 打分分析，回头客统计，guestId,入住时间统计，gmtCreate,意见统计
193 | pass
194 | _test()
--------------------------------------------------------------------------------
/txt_analysis/spider_xiecheng.py:
--------------------------------------------------------------------------------
1 | import re
2 | import json
3 | import requests
4 | #首先先在输入的地址中提取店铺ID，然后将店铺ID和找到的接口进行匹配得到一个地址链接
5 | ##然后将得到的地址链接导入到网络爬虫中去得到json1文件
6 | #最后解析jason文件得到内容
7 | class Crawler:
8 | def __init__(self):
9 | #1625734074
10 | self.shop_id = None
11 | self.page_index = 0
12 | self.page_num = 1
13 | self.info = {}
14 | def crawl(self, url=None, shop_id=None):
15 | self._get_shop_id(url, shop_id)
16 | i = 0
17 | base_url = 'https://m.ctrip.com/restapi/soa2/12455/json/BnbCommentList'
18 | while i < self.page_num:
19 | data = json.dumps(
20 | {"pid": '{}'.format(self.shop_id), "searchType": 2, "tagId": 0,
21 | "pageindex": '{}'.format(i), "pageSize": 40,
22 | "order": 0,
23 | "head": {"cid": "", "ctok": "", "cver": "1.0", "lang": "01", "sid": "8888", "syscode": "09",
24 | "auth": "",
25 | "xsid": "", "extension": [{"name": "webp", "value": "1"}, {"name": "cityid", "value": ""},
26 | {"name": "platform", "value": "pc"},
27 | {"name": "source", "value": "2"},
28 | {"name": "pagecode", "value": "10650016818"},
29 | {"name": "module", "value": "11"}]}})
30 | self._get_json_request(base_url,data)
31 | i += 1
32 | self.page_num = 1
33 | return self.info
34 | def _get_shop_id(self, url, id):
35 | if url is not None and 'onlineinn' in url:
36 | # 链接整理
37 | shop_id = re.findall('pid=(.*?)&',url)[0]
38 | # print(shop_id)
39 | if shop_id is None:
40 | raise ValueError("Bad url")
41 | self.shop_id = shop_id
42 | elif id is not None:
43 | self.shop_id = id
44 | else:
45 | raise ValueError("Bad url")
46 | def _get_json_request(self, url,data):
47 | try:
48 | headers = {
49 | 'content-type': 'application/json',
50 | 'cookieOrigin': 'https://inn.ctrip.com',
51 | 'Origin': 'https://inn.ctrip.com',
52 | 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.157 Safari/537.36',
53 | }
54 | result = requests.post(url, headers=headers,data=data).json()
55 | except requests.ConnectionError:
56 | raise ValueError("requests.ConnectionError")
57 | if self.page_num == 1:
58 | self._get_initial_info(result)
59 | self._get_a_json_info(result)
60 | def _get_initial_info(self, result):
61 | # 提取输入翻页地址
62 | self.page_num = result["count"] // 40 + 1
63 | # print(self.page_num)
64 | # average_score = {}
65 | # average_score["average_dish_score"] = float(result["average_dish_score"])
66 | # average_score["average_service_score"] = float(result["average_service_score"])
67 | # average_score["average_score"] = float(result["average_score"])
68 | # self.info["average_score"] = average_score
69 | # # get the score detail
70 | # self.info["score_detail"] = result["score_detail"]
71 | # # get the weeks score
72 | # weeks_score = {}
73 | # for key, value in result["weeks_score"].items():
74 | # weeks_score[key] = float(value)
75 | # self.info["weeks_score"] = weeks_score
76 | # # get the recommend dished
77 | # self.info["recommend_dishes"] = result["recommend_dishes"]
78 | # # get the comment num
79 | # self.info["comment_num"] = result['comment_num']
80 | # # initialize the self.info variable
81 | self.info["content"] = []
82 | self.info["content"] = []
83 | self.info["score"] = []
84 | self.info["commentTextList"] = []
85 | self.info["checkInType"] = []
86 | self.info["guestId"] = []
87 | self.info["gmtCreate"] = []
88 | self.info["levelName"] = []
89 | for a_json1 in result["bnbCommentTags"]:
90 | try:
91 | q1 = a_json1["tagName"]
92 | q2 = a_json1["popularity"]
93 | self.info["commentTextList"].append([q1,q2])
94 | except:
95 | self.info["commentTextList"].append([])
96 | def _get_a_json_info(self,result):
97 | for a_json in result["clist"]:
98 | try:
99 | self.info["score"].append(int(a_json["rate"]))
100 | except:
101 | self.info["score"].append([])
102 | try:
103 | self.info["content"].append(a_json["content"])
104 | except:
105 | self.info["content"].append([])
106 | try:
107 | self.info["guestId"].append(a_json["uinfo"]['userId'])
108 | except:
109 | self.info["guestId"].append([])
110 | try:
111 | self.info["levelName"].append(a_json["uinfo"]['levelName'])
112 | except:
113 | self.info["levelName"].append([])
114 | try:
115 | self.info["gmtCreate"].append(a_json["ctime"])
116 | except:
117 | self.info["gmtCreate"].append([])
118 | try:
119 | # print(tralvel_type[a_json["checkInType"]])
120 | # 需要做字典映射：,出游类型：家庭出游，朋友出游，情侣出游，代人预订，商务出差
121 | # self.info["checkInType"].append(tralvel_type[a_json["checkInType"]])
122 | self.info["checkInType"].append(a_json["checkInType"])
123 | except:
124 | self.info["checkInType"].append([])
125 | _crawler = Crawler()
126 | crawl = _crawler.crawl
127 | if __name__ == "__main__":
128 | shop_id = 'https://inn.ctrip.com/onlineinn/detail?pid=929393353&channelid=211'
129 | # print(shop_id)
130 | crawler = Crawler()
131 | a = crawler.crawl(shop_id)
--------------------------------------------------------------------------------
/txt_analysis/spider_zhenguo.py:
--------------------------------------------------------------------------------
1 | import re
2 | import json
3 | import requests
4 | # from fake_useragent import UserAgent
5 | class Crawler:
6 | def __init__(self):
7 | self.base_url = 'https://minsu.meituan.com/gw/ugc/api/v1/product/comments?productId=%s&pageNow=%s&pageSize=1000'
8 | self.shop_id = None
9 | self.page_num = 1
10 | self.info = {}
11 | def crawl(self, url=None, shop_id=None):
12 | self._get_shop_id(url, shop_id)
13 | self._get_json_request(self.base_url % (self.shop_id, 1))
14 | # self.page_num = 1
15 | # self._filter()
16 | return self.info
17 | @staticmethod
18 | def _is_too_short(sentence):
19 | #########过滤文本字数
20 | if len(sentence) < 2:
21 | return True
22 | if len(re.findall(r'[\u4e00-\u9fa5]', sentence)) <= len(sentence) * 0.4:
23 | return True
24 | return False
25 | @staticmethod
26 | def _is_numeric(sentence):
27 | match = re.findall("\d+", sentence)
28 | if match is not None and sum([len(m) for m in match]) >= len(sentence) * 0.75:
29 | return True
30 | return False
31 | @staticmethod
32 | def _is_english(sentence):
33 | match = re.findall("[a-zA-Z]+", sentence)
34 | if match is not None and sum([len(m) for m in match]) >= len(sentence) * 0.75:
35 | return True
36 | return False
37 | @staticmethod
38 | def _is_word_repeat(sentence):
39 | repeat_words, length = [], 0
40 | for word in sentence:
41 | times = sentence.count(word)
42 | if times >= 4 and word not in repeat_words:
43 | repeat_words.append(word)
44 | length += times
45 | if length > len(sentence) / 2:
46 | return True
47 | return False
48 | def _get_shop_id(self, url, id):
49 | if url is not None:
50 | # 匹配出数字即可
51 | if 'rank' in url:
52 | shop_id = re.findall('/housing/(.*)/', url)[0]
53 | self.shop_id = shop_id
54 | else:
55 | shop_id = re.search("\d+", url)
56 | if shop_id is None:
57 | raise ValueError("Bad url")
58 | self.shop_id = shop_id.group()
59 | elif id is not None:
60 | self.shop_id = id
61 | else:
62 | raise ValueError("Bad url")
63 | def _get_json_request(self, url):
64 | try:
65 | # print(url)
66 | headers = {
67 | 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3',
68 | 'Accept-Encoding': 'gzip, deflate, br',
69 | 'Accept-Language': 'zh-CN,zh;q=0.9',
70 | 'Cache-Control': 'max-age=0',
71 | 'Connection': 'keep-alive',
72 | 'Cookie': 'zgwww=93b60120-342e-11ea-8352-7929dfe9c6a2; uuid=D51492DA6AAA270A8B7FE7A35B3B94DD39666FAF2EAABB2A10B5B4413F03334A; iuuid=D51492DA6AAA270A8B7FE7A35B3B94DD39666FAF2EAABB2A10B5B4413F03334A; _lxsdk_cuid=16f92f4f879c8-040cf5ba938711-353166-1fa400-16f92f4f879c8; _lxsdk=D51492DA6AAA270A8B7FE7A35B3B94DD39666FAF2EAABB2A10B5B4413F03334A; __mta=147626248.1578718526069.1578718542593.1578718605961.3; XSRF-TOKEN=eldkyp20-QuUkBlhveN5L5ovat5brDFCGXe0',
73 | 'Host': 'minsu.meituan.com',
74 | 'Upgrade-Insecure-Requests': '1',
75 | 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.157 Safari/537.36',
76 | }
77 | result = requests.get(url, headers=headers)
78 | except requests.ConnectionError:
79 | raise ValueError("requests.ConnectionError")
80 | content = json.loads(result.text)
81 | # print(content)
82 | result = content["data"]
83 | self._get_initial_info(result)
84 | content = result["list"]
85 | for a_json in content:
86 | self._get_a_json_info(a_json)
87 | def _get_initial_info(self, result):
88 | self.info["content"] = []
89 | self.info["score"] = []
90 | self.info["totalScoreDesc"] = []
91 | self.info["commentTextList"] = []
92 | self.info["hostReply"] = []
93 | self.info["guestId"] = []
94 | self.info["gmtCreate"] = []
95 | def _get_a_json_info(self, a_json):
96 | try:
97 | self.info["score"].append(int(a_json["totalScore"]/10))
98 | except:
99 | self.info["score"].append([])
100 | try:
101 | self.info["content"].append(a_json["body"])
102 | except:
103 | self.info["content"].append([])
104 | try:
105 | self.info["commentTextList"].append(a_json["commentTextList"])
106 | except:
107 | self.info["commentTextList"].append([])
108 | try:
109 | self.info["totalScoreDesc"].append(a_json["totalScoreDesc"])
110 | except:
111 | self.info["totalScoreDesc"].append([])
112 | try:
113 | self.info["guestId"].append(a_json["guestId"])
114 | except:
115 | self.info["guestId"].append([])
116 | try:
117 | self.info["gmtCreate"].append(a_json["gmtCreate"])
118 | except:
119 | self.info["gmtCreate"].append([])
120 | try:
121 | self.info["hostReply"].append(a_json["hostReply"])
122 | except:
123 | self.info["hostReply"].append([])
124 | _crawler = Crawler()
125 | crawl = _crawler.crawl
126 | if __name__ == "__main__":
127 | shop_id = 'https://minsu.meituan.com/housing/9080714/'
128 | crawler = Crawler()
129 | a = crawler.crawl(shop_id)
--------------------------------------------------------------------------------
