├── .github
└── FUNDING.yml
├── .gitignore
├── CHANGELOG.md
├── Dockerfile
├── LICENSE
├── README.md
├── _config.yml
├── config.py.sample
├── docker-compose.yml
├── docs
├── _pages
│ ├── home.md
│ └── wp2128259-stock-market-wallpapers.jpg
├── stocksight-dashboard-kibana.png
└── stocksight.png
├── export.json
├── requirements.txt
├── sentiment.py
├── startup.sh
├── stockprice.py
└── twitteruserids.txt
/.github/FUNDING.yml:
--------------------------------------------------------------------------------
1 | patreon: shirosaidev
2 | custom: https://www.paypal.me/shirosaidev
3 |
--------------------------------------------------------------------------------
/.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 | env/
12 | build/
13 | develop-eggs/
14 | dist/
15 | downloads/
16 | eggs/
17 | .eggs/
18 | lib/
19 | lib64/
20 | parts/
21 | sdist/
22 | var/
23 | wheels/
24 | *.egg-info/
25 | .installed.cfg
26 | *.egg
27 |
28 | # PyInstaller
29 | # Usually these files are written by a python script from a template
30 | # before PyInstaller builds the exe, so as to inject date/other infos into it.
31 | *.manifest
32 | *.spec
33 |
34 | # Installer logs
35 | pip-log.txt
36 | pip-delete-this-directory.txt
37 |
38 | # Unit test / coverage reports
39 | htmlcov/
40 | .tox/
41 | .coverage
42 | .coverage.*
43 | .cache
44 | nosetests.xml
45 | coverage.xml
46 | *.cover
47 | .hypothesis/
48 |
49 | # Translations
50 | *.mo
51 | *.pot
52 |
53 | # Django stuff:
54 | *.log
55 | local_settings.py
56 |
57 | # Flask stuff:
58 | instance/
59 | .webassets-cache
60 |
61 | # Scrapy stuff:
62 | .scrapy
63 |
64 | # Sphinx documentation
65 | docs/_build/
66 |
67 | # PyBuilder
68 | target/
69 |
70 | # Jupyter Notebook
71 | .ipynb_checkpoints
72 |
73 | # pyenv
74 | .python-version
75 |
76 | # celery beat schedule file
77 | celerybeat-schedule
78 |
79 | # SageMath parsed files
80 | *.sage.py
81 |
82 | # dotenv
83 | .env
84 |
85 | # virtualenv
86 | .venv
87 | venv/
88 | ENV/
89 |
90 | # Spyder project settings
91 | .spyderproject
92 | .spyproject
93 |
94 | # Rope project settings
95 | .ropeproject
96 |
97 | # mkdocs documentation
98 | /site
99 |
100 | # mypy
101 | .mypy_cache/
102 | .DS_Store
103 |
--------------------------------------------------------------------------------
/CHANGELOG.md:
--------------------------------------------------------------------------------
1 | # stocksight Change Log
2 |
3 | ## [0.1-b.12] = 2020-06-08
4 | ### changed
5 | - removed --noelasticsearch cli arg option
6 |
7 | ## [0.1-b.11] = 2020-05-24
8 | ### changed
9 | - removed stocksight web site uploading capability, site has been removed
10 |
11 | ## [0.1-b.10] = 2020-03-29
12 | ### added
13 | - Dockerfile and docker-compose.yml for running in docker
14 | ### changed
15 | - added random time delay between fetching tweets to reduce chance of getting Twitter 420 code (throttled/backoff)
16 | ### fixed
17 | - using -k keywords no longer causes twitter user id's to be looked up
18 | - fatal error when looking up and using twitter user ids
19 |
20 | ## [0.1-b.9] = 2019-10-27
21 | ### added
22 | - -l --linksentiment cli arg - follow any tweet link urls and run sentiment analysis on those web pages
23 | - requirement for newspaper3k python module to requirements.txt, install with pip
24 |
25 | ## [0.1-b.8] = 2019-10-25
26 | ### added
27 | - -w --websentiment cli arg - Get sentiment results from text processing website
28 | - improved nltk token processing - no longed needed to provide multiple case in nltk tokens in config
29 | - requirement for nltk stopwords, install with python -c "import nltk; nltk.download('stopwords')"
30 | ### changed
31 | - getting web sentiment results from text processing website is no longer default
32 | - improved tweet text cleaning, sentiment algorithm and stocksight sentiment upload values
33 |
34 | ## [0.1-b.7] = 2019-10-24
35 | ### added
36 | - check if running Python 3
37 | - -U --upload - uploads sentiment to stocksight website (BETA) https://stocksight.diskoverspace.com/
38 | - stocksight_token in config.py.sample, used for auth to upload to stocksight website, copy to your config
39 | - nltk_min_tokens in config.py.sample, used to set minimum number of tokens required, copy to your config
40 | - tweet/news headline count/filtered/ratio log output
41 | - --noelasticsearch cli arg for not adding new docs to Elasticsearch
42 | - -s stock symbol cli arg (required arg), this is the stock symbol name and also used as the "tag name" on the stocksight webiste when uploading sentiment data
43 | - --overridetokensreq and --overridetokensignore cli args
44 | - -a --addtokens cli arg to add nltk required tokens from config to keywords
45 | ### changed
46 | - --newsheadlines no longer requires stock symbol, use -s to provide stock symbol
47 | - nltk required tokens from config now do not automatically get added to keywords, use -a or --addtokens to add them
48 | ### fixed
49 | - 'NoneType' object is not iterable Can't get sentiment from url caused by 400 Form Validation Errors text: This field is required traceback error when tweet with no text passed to sentiment_analysis
50 |
51 | ## [0.1-b.6] = 2019-07-15
52 | ### fixed
53 | - "TypeError: sequence item 0: expected str instance, int found" traceback error when running with -f twitteruserids.txt
54 |
55 | ## [0.1-b.5] = 2019-01-11
56 | ### changed
57 | - set encoding to utf-8 and checked for bytes when writing to twitteruserids.txt
58 |
59 | ## [0.1-b.4] = 2018-12-10
60 | ### fixed
61 | - TypeError: can't concat str to bytes when writing to twitteruserids.txt
62 |
63 | ## [0.1-b.3] = 2018-11-23
64 | ### added
65 | - requirements.txt for installing python requirements with pip
66 | - config.py.sample has new setting for specifying elasticsearch host/ip, port, username and password, copy to your config file
67 |
68 | ## [0.1-b.2] = 2018-10-10
69 | ### added
70 | - cli option -n --newsheadlines to fetch and analyze stock symbol headlines from yahoo finance website instead of twitter
71 | - cli option --frequency to control how often news headlines are retrieved
72 | - cli option --followlinks to follow any links in news headlines and scrape any relevant text on landing page
73 | - additional mappings for newsheadline docs in elasticsearch indices
74 | ### changed
75 | - code cleanup
76 |
77 | ## [0.1-b.1] = 2018-10-09
78 | ### note
79 | - first release
80 |
--------------------------------------------------------------------------------
/Dockerfile:
--------------------------------------------------------------------------------
1 | FROM python:3.6
2 |
3 | LABEL maintainer="shirosai"
4 |
5 | WORKDIR /app
6 |
7 | COPY requirements.txt ./
8 |
9 | RUN pip install --no-cache-dir -r requirements.txt
10 | RUN python -c "import nltk; nltk.download('punkt'); nltk.download('stopwords')"
11 |
12 | COPY sentiment.py ./
13 | COPY stockprice.py ./
14 | COPY startup.sh ./
15 |
16 | ENV PYTHONIOENCODING=utf8
17 |
18 | ENTRYPOINT [ "bash", "startup.sh" ]
--------------------------------------------------------------------------------
/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 2017-2019 Chris Park
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 |
3 | [](./LICENSE)
4 | [](https://github.com/shirosaidev/stocksight/releases/latest)
5 | [](https://www.patreon.com/shirosaidev)
6 | [](https://www.paypal.com/cgi-bin/webscr?cmd=_s-xclick&hosted_button_id=CLF223XAS4W72)
7 |
8 | # stocksight
9 | Stock market analyzer and stock predictor using Elasticsearch, Twitter, News headlines and Python natural language processing and sentiment analysis. How much do emotions on Twitter and news headlines affect a stock's price? Let's find out...
10 |
11 | ## About
12 | stocksight is an open source stock market analysis software that uses Elasticsearch to store Twitter and news headlines data for stocks. stocksight analyzes the emotions of what the author writes and does sentiment analysis on the text to determine how the author "feels" about a stock. It could be used for more than finding sentiment of just stocks, it could be used to find sentiment of anything...
13 |
14 |
15 | ## Slack workspace
16 | Join the conversation, get support, etc on [stocksight Slack](https://join.slack.com/t/stocksightworkspace/shared_invite/enQtNzk1ODI0NjA3MTM4LTA3ZDA0YzllOGNiM2I5ZjAzYWM2MjNmMjI0OTRlY2ZjYTk1NmM5YmEwMmMwOTE2OTNiMGZlNzdjZmZkM2RjM2U).
17 |
18 |
19 | ## Requirements
20 | - Python 3.x
21 | - Elasticsearch 5.x
22 | - Kibana 5.x
23 | - elasticsearch python module
24 | - nltk python module
25 | - requests python module
26 | - tweepy python module
27 | - beautifulsoup4 python module
28 | - textblob python module
29 | - vaderSentiment python module
30 | - newspaper3k python module
31 |
32 | ### Download
33 |
34 | ```shell
35 | $ git clone https://github.com/shirosaidev/stocksight.git
36 | $ cd stocksight
37 | ```
38 | [Download latest version](https://github.com/shirosaidev/stocksight/releases/latest)
39 |
40 | ## Screenshot
41 | Stocksight Kibana dashboard
42 |
43 |
44 |
45 | ## Install - Docker
46 |
47 | *** **See [how to use](#how-to-use) below before building the Docker containers** ***
48 |
49 | 1) Download/clone stocksight repo with git.
50 | 2) Set up stocksight, elasticsearch and kibana containers using Docker compose
51 | ```
52 | cd stocksight
53 | cp config.py.sample config.py
54 | ***see how to use below for config.py (stocksight config) changes***
55 | docker-compose build && docker-compose up
56 | ```
57 | **This will volume mount config.py (stocksight settings) and twitteruserids.txt to those files in your local git cloned "stocksight" directory**
58 |
59 | 3) Once all the containers have started up, shell into the container
60 |
61 | `docker exec -it stocksight_stocksight_1 bash`
62 |
63 | 4) See examples below for running stocksight.
64 |
65 | ## Install - local
66 |
67 | **Recommended to install Elasticsearch and Kibana in local machine or other machine/vm/docker**
68 |
69 | 1) Install python requirements using pip
70 |
71 | `pip install -r requirements.txt`
72 |
73 | 2) Install python nltk data
74 |
75 | `python -c "import nltk; nltk.download('punkt'); nltk.download('stopwords')"`
76 |
77 |
78 | ## How to use
79 | 1) Create a new twitter application and generate your consumer key and access token. https://developer.twitter.com/en/docs/basics/developer-portal/guides/apps.html
80 | https://developer.twitter.com/en/docs/basics/authentication/guides/access-tokens.html
81 |
82 | 2) Copy config.py.sample to config.py (stocksight config file)
83 |
84 | 3) Set elasticsearch settings in config.py for your env (for Docker, set `elasticsearch_host = "elasticsearch"`)
85 |
86 | 4) Add twitter consumer key/access token and secrets to config.py
87 |
88 | 5) Edit config.py and modify NLTK tokens required/ignored and twitter feeds you want to mine. NLTK tokens required are keywords which must be in tweet before adding it to Elasticsearch (whitelist). NLTK tokens ignored are keywords which if are found in tweet, it will not be added to Elasticsearch (blacklist).
89 |
90 | ### Examples
91 |
92 | Run sentiment.py to create 'stocksight' index in Elasticsearch and start mining and analyzing Tweets using keywords and the stock symbol TSLA
93 |
94 | ```sh
95 | $ python sentiment.py -s TSLA -k 'Elon Musk',Musk,Tesla,SpaceX --debug
96 | ```
97 |
98 | Start mining and analyzing Tweets using keywords and the stock symbol TSLA and follow any url links in tweets and performing sentiment analysis on the link web page as well as the tweet
99 |
100 | ```sh
101 | $ python sentiment.py -s TSLA -k 'Elon Musk',Musk,Tesla,SpaceX -l --debug
102 | ```
103 |
104 | Start mining and analyzing Tweets from feeds in config using cached user ids from file (if you change any of the twitter feeds in the config file, you need to delete this file and recreate it without -f)
105 |
106 | ```sh
107 | $ python sentiment.py -s TSLA -f twitteruserids.txt --debug
108 | ```
109 |
110 | Start mining and analyzing News headlines and following headline links and scraping relevant text on landing page
111 |
112 | ```sh
113 | $ python sentiment.py -s TSLA --followlinks --debug
114 | ```
115 |
116 | Run stockprice.py to add stock prices to 'stocksight' index in Elasticsearch
117 |
118 | ```sh
119 | $ python stockprice.py -s TSLA --debug
120 | ```
121 |
122 | ### Kibana
123 |
124 | Load 'stocksight' index in Kibana. For index pattern you can use 'stocksight' if you only have the single index or 'stocksight-*', etc. For time-field name you will want to use the date/time field 'date'.
125 |
126 | To import the saved exported visualizations/dashboard, go to Kibana, click on management, click on saved objects, click on the import button and import the export.json file.
127 |
128 |
129 | ### CLI options
130 |
131 | ```
132 | usage: sentiment.py [-h] [-i INDEX] [-d] -s SYMBOL [-k KEYWORDS] [-a] [-u URL]
133 | [-f FILE] [-l] [-n] [--frequency FREQUENCY]
134 | [--followlinks] [-w]
135 | [--overridetokensreq TOKEN [TOKEN ...]]
136 | [--overridetokensignore TOKEN [TOKEN ...]] [-v] [--debug]
137 | [-q] [-V]
138 |
139 | optional arguments:
140 | -h, --help show this help message and exit
141 | -i INDEX, --index INDEX
142 | Index name for Elasticsearch (default: stocksight)
143 | -d, --delindex Delete existing Elasticsearch index first
144 | -s SYMBOL, --symbol SYMBOL
145 | Stock symbol you are interesed in searching for,
146 | example: TSLA
147 | -k KEYWORDS, --keywords KEYWORDS
148 | Use keywords to search for in Tweets instead of feeds.
149 | Separated by comma, case insensitive, spaces are ANDs
150 | commas are ORs. Example: TSLA,'Elon
151 | Musk',Musk,Tesla,SpaceX
152 | -a, --addtokens Add nltk tokens required from config to keywords
153 | -u URL, --url URL Use twitter users from any links in web page at url
154 | -f FILE, --file FILE Use twitter user ids from file
155 | -l, --linksentiment Follow any link url in tweets and analyze sentiment on
156 | web page
157 | -n, --newsheadlines Get news headlines instead of Twitter using stock
158 | symbol from -s
159 | --frequency FREQUENCY
160 | How often in seconds to retrieve news headlines
161 | (default: 120 sec)
162 | --followlinks Follow links on news headlines and scrape relevant
163 | text from landing page
164 | -w, --websentiment Get sentiment results from text processing website
165 | --overridetokensreq TOKEN [TOKEN ...]
166 | Override nltk required tokens from config, separate
167 | with space
168 | --overridetokensignore TOKEN [TOKEN ...]
169 | Override nltk ignore tokens from config, separate with
170 | space
171 | -v, --verbose Increase output verbosity
172 | --debug Debug message output
173 | -q, --quiet Run quiet with no message output
174 | -V, --version Prints version and exits
175 |
176 |
177 | usage: stockprice.py [-h] [-i INDEX] [-d] [-s SYMBOL] [-f FREQUENCY] [-v]
178 | [--debug] [-q] [-V]
179 |
180 | optional arguments:
181 | -h, --help show this help message and exit
182 | -i INDEX, --index INDEX
183 | Index name for Elasticsearch (default: stocksight)
184 | -d, --delindex Delete existing Elasticsearch index first
185 | -s SYMBOL, --symbol SYMBOL
186 | Stock symbol to use, example: TSLA
187 | -f FREQUENCY, --frequency FREQUENCY
188 | How often in seconds to retrieve stock data (default:
189 | 120 sec)
190 | -v, --verbose Increase output verbosity
191 | --debug Debug message output
192 | -q, --quiet Run quiet with no message output
193 | -V, --version Prints version and exits
194 | ```
195 |
196 |
197 | ## Disclaimer
198 |
199 | This software is for educational purposes only. USE THE SOFTWARE AT YOUR OWN RISK. THE AUTHORS AND ALL AFFILIATES ASSUME NO RESPONSIBILITY FOR YOUR TRADING RESULTS. Do not risk money which you are afraid to lose. There might be bugs in the code - this software DOES NOT come with ANY warranty.
200 |
--------------------------------------------------------------------------------
/_config.yml:
--------------------------------------------------------------------------------
1 | remote_theme : "mmistakes/minimal-mistakes"
2 | minimal_mistakes_skin : "default"
3 |
4 | # Site Settings
5 | locale : "en-US"
6 | title : "stocksight"
7 | title_separator : "-"
8 | name : "shirosaidev"
9 | description : "croud-sourced open-source stock analyzer and stock predictor"
10 | url : https://shirosaidev.github.io
11 | baseurl : "/stocksight"
12 | repository : "shirosaidev/stocksight"
13 | show_downloads : true
14 |
15 | # Analytics
16 | analytics:
17 | provider : google
18 | google:
19 | tracking_id : UA-145407030-1
20 |
21 | plugins:
22 | - jekyll-remote-theme
23 | - jekyll-include-cache
24 | include: ["_pages"]
25 | defaults:
26 | - scope:
27 | path: "_pages"
28 | type: pages
29 | values:
30 | layout: splash
31 | author_profile: true
32 |
--------------------------------------------------------------------------------
/config.py.sample:
--------------------------------------------------------------------------------
1 | elasticsearch_host = "localhost"
2 | elasticsearch_port = 9200
3 | elasticsearch_user = ""
4 | elasticsearch_password = ""
5 | consumer_key = ""
6 | consumer_secret = ""
7 | access_token = ""
8 | access_token_secret = ""
9 | nltk_tokens_required = ("neuralink", "solar", "tesla", "@tesla", "#tesla", "tesla", "tsla", "#tsla", "elonmusk", "elon", "musk", "spacex", "starlink")
10 | nltk_min_tokens = 1
11 | nltk_tokens_ignored = ("win", "giveaway")
12 | twitter_feeds = ["@elonmusk", "@cnbc", "@benzinga", "@stockwits",
13 | "@Newsweek", "@WashingtonPost", "@breakoutstocks", "@bespokeinvest",
14 | "@WSJMarkets", "@stephanie_link", "@nytimesbusiness", "@IBDinvestors",
15 | "@WSJDealJournal", "@jimcramer", "@TheStalwart", "@TruthGundlach",
16 | "@Carl_C_Icahn", "@ReformedBroker", "@bespokeinvest", "@stlouisfed",
17 | "@muddywatersre", "@mcuban", "@AswathDamodaran", "@elerianm",
18 | "@MorganStanley", "@ianbremmer", "@GoldmanSachs", "@Wu_Tang_Finance",
19 | "@Schuldensuehner", "@NorthmanTrader", "@Frances_Coppola", "@bySamRo",
20 | "@BuzzFeed","@nytimes"]
21 |
--------------------------------------------------------------------------------
/docker-compose.yml:
--------------------------------------------------------------------------------
1 | version: '3'
2 | services:
3 | stocksight:
4 | build: .
5 | environment:
6 | - ES_HOST=elasticsearch
7 | depends_on:
8 | - elasticsearch
9 | volumes:
10 | - ./config.py:/app/config.py
11 | - ./twitteruserids.txt:/app/twitteruserids.txt
12 | elasticsearch:
13 | image: elasticsearch:5.6.16
14 | volumes:
15 | - ./esdata:/usr/share/elasticsearch/data
16 | environment:
17 | - discovery.type=single-node
18 | - bootstrap.memory_lock=true
19 | - "ES_JAVA_OPTS=-Xms512m -Xmx512m"
20 | ulimits:
21 | memlock:
22 | soft: -1
23 | hard: -1
24 | ports:
25 | - 9200:9200
26 | kibana:
27 | image: kibana:5.6.16
28 | ports:
29 | - 5601:5601
30 | depends_on:
31 | - elasticsearch
--------------------------------------------------------------------------------
/docs/_pages/home.md:
--------------------------------------------------------------------------------
1 | ---
2 | layout: splash
3 | permalink: /
4 | header:
5 | overlay_color: "#000"
6 | overlay_filter: "0.5"
7 | overlay_image: https://github.com/shirosaidev/stocksight/blob/master/docs/_pages/wp2128259-stock-market-wallpapers.jpg?raw=true
8 | cta_label: " Download"
9 | cta_url: "https://github.com/shirosaidev/stocksight/releases/latest"
10 | caption:
11 | excerpt: "Stock analyzer and stock predictor using Elasticsearch, Twitter, News headlines and Python natural language processing and sentiment analysis.
Latest release v0.1-b.11
12 | {::nomarkdown} {:/nomarkdown}"
13 | github:
14 | - excerpt: '{::nomarkdown}
15 | {:/nomarkdown}'
16 | intro:
17 | - excerpt: '{::nomarkdown}Support the development Sponsor Patreon Donate PayPal View on GitHub{:/nomarkdown}'
18 | ---
19 |
20 | {% include feature_row id="intro" type="center" %}
21 |
22 |
stocksight is an open source stock analysis software that uses Elasticsearch to store Twitter and news headlines data for stocks. stocksight analyzes the emotions of what the author writes and does sentiment analysis on the text to determine how the author "feels" about a stock.
23 | -------------------------------------------------------------------------------- /docs/_pages/wp2128259-stock-market-wallpapers.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirosaidev/stocksight/580d35876f2d9c0cb905b723c664f053abdd567c/docs/_pages/wp2128259-stock-market-wallpapers.jpg -------------------------------------------------------------------------------- /docs/stocksight-dashboard-kibana.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirosaidev/stocksight/580d35876f2d9c0cb905b723c664f053abdd567c/docs/stocksight-dashboard-kibana.png -------------------------------------------------------------------------------- /docs/stocksight.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirosaidev/stocksight/580d35876f2d9c0cb905b723c664f053abdd567c/docs/stocksight.png -------------------------------------------------------------------------------- /export.json: -------------------------------------------------------------------------------- 1 | [ 2 | { 3 | "_id": "AWZPAfg50rkQl37xrvXw", 4 | "_type": "dashboard", 5 | "_source": { 6 | "title": "stocksight_dashboard", 7 | "hits": 0, 8 | "description": "", 9 | "panelsJSON": "[{\"col\":1,\"id\":\"AWZO7a1n0rkQl37xrvXK\",\"panelIndex\":1,\"row\":3,\"size_x\":3,\"size_y\":3,\"type\":\"visualization\"},{\"col\":9,\"id\":\"AWZO8wUR0rkQl37xrvXV\",\"panelIndex\":2,\"row\":3,\"size_x\":4,\"size_y\":3,\"type\":\"visualization\"},{\"col\":1,\"columns\":[\"author\",\"location\",\"message\",\"polarity\",\"subjectivity\",\"sentiment\"],\"id\":\"AWZO_6iv0rkQl37xrvXt\",\"panelIndex\":3,\"row\":6,\"size_x\":12,\"size_y\":4,\"sort\":[\"date\",\"desc\"],\"type\":\"search\"},{\"col\":1,\"id\":\"AWZW6DNS0rkQl37xrvcg\",\"panelIndex\":4,\"row\":10,\"size_x\":12,\"size_y\":4,\"type\":\"visualization\"},{\"col\":4,\"id\":\"AWZYOrcih4RzKn4w3M7J\",\"panelIndex\":5,\"row\":3,\"size_x\":5,\"size_y\":3,\"type\":\"visualization\"},{\"col\":1,\"id\":\"AWZY6Xtjh4RzKn4w3NXT\",\"panelIndex\":6,\"row\":1,\"size_x\":12,\"size_y\":2,\"type\":\"visualization\"}]", 10 | "optionsJSON": "{\"darkTheme\":true}", 11 | "uiStateJSON": "{\"P-2\":{\"vis\":{\"legendOpen\":true}},\"P-6\":{\"vis\":{\"defaultColors\":{\"0 - 1\":\"rgb(0,104,55)\"}}}}", 12 | "version": 1, 13 | "timeRestore": false, 14 | "kibanaSavedObjectMeta": { 15 | "searchSourceJSON": "{\"filter\":[{\"query\":{\"match_all\":{}}}],\"highlightAll\":true,\"version\":true}" 16 | } 17 | } 18 | }, 19 | { 20 | "_id": "AWZO_6iv0rkQl37xrvXt", 21 | "_type": "search", 22 | "_source": { 23 | "title": "stocksight_savesearch", 24 | "description": "", 25 | "hits": 0, 26 | "columns": [ 27 | "author", 28 | "location", 29 | "message", 30 | "polarity", 31 | "subjectivity", 32 | "sentiment" 33 | ], 34 | "sort": [ 35 | "date", 36 | "desc" 37 | ], 38 | "version": 1, 39 | "kibanaSavedObjectMeta": { 40 | "searchSourceJSON": "{\"index\":\"stocksight\",\"highlightAll\":true,\"version\":true,\"query\":{\"match_all\":{}},\"filter\":[{\"meta\":{\"index\":\"stocksight\",\"negate\":false,\"disabled\":false,\"alias\":null,\"type\":\"phrase\",\"key\":\"_type\",\"value\":\"tweet\"},\"query\":{\"match\":{\"_type\":{\"query\":\"tweet\",\"type\":\"phrase\"}}},\"$state\":{\"store\":\"appState\"}}]}" 41 | } 42 | } 43 | }, 44 | { 45 | "_id": "AWZY6Xtjh4RzKn4w3NXT", 46 | "_type": "visualization", 47 | "_source": { 48 | "title": "stocksight_polarity", 49 | "visState": "{\"title\":\"stocksight_polarity\",\"type\":\"metric\",\"params\":{\"addTooltip\":true,\"addLegend\":false,\"type\":\"gauge\",\"gauge\":{\"verticalSplit\":false,\"autoExtend\":false,\"percentageMode\":false,\"gaugeType\":\"Metric\",\"gaugeStyle\":\"Full\",\"backStyle\":\"Full\",\"orientation\":\"vertical\",\"colorSchema\":\"Green to Red\",\"gaugeColorMode\":\"None\",\"useRange\":false,\"colorsRange\":[{\"from\":0,\"to\":1}],\"invertColors\":false,\"labels\":{\"show\":true,\"color\":\"black\"},\"scale\":{\"show\":false,\"labels\":false,\"color\":\"#333\",\"width\":2},\"type\":\"simple\",\"style\":{\"fontSize\":\"24\",\"bgColor\":false,\"labelColor\":false,\"subText\":\"\"},\"extendRange\":false}},\"aggs\":[{\"id\":\"5\",\"enabled\":true,\"type\":\"count\",\"schema\":\"metric\",\"params\":{}},{\"id\":\"1\",\"enabled\":true,\"type\":\"avg\",\"schema\":\"metric\",\"params\":{\"field\":\"polarity\"}},{\"id\":\"4\",\"enabled\":true,\"type\":\"median\",\"schema\":\"metric\",\"params\":{\"field\":\"polarity\",\"percents\":[50]}},{\"id\":\"2\",\"enabled\":true,\"type\":\"min\",\"schema\":\"metric\",\"params\":{\"field\":\"polarity\"}},{\"id\":\"3\",\"enabled\":true,\"type\":\"max\",\"schema\":\"metric\",\"params\":{\"field\":\"polarity\"}}],\"listeners\":{}}", 50 | "uiStateJSON": "{\"vis\":{\"defaultColors\":{\"0 - 1\":\"rgb(0,104,55)\"}}}", 51 | "description": "", 52 | "version": 1, 53 | "kibanaSavedObjectMeta": { 54 | "searchSourceJSON": "{\"index\":\"stocksight\",\"query\":{\"match_all\":{}},\"filter\":[]}" 55 | } 56 | } 57 | }, 58 | { 59 | "_id": "AWZO7a1n0rkQl37xrvXK", 60 | "_type": "visualization", 61 | "_source": { 62 | "title": "stocksight_sentinel", 63 | "visState": "{\"title\":\"stocksight_sentinel\",\"type\":\"pie\",\"params\":{\"addLegend\":true,\"addTooltip\":true,\"isDonut\":false,\"legendPosition\":\"bottom\",\"type\":\"pie\"},\"aggs\":[{\"id\":\"1\",\"enabled\":true,\"type\":\"count\",\"schema\":\"metric\",\"params\":{}},{\"id\":\"2\",\"enabled\":true,\"type\":\"terms\",\"schema\":\"segment\",\"params\":{\"field\":\"sentiment.keyword\",\"size\":5,\"order\":\"desc\",\"orderBy\":\"1\"}}],\"listeners\":{}}", 64 | "uiStateJSON": "{}", 65 | "description": "", 66 | "version": 1, 67 | "kibanaSavedObjectMeta": { 68 | "searchSourceJSON": "{\"index\":\"stocksight\",\"query\":{\"match_all\":{}},\"filter\":[]}" 69 | } 70 | } 71 | }, 72 | { 73 | "_id": "AWZYOrcih4RzKn4w3M7J", 74 | "_type": "visualization", 75 | "_source": { 76 | "title": "stocksight_stockprice", 77 | "visState": "{\"title\":\"stocksight_stockprice\",\"type\":\"line\",\"params\":{\"grid\":{\"categoryLines\":false,\"style\":{\"color\":\"#eee\"}},\"categoryAxes\":[{\"id\":\"CategoryAxis-1\",\"type\":\"category\",\"position\":\"bottom\",\"show\":true,\"style\":{},\"scale\":{\"type\":\"linear\"},\"labels\":{\"show\":true,\"truncate\":100},\"title\":{\"text\":\"date per 30 seconds\"}}],\"valueAxes\":[{\"id\":\"ValueAxis-1\",\"name\":\"LeftAxis-1\",\"type\":\"value\",\"position\":\"left\",\"show\":true,\"style\":{},\"scale\":{\"type\":\"linear\",\"mode\":\"normal\"},\"labels\":{\"show\":true,\"rotate\":0,\"filter\":false,\"truncate\":100},\"title\":{\"text\":\"Sum of price_last\"}}],\"seriesParams\":[{\"show\":\"true\",\"type\":\"line\",\"mode\":\"normal\",\"data\":{\"label\":\"Sum of price_last\",\"id\":\"1\"},\"valueAxis\":\"ValueAxis-1\",\"drawLinesBetweenPoints\":true,\"showCircles\":true},{\"show\":true,\"mode\":\"normal\",\"type\":\"line\",\"drawLinesBetweenPoints\":true,\"showCircles\":true,\"data\":{\"id\":\"3\",\"label\":\"Sum of price_high\"},\"valueAxis\":\"ValueAxis-1\"},{\"show\":true,\"mode\":\"normal\",\"type\":\"line\",\"drawLinesBetweenPoints\":true,\"showCircles\":true,\"data\":{\"id\":\"4\",\"label\":\"Sum of price_low\"},\"valueAxis\":\"ValueAxis-1\"}],\"addTooltip\":true,\"addLegend\":true,\"legendPosition\":\"bottom\",\"times\":[],\"addTimeMarker\":false,\"type\":\"line\"},\"aggs\":[{\"id\":\"1\",\"enabled\":true,\"type\":\"sum\",\"schema\":\"metric\",\"params\":{\"field\":\"price_last\"}},{\"id\":\"2\",\"enabled\":true,\"type\":\"date_histogram\",\"schema\":\"segment\",\"params\":{\"field\":\"date\",\"interval\":\"auto\",\"customInterval\":\"2h\",\"min_doc_count\":1,\"extended_bounds\":{}}},{\"id\":\"3\",\"enabled\":true,\"type\":\"sum\",\"schema\":\"metric\",\"params\":{\"field\":\"price_high\"}},{\"id\":\"4\",\"enabled\":true,\"type\":\"sum\",\"schema\":\"metric\",\"params\":{\"field\":\"price_low\"}}],\"listeners\":{}}", 78 | "uiStateJSON": "{}", 79 | "description": "", 80 | "version": 1, 81 | "kibanaSavedObjectMeta": { 82 | "searchSourceJSON": "{\"index\":\"stocksight\",\"query\":{\"match_all\":{}},\"filter\":[{\"meta\":{\"index\":\"stocksight\",\"negate\":false,\"disabled\":false,\"alias\":null,\"type\":\"phrase\",\"key\":\"_type\",\"value\":\"stock\"},\"query\":{\"match\":{\"_type\":{\"query\":\"stock\",\"type\":\"phrase\"}}},\"$state\":{\"store\":\"appState\"}}]}" 83 | } 84 | } 85 | }, 86 | { 87 | "_id": "AWZO8wUR0rkQl37xrvXV", 88 | "_type": "visualization", 89 | "_source": { 90 | "title": "stocksight_tweets", 91 | "visState": "{\"title\":\"stocksight_tweets\",\"type\":\"line\",\"params\":{\"grid\":{\"categoryLines\":false,\"style\":{\"color\":\"#eee\"}},\"categoryAxes\":[{\"id\":\"CategoryAxis-1\",\"type\":\"category\",\"position\":\"bottom\",\"show\":true,\"style\":{},\"scale\":{\"type\":\"linear\"},\"labels\":{\"show\":true,\"truncate\":100},\"title\":{\"text\":\"date per 30 seconds\"}}],\"valueAxes\":[{\"id\":\"ValueAxis-1\",\"name\":\"LeftAxis-1\",\"type\":\"value\",\"position\":\"left\",\"show\":true,\"style\":{},\"scale\":{\"type\":\"linear\",\"mode\":\"normal\"},\"labels\":{\"show\":true,\"rotate\":0,\"filter\":false,\"truncate\":100},\"title\":{\"text\":\"Count\"}}],\"seriesParams\":[{\"show\":\"true\",\"type\":\"line\",\"mode\":\"normal\",\"data\":{\"label\":\"Count\",\"id\":\"1\"},\"valueAxis\":\"ValueAxis-1\",\"drawLinesBetweenPoints\":true,\"showCircles\":true,\"interpolate\":\"linear\"}],\"addTooltip\":true,\"addLegend\":true,\"legendPosition\":\"bottom\",\"times\":[],\"addTimeMarker\":false,\"type\":\"line\"},\"aggs\":[{\"id\":\"1\",\"enabled\":true,\"type\":\"count\",\"schema\":\"metric\",\"params\":{\"customLabel\":\"\"}},{\"id\":\"2\",\"enabled\":true,\"type\":\"date_histogram\",\"schema\":\"segment\",\"params\":{\"field\":\"date\",\"interval\":\"auto\",\"customInterval\":\"2h\",\"min_doc_count\":1,\"extended_bounds\":{}}}],\"listeners\":{}}", 92 | "uiStateJSON": "{}", 93 | "description": "", 94 | "version": 1, 95 | "kibanaSavedObjectMeta": { 96 | "searchSourceJSON": "{\"index\":\"stocksight\",\"query\":{\"match_all\":{}},\"filter\":[]}" 97 | } 98 | } 99 | }, 100 | { 101 | "_id": "AWZW6DNS0rkQl37xrvcg", 102 | "_type": "visualization", 103 | "_source": { 104 | "title": "stocksight_wordcloud", 105 | "visState": "{\n \"title\": \"stocksight_wordcloud\",\n \"type\": \"tagcloud\",\n \"params\": {\n \"scale\": \"linear\",\n \"orientation\": \"single\",\n \"minFontSize\": 14,\n \"maxFontSize\": 36,\n \"type\": \"tagcloud\"\n },\n \"aggs\": [\n {\n \"id\": \"1\",\n \"enabled\": true,\n \"type\": \"count\",\n \"schema\": \"metric\",\n \"params\": {}\n },\n {\n \"id\": \"2\",\n \"enabled\": true,\n \"type\": \"terms\",\n \"schema\": \"segment\",\n \"params\": {\n \"field\": \"message.keyword\",\n \"size\": 25,\n \"order\": \"desc\",\n \"orderBy\": \"1\"\n }\n }\n ],\n \"listeners\": {}\n}", 106 | "uiStateJSON": "{}", 107 | "description": "", 108 | "version": 1, 109 | "kibanaSavedObjectMeta": { 110 | "searchSourceJSON": "{\n \"index\": \"stocksight\",\n \"query\": {\n \"match_all\": {}\n },\n \"filter\": []\n}" 111 | } 112 | } 113 | } 114 | ] -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | elasticsearch>=5.0.0,<6.0.0 2 | requests 3 | nltk 4 | tweepy 5 | beautifulsoup4 6 | textblob 7 | vaderSentiment 8 | newspaper3k 9 | -------------------------------------------------------------------------------- /sentiment.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # -*- coding: utf-8 -*- 3 | """sentiment.py - analyze tweets on Twitter and add 4 | relevant tweets and their sentiment values to 5 | Elasticsearch. 6 | See README.md or https://github.com/shirosaidev/stocksight 7 | for more information. 8 | 9 | Copyright (C) Chris Park 2018-2020 10 | stocksight is released under the Apache 2.0 license. See 11 | LICENSE for the full license text. 12 | """ 13 | 14 | import sys 15 | import json 16 | import time 17 | import re 18 | import requests 19 | import nltk 20 | import argparse 21 | import logging 22 | import string 23 | try: 24 | import urllib.parse as urlparse 25 | except ImportError: 26 | import urlparse 27 | from tweepy.streaming import StreamListener 28 | from tweepy import API, Stream, OAuthHandler, TweepError 29 | from textblob import TextBlob 30 | from vaderSentiment.vaderSentiment import SentimentIntensityAnalyzer 31 | from bs4 import BeautifulSoup 32 | from elasticsearch import Elasticsearch 33 | from random import randint, randrange 34 | from datetime import datetime 35 | from newspaper import Article, ArticleException 36 | 37 | # import elasticsearch host, twitter keys and tokens 38 | from config import * 39 | 40 | 41 | STOCKSIGHT_VERSION = '0.1-b.12' 42 | __version__ = STOCKSIGHT_VERSION 43 | 44 | IS_PY3 = sys.version_info >= (3, 0) 45 | 46 | if not IS_PY3: 47 | print("Sorry, stocksight requires Python 3.") 48 | sys.exit(1) 49 | 50 | # sentiment text-processing url 51 | sentimentURL = 'http://text-processing.com/api/sentiment/' 52 | 53 | # tweet id list 54 | tweet_ids = [] 55 | 56 | # file to hold twitter user ids 57 | twitter_users_file = './twitteruserids.txt' 58 | 59 | prev_time = time.time() 60 | sentiment_avg = [0.0,0.0,0.0] 61 | 62 | 63 | class TweetStreamListener(StreamListener): 64 | 65 | def __init__(self): 66 | self.count = 0 67 | self.count_filtered = 0 68 | self.filter_ratio = 0 69 | 70 | # on success 71 | def on_data(self, data): 72 | try: 73 | self.count+=1 74 | # decode json 75 | dict_data = json.loads(data) 76 | 77 | print("\n------------------------------> (tweets: %s, filtered: %s, filter-ratio: %s)" \ 78 | % (self.count, self.count_filtered, str(round(self.count_filtered/self.count*100,2))+"%")) 79 | logger.debug('tweet data: ' + str(dict_data)) 80 | 81 | text = dict_data["text"] 82 | if text is None: 83 | logger.info("Tweet has no relevant text, skipping") 84 | self.count_filtered+=1 85 | return True 86 | 87 | # grab html links from tweet 88 | tweet_urls = [] 89 | if args.linksentiment: 90 | tweet_urls = re.findall(r'(https?://[^\s]+)', text) 91 | 92 | # clean up tweet text 93 | textclean = clean_text(text) 94 | 95 | # check if tweet has no valid text 96 | if textclean == "": 97 | logger.info("Tweet does not cotain any valid text after cleaning, not adding") 98 | self.count_filtered+=1 99 | return True 100 | 101 | # get date when tweet was created 102 | created_date = time.strftime( 103 | '%Y-%m-%dT%H:%M:%S', time.strptime(dict_data['created_at'], '%a %b %d %H:%M:%S +0000 %Y')) 104 | 105 | # store dict_data into vars 106 | screen_name = str(dict_data.get("user", {}).get("screen_name")) 107 | location = str(dict_data.get("user", {}).get("location")) 108 | language = str(dict_data.get("user", {}).get("lang")) 109 | friends = int(dict_data.get("user", {}).get("friends_count")) 110 | followers = int(dict_data.get("user", {}).get("followers_count")) 111 | statuses = int(dict_data.get("user", {}).get("statuses_count")) 112 | text_filtered = str(textclean) 113 | tweetid = int(dict_data.get("id")) 114 | text_raw = str(dict_data.get("text")) 115 | 116 | # output twitter data 117 | print("\n<------------------------------") 118 | print("Tweet Date: " + created_date) 119 | print("Screen Name: " + screen_name) 120 | print("Location: " + location) 121 | print("Language: " + language) 122 | print("Friends: " + str(friends)) 123 | print("Followers: " + str(followers)) 124 | print("Statuses: " + str(statuses)) 125 | print("Tweet ID: " + str(tweetid)) 126 | print("Tweet Raw Text: " + text_raw) 127 | print("Tweet Filtered Text: " + text_filtered) 128 | 129 | # create tokens of words in text using nltk 130 | text_for_tokens = re.sub( 131 | r"[\%|\$|\.|\,|\!|\:|\@]|\(|\)|\#|\+|(``)|('')|\?|\-", "", text_filtered) 132 | tokens = nltk.word_tokenize(text_for_tokens) 133 | # convert to lower case 134 | tokens = [w.lower() for w in tokens] 135 | # remove punctuation from each word 136 | table = str.maketrans('', '', string.punctuation) 137 | stripped = [w.translate(table) for w in tokens] 138 | # remove remaining tokens that are not alphabetic 139 | tokens = [w for w in stripped if w.isalpha()] 140 | # filter out stop words 141 | stop_words = set(nltk.corpus.stopwords.words('english')) 142 | tokens = [w for w in tokens if not w in stop_words] 143 | # remove words less than 3 characters 144 | tokens = [w for w in tokens if not len(w) < 3] 145 | print("NLTK Tokens: " + str(tokens)) 146 | 147 | # check for min token length 148 | if len(tokens) < 5: 149 | logger.info("Tweet does not contain min. number of tokens, not adding") 150 | self.count_filtered+=1 151 | return True 152 | 153 | # do some checks before adding to elasticsearch and crawling urls in tweet 154 | if friends == 0 or \ 155 | followers == 0 or \ 156 | statuses == 0 or \ 157 | text == "" or \ 158 | tweetid in tweet_ids: 159 | logger.info("Tweet doesn't meet min requirements, not adding") 160 | self.count_filtered+=1 161 | return True 162 | 163 | # check ignored tokens from config 164 | for t in nltk_tokens_ignored: 165 | if t in tokens: 166 | logger.info("Tweet contains token from ignore list, not adding") 167 | self.count_filtered+=1 168 | return True 169 | # check required tokens from config 170 | tokenspass = False 171 | tokensfound = 0 172 | for t in nltk_tokens_required: 173 | if t in tokens: 174 | tokensfound += 1 175 | if tokensfound == nltk_min_tokens: 176 | tokenspass = True 177 | break 178 | if not tokenspass: 179 | logger.info("Tweet does not contain token from required list or min required, not adding") 180 | self.count_filtered+=1 181 | return True 182 | 183 | # clean text for sentiment analysis 184 | text_clean = clean_text_sentiment(text_filtered) 185 | 186 | # check if tweet has no valid text 187 | if text_clean == "": 188 | logger.info("Tweet does not cotain any valid text after cleaning, not adding") 189 | self.count_filtered+=1 190 | return True 191 | 192 | print("Tweet Clean Text (sentiment): " + text_clean) 193 | 194 | # get sentiment values 195 | polarity, subjectivity, sentiment = sentiment_analysis(text_clean) 196 | 197 | # add tweet_id to list 198 | tweet_ids.append(dict_data["id"]) 199 | 200 | # get sentiment for tweet 201 | if len(tweet_urls) > 0: 202 | tweet_urls_polarity = 0 203 | tweet_urls_subjectivity = 0 204 | for url in tweet_urls: 205 | res = tweeklink_sentiment_analysis(url) 206 | if res is None: 207 | continue 208 | pol, sub, sen = res 209 | tweet_urls_polarity = (tweet_urls_polarity + pol) / 2 210 | tweet_urls_subjectivity = (tweet_urls_subjectivity + sub) / 2 211 | if sentiment == "positive" or sen == "positive": 212 | sentiment = "positive" 213 | elif sentiment == "negative" or sen == "negative": 214 | sentiment = "negative" 215 | else: 216 | sentiment = "neutral" 217 | 218 | # calculate average polarity and subjectivity from tweet and tweet links 219 | if tweet_urls_polarity > 0: 220 | polarity = (polarity + tweet_urls_polarity) / 2 221 | if tweet_urls_subjectivity > 0: 222 | subjectivity = (subjectivity + tweet_urls_subjectivity) / 2 223 | 224 | 225 | logger.info("Adding tweet to elasticsearch") 226 | # add twitter data and sentiment info to elasticsearch 227 | es.index(index=args.index, 228 | doc_type="tweet", 229 | body={"author": screen_name, 230 | "location": location, 231 | "language": language, 232 | "friends": friends, 233 | "followers": followers, 234 | "statuses": statuses, 235 | "date": created_date, 236 | "message": text_filtered, 237 | "tweet_id": tweetid, 238 | "polarity": polarity, 239 | "subjectivity": subjectivity, 240 | "sentiment": sentiment}) 241 | 242 | # randomly sleep to stagger request time 243 | time.sleep(randrange(2,5)) 244 | return True 245 | 246 | except Exception as e: 247 | logger.warning("Exception: exception caused by: %s" % e) 248 | raise 249 | 250 | # on failure 251 | def on_error(self, status_code): 252 | logger.error("Got an error with status code: %s (will try again later)" % status_code) 253 | # randomly sleep to stagger request time 254 | time.sleep(randrange(2,30)) 255 | return True 256 | 257 | # on timeout 258 | def on_timeout(self): 259 | logger.warning("Timeout... (will try again later)") 260 | # randomly sleep to stagger request time 261 | time.sleep(randrange(2,30)) 262 | return True 263 | 264 | 265 | class NewsHeadlineListener: 266 | 267 | def __init__(self, url=None, frequency=120): 268 | self.url = url 269 | self.headlines = [] 270 | self.followedlinks = [] 271 | self.frequency = frequency 272 | self.count = 0 273 | self.count_filtered = 0 274 | self.filter_ratio = 0 275 | 276 | while True: 277 | new_headlines = self.get_news_headlines(self.url) 278 | 279 | # add any new headlines 280 | for htext, htext_url in new_headlines: 281 | if htext not in self.headlines: 282 | self.headlines.append(htext) 283 | self.count+=1 284 | 285 | datenow = datetime.utcnow().isoformat() 286 | # output news data 287 | print("\n------------------------------> (news headlines: %s, filtered: %s, filter-ratio: %s)" \ 288 | % (self.count, self.count_filtered, str(round(self.count_filtered/self.count*100,2))+"%")) 289 | print("Date: " + datenow) 290 | print("News Headline: " + htext) 291 | print("Location (url): " + htext_url) 292 | 293 | # create tokens of words in text using nltk 294 | text_for_tokens = re.sub( 295 | r"[\%|\$|\.|\,|\!|\:|\@]|\(|\)|\#|\+|(``)|('')|\?|\-", "", htext) 296 | tokens = nltk.word_tokenize(text_for_tokens) 297 | print("NLTK Tokens: " + str(tokens)) 298 | 299 | # check for min token length 300 | if len(tokens) < 5: 301 | logger.info("Text does not contain min. number of tokens, not adding") 302 | self.count_filtered+=1 303 | continue 304 | 305 | # check ignored tokens from config 306 | for t in nltk_tokens_ignored: 307 | if t in tokens: 308 | logger.info("Text contains token from ignore list, not adding") 309 | self.count_filtered+=1 310 | continue 311 | # check required tokens from config 312 | tokenspass = False 313 | for t in nltk_tokens_required: 314 | if t in tokens: 315 | tokenspass = True 316 | break 317 | if not tokenspass: 318 | logger.info("Text does not contain token from required list, not adding") 319 | self.count_filtered+=1 320 | continue 321 | 322 | # get sentiment values 323 | polarity, subjectivity, sentiment = sentiment_analysis(htext) 324 | 325 | logger.info("Adding news headline to elasticsearch") 326 | # add news headline data and sentiment info to elasticsearch 327 | es.index(index=args.index, 328 | doc_type="newsheadline", 329 | body={"date": datenow, 330 | "location": htext_url, 331 | "message": htext, 332 | "polarity": polarity, 333 | "subjectivity": subjectivity, 334 | "sentiment": sentiment}) 335 | 336 | logger.info("Will get news headlines again in %s sec..." % self.frequency) 337 | time.sleep(self.frequency) 338 | 339 | def get_news_headlines(self, url): 340 | 341 | latestheadlines = [] 342 | latestheadlines_links = [] 343 | parsed_uri = urlparse.urljoin(url, '/') 344 | 345 | try: 346 | 347 | req = requests.get(url) 348 | html = req.text 349 | soup = BeautifulSoup(html, 'html.parser') 350 | html = soup.findAll('h3') 351 | links = soup.findAll('a') 352 | 353 | logger.debug(html) 354 | logger.debug(links) 355 | 356 | if html: 357 | for i in html: 358 | latestheadlines.append((i.next.next.next.next, url)) 359 | logger.debug(latestheadlines) 360 | 361 | if args.followlinks: 362 | if links: 363 | for i in links: 364 | if '/news/' in i['href']: 365 | l = parsed_uri.rstrip('/') + i['href'] 366 | if l not in self.followedlinks: 367 | latestheadlines_links.append(l) 368 | self.followedlinks.append(l) 369 | logger.debug(latestheadlines_links) 370 | 371 | logger.info("Following any new links and grabbing text from page...") 372 | 373 | for linkurl in latestheadlines_links: 374 | for p in get_page_text(linkurl): 375 | latestheadlines.append((p, linkurl)) 376 | logger.debug(latestheadlines) 377 | 378 | except requests.exceptions.RequestException as re: 379 | logger.warning("Exception: can't crawl web site (%s)" % re) 380 | pass 381 | 382 | return latestheadlines 383 | 384 | 385 | def get_page_text(url): 386 | 387 | max_paragraphs = 10 388 | 389 | try: 390 | logger.debug(url) 391 | req = requests.get(url) 392 | html = req.text 393 | soup = BeautifulSoup(html, 'html.parser') 394 | html_p = soup.findAll('p') 395 | 396 | logger.debug(html_p) 397 | 398 | if html_p: 399 | n = 1 400 | for i in html_p: 401 | if n <= max_paragraphs: 402 | if i.string is not None: 403 | logger.debug(i.string) 404 | yield i.string 405 | n += 1 406 | 407 | except requests.exceptions.RequestException as re: 408 | logger.warning("Exception: can't crawl web site (%s)" % re) 409 | pass 410 | 411 | 412 | def clean_text(text): 413 | # clean up text 414 | text = text.replace("\n", " ") 415 | text = re.sub(r"https?\S+", "", text) 416 | text = re.sub(r"&.*?;", "", text) 417 | text = re.sub(r"<.*?>", "", text) 418 | text = text.replace("RT", "") 419 | text = text.replace(u"…", "") 420 | text = text.strip() 421 | return text 422 | 423 | 424 | def clean_text_sentiment(text): 425 | # clean up text for sentiment analysis 426 | text = re.sub(r"[#|@]\S+", "", text) 427 | text = text.strip() 428 | return text 429 | 430 | 431 | def get_sentiment_from_url(text, sentimentURL): 432 | # get sentiment from text processing website 433 | payload = {'text': text} 434 | 435 | try: 436 | #logger.debug(text) 437 | post = requests.post(sentimentURL, data=payload) 438 | #logger.debug(post.status_code) 439 | #logger.debug(post.text) 440 | except requests.exceptions.RequestException as re: 441 | logger.error("Exception: requests exception getting sentiment from url caused by %s" % re) 442 | raise 443 | 444 | # return None if we are getting throttled or other connection problem 445 | if post.status_code != 200: 446 | logger.warning("Can't get sentiment from url caused by %s %s" % (post.status_code, post.text)) 447 | return None 448 | 449 | response = post.json() 450 | 451 | neg = response['probability']['neg'] 452 | pos = response['probability']['pos'] 453 | neu = response['probability']['neutral'] 454 | label = response['label'] 455 | 456 | # determine if sentiment is positive, negative, or neutral 457 | if label == "neg": 458 | sentiment = "negative" 459 | elif label == "neutral": 460 | sentiment = "neutral" 461 | else: 462 | sentiment = "positive" 463 | 464 | return sentiment, neg, pos, neu 465 | 466 | 467 | def sentiment_analysis(text): 468 | """Determine if sentiment is positive, negative, or neutral 469 | algorithm to figure out if sentiment is positive, negative or neutral 470 | uses sentiment polarity from TextBlob, VADER Sentiment and 471 | sentiment from text-processing URL 472 | could be made better :) 473 | """ 474 | 475 | # pass text into sentiment url 476 | if args.websentiment: 477 | ret = get_sentiment_from_url(text, sentimentURL) 478 | if ret is None: 479 | sentiment_url = None 480 | else: 481 | sentiment_url, neg_url, pos_url, neu_url = ret 482 | else: 483 | sentiment_url = None 484 | 485 | # pass text into TextBlob 486 | text_tb = TextBlob(text) 487 | 488 | # pass text into VADER Sentiment 489 | analyzer = SentimentIntensityAnalyzer() 490 | text_vs = analyzer.polarity_scores(text) 491 | 492 | # determine sentiment from our sources 493 | if sentiment_url is None: 494 | if text_tb.sentiment.polarity < 0 and text_vs['compound'] <= -0.05: 495 | sentiment = "negative" 496 | elif text_tb.sentiment.polarity > 0 and text_vs['compound'] >= 0.05: 497 | sentiment = "positive" 498 | else: 499 | sentiment = "neutral" 500 | else: 501 | if text_tb.sentiment.polarity < 0 and text_vs['compound'] <= -0.05 and sentiment_url == "negative": 502 | sentiment = "negative" 503 | elif text_tb.sentiment.polarity > 0 and text_vs['compound'] >= 0.05 and sentiment_url == "positive": 504 | sentiment = "positive" 505 | else: 506 | sentiment = "neutral" 507 | 508 | # calculate average polarity from TextBlob and VADER 509 | polarity = (text_tb.sentiment.polarity + text_vs['compound']) / 2 510 | 511 | # output sentiment polarity 512 | print("************") 513 | print("Sentiment Polarity: " + str(round(polarity, 3))) 514 | 515 | # output sentiment subjectivity (TextBlob) 516 | print("Sentiment Subjectivity: " + str(round(text_tb.sentiment.subjectivity, 3))) 517 | 518 | # output sentiment 519 | print("Sentiment (url): " + str(sentiment_url)) 520 | print("Sentiment (algorithm): " + str(sentiment)) 521 | print("Overall sentiment (textblob): ", text_tb.sentiment) 522 | print("Overall sentiment (vader): ", text_vs) 523 | print("sentence was rated as ", round(text_vs['neg']*100, 3), "% Negative") 524 | print("sentence was rated as ", round(text_vs['neu']*100, 3), "% Neutral") 525 | print("sentence was rated as ", round(text_vs['pos']*100, 3), "% Positive") 526 | print("************") 527 | 528 | return polarity, text_tb.sentiment.subjectivity, sentiment 529 | 530 | 531 | def tweeklink_sentiment_analysis(url): 532 | # get text summary of tweek link web page and run sentiment analysis on it 533 | try: 534 | logger.info('Following tweet link %s to get sentiment..' % url) 535 | article = Article(url) 536 | article.download() 537 | article.parse() 538 | # check if twitter web page 539 | if "Tweet with a location" in article.text: 540 | logger.info('Link to Twitter web page, skipping') 541 | return None 542 | article.nlp() 543 | tokens = article.keywords 544 | print("Tweet link nltk tokens:", tokens) 545 | 546 | # check for min token length 547 | if len(tokens) < 5: 548 | logger.info("Tweet link does not contain min. number of tokens, not adding") 549 | return None 550 | # check ignored tokens from config 551 | for t in nltk_tokens_ignored: 552 | if t in tokens: 553 | logger.info("Tweet link contains token from ignore list, not adding") 554 | return None 555 | # check required tokens from config 556 | tokenspass = False 557 | tokensfound = 0 558 | for t in nltk_tokens_required: 559 | if t in tokens: 560 | tokensfound += 1 561 | if tokensfound == nltk_min_tokens: 562 | tokenspass = True 563 | break 564 | if not tokenspass: 565 | logger.info("Tweet link does not contain token from required list or min required, not adding") 566 | return None 567 | 568 | summary = article.summary 569 | if summary == '': 570 | logger.info('No text found in tweet link url web page') 571 | return None 572 | summary_clean = clean_text(summary) 573 | summary_clean = clean_text_sentiment(summary_clean) 574 | print("Tweet link Clean Summary (sentiment): " + summary_clean) 575 | polarity, subjectivity, sentiment = sentiment_analysis(summary_clean) 576 | 577 | return polarity, subjectivity, sentiment 578 | 579 | except ArticleException as e: 580 | logger.warning('Exception: error getting text on Twitter link caused by: %s' % e) 581 | return None 582 | 583 | 584 | def get_twitter_users_from_url(url): 585 | twitter_users = [] 586 | logger.info("Grabbing any twitter users from url %s" % url) 587 | try: 588 | twitter_urls = ("http://twitter.com/", "http://www.twitter.com/", 589 | "https://twitter.com/", "https://www.twitter.com/") 590 | # req_header = {'User-Agent': "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_6) AppleWebKit/604.1.38 (KHTML, like Gecko) Version/11.0 Safari/604.1.38"} 591 | req = requests.get(url) 592 | html = req.text 593 | soup = BeautifulSoup(html, 'html.parser') 594 | html_links = [] 595 | for link in soup.findAll('a'): 596 | html_links.append(link.get('href')) 597 | if html_links: 598 | for link in html_links: 599 | # check if twitter_url in link 600 | parsed_uri = urlparse.urljoin(link, '/') 601 | # get twitter user name from link and add to list 602 | if parsed_uri in twitter_urls and "=" not in link and "?" not in link: 603 | user = link.split('/')[3] 604 | twitter_users.append(u'@' + user) 605 | logger.debug(twitter_users) 606 | except requests.exceptions.RequestException as re: 607 | logger.warning("Requests exception: can't crawl web site caused by: %s" % re) 608 | pass 609 | return twitter_users 610 | 611 | 612 | def get_twitter_users_from_file(file): 613 | # get twitter user ids from text file 614 | twitter_users = [] 615 | logger.info("Grabbing any twitter user ids from file %s" % file) 616 | try: 617 | f = open(file, "rt", encoding='utf-8') 618 | for line in f.readlines(): 619 | u = line.strip() 620 | twitter_users.append(u) 621 | logger.debug(twitter_users) 622 | f.close() 623 | except (IOError, OSError) as e: 624 | logger.warning("Exception: error opening file caused by: %s" % e) 625 | pass 626 | return twitter_users 627 | 628 | 629 | if __name__ == '__main__': 630 | # parse cli args 631 | parser = argparse.ArgumentParser() 632 | parser.add_argument("-i", "--index", metavar="INDEX", default="stocksight", 633 | help="Index name for Elasticsearch (default: stocksight)") 634 | parser.add_argument("-d", "--delindex", action="store_true", 635 | help="Delete existing Elasticsearch index first") 636 | parser.add_argument("-s", "--symbol", metavar="SYMBOL", required=True, 637 | help="Stock symbol you are interesed in searching for, example: TSLA") 638 | parser.add_argument("-k", "--keywords", metavar="KEYWORDS", 639 | help="Use keywords to search for in Tweets instead of feeds. " 640 | "Separated by comma, case insensitive, spaces are ANDs commas are ORs. " 641 | "Example: TSLA,'Elon Musk',Musk,Tesla,SpaceX") 642 | parser.add_argument("-a", "--addtokens", action="store_true", 643 | help="Add nltk tokens required from config to keywords") 644 | parser.add_argument("-u", "--url", metavar="URL", 645 | help="Use twitter users from any links in web page at url") 646 | parser.add_argument("-f", "--file", metavar="FILE", 647 | help="Use twitter user ids from file") 648 | parser.add_argument("-l", "--linksentiment", action="store_true", 649 | help="Follow any link url in tweets and analyze sentiment on web page") 650 | parser.add_argument("-n", "--newsheadlines", action="store_true", 651 | help="Get news headlines instead of Twitter using stock symbol from -s") 652 | parser.add_argument("--frequency", metavar="FREQUENCY", default=120, type=int, 653 | help="How often in seconds to retrieve news headlines (default: 120 sec)") 654 | parser.add_argument("--followlinks", action="store_true", 655 | help="Follow links on news headlines and scrape relevant text from landing page") 656 | parser.add_argument("-w", "--websentiment", action="store_true", 657 | help="Get sentiment results from text processing website") 658 | parser.add_argument("--overridetokensreq", metavar="TOKEN", nargs="+", 659 | help="Override nltk required tokens from config, separate with space") 660 | parser.add_argument("--overridetokensignore", metavar="TOKEN", nargs="+", 661 | help="Override nltk ignore tokens from config, separate with space") 662 | parser.add_argument("-v", "--verbose", action="store_true", 663 | help="Increase output verbosity") 664 | parser.add_argument("--debug", action="store_true", 665 | help="Debug message output") 666 | parser.add_argument("-q", "--quiet", action="store_true", 667 | help="Run quiet with no message output") 668 | parser.add_argument("-V", "--version", action="version", 669 | version="stocksight v%s" % STOCKSIGHT_VERSION, 670 | help="Prints version and exits") 671 | args = parser.parse_args() 672 | 673 | # set up logging 674 | logger = logging.getLogger('stocksight') 675 | logger.setLevel(logging.INFO) 676 | eslogger = logging.getLogger('elasticsearch') 677 | eslogger.setLevel(logging.WARNING) 678 | tweepylogger = logging.getLogger('tweepy') 679 | tweepylogger.setLevel(logging.INFO) 680 | requestslogger = logging.getLogger('requests') 681 | requestslogger.setLevel(logging.INFO) 682 | logging.addLevelName( 683 | logging.INFO, "\033[1;32m%s\033[1;0m" 684 | % logging.getLevelName(logging.INFO)) 685 | logging.addLevelName( 686 | logging.WARNING, "\033[1;31m%s\033[1;0m" 687 | % logging.getLevelName(logging.WARNING)) 688 | logging.addLevelName( 689 | logging.ERROR, "\033[1;41m%s\033[1;0m" 690 | % logging.getLevelName(logging.ERROR)) 691 | logging.addLevelName( 692 | logging.DEBUG, "\033[1;33m%s\033[1;0m" 693 | % logging.getLevelName(logging.DEBUG)) 694 | logformatter = '%(asctime)s [%(levelname)s][%(name)s] %(message)s' 695 | loglevel = logging.INFO 696 | logging.basicConfig(format=logformatter, level=loglevel) 697 | if args.verbose: 698 | logger.setLevel(logging.INFO) 699 | eslogger.setLevel(logging.INFO) 700 | tweepylogger.setLevel(logging.INFO) 701 | requestslogger.setLevel(logging.INFO) 702 | if args.debug: 703 | logger.setLevel(logging.DEBUG) 704 | eslogger.setLevel(logging.DEBUG) 705 | tweepylogger.setLevel(logging.DEBUG) 706 | requestslogger.setLevel(logging.DEBUG) 707 | if args.quiet: 708 | logger.disabled = True 709 | eslogger.disabled = True 710 | tweepylogger.disabled = True 711 | requestslogger.disabled = True 712 | 713 | # print banner 714 | if not args.quiet: 715 | c = randint(1, 4) 716 | if c == 1: 717 | color = '31m' 718 | elif c == 2: 719 | color = '32m' 720 | elif c == 3: 721 | color = '33m' 722 | elif c == 4: 723 | color = '35m' 724 | 725 | banner = """\033[%s 726 | _ _ 727 | _| |_ _ _ _| |_ _ _ _ 728 | | __| |_ ___ ___| |_| __|_|___| |_| |_ 729 | |__ | _| . | _| '_|__ | | . | | _| 730 | |_ _|_| |___|___|_,_|_ _|_|_ |_|_|_| 731 | |_| |_| |___| 732 | :) = +$ :( = -$ v%s 733 | https://github.com/shirosaidev/stocksight 734 | \033[0m""" % (color, STOCKSIGHT_VERSION) 735 | print(banner + '\n') 736 | 737 | # create instance of elasticsearch 738 | es = Elasticsearch(hosts=[{'host': elasticsearch_host, 'port': elasticsearch_port}], 739 | http_auth=(elasticsearch_user, elasticsearch_password)) 740 | 741 | # set up elasticsearch mappings and create index 742 | mappings = { 743 | "mappings": { 744 | "tweet": { 745 | "properties": { 746 | "author": { 747 | "type": "string", 748 | "fields": { 749 | "keyword": { 750 | "type": "keyword" 751 | } 752 | } 753 | }, 754 | "location": { 755 | "type": "string", 756 | "fields": { 757 | "keyword": { 758 | "type": "keyword" 759 | } 760 | } 761 | }, 762 | "language": { 763 | "type": "string", 764 | "fields": { 765 | "keyword": { 766 | "type": "keyword" 767 | } 768 | } 769 | }, 770 | "friends": { 771 | "type": "long" 772 | }, 773 | "followers": { 774 | "type": "long" 775 | }, 776 | "statuses": { 777 | "type": "long" 778 | }, 779 | "date": { 780 | "type": "date" 781 | }, 782 | "message": { 783 | "type": "string", 784 | "fields": { 785 | "english": { 786 | "type": "string", 787 | "analyzer": "english" 788 | }, 789 | "keyword": { 790 | "type": "keyword" 791 | } 792 | } 793 | }, 794 | "tweet_id": { 795 | "type": "long" 796 | }, 797 | "polarity": { 798 | "type": "float" 799 | }, 800 | "subjectivity": { 801 | "type": "float" 802 | }, 803 | "sentiment": { 804 | "type": "string", 805 | "fields": { 806 | "keyword": { 807 | "type": "keyword" 808 | } 809 | } 810 | } 811 | } 812 | }, 813 | "newsheadline": { 814 | "properties": { 815 | "date": { 816 | "type": "date" 817 | }, 818 | "location": { 819 | "type": "string", 820 | "fields": { 821 | "keyword": { 822 | "type": "keyword" 823 | } 824 | } 825 | }, 826 | "message": { 827 | "type": "string", 828 | "fields": { 829 | "english": { 830 | "type": "string", 831 | "analyzer": "english" 832 | }, 833 | "keyword": { 834 | "type": "keyword" 835 | } 836 | } 837 | }, 838 | "polarity": { 839 | "type": "float" 840 | }, 841 | "subjectivity": { 842 | "type": "float" 843 | }, 844 | "sentiment": { 845 | "type": "string", 846 | "fields": { 847 | "keyword": { 848 | "type": "keyword" 849 | } 850 | } 851 | } 852 | } 853 | } 854 | } 855 | } 856 | 857 | if args.delindex: 858 | logger.info('Deleting existing Elasticsearch index ' + args.index) 859 | es.indices.delete(index=args.index, ignore=[400, 404]) 860 | 861 | logger.info('Creating new Elasticsearch index or using existing ' + args.index) 862 | es.indices.create(index=args.index, body=mappings, ignore=[400, 404]) 863 | 864 | # check if we need to override any tokens 865 | if args.overridetokensreq: 866 | nltk_tokens_required = tuple(args.overridetokensreq) 867 | if args.overridetokensignore: 868 | nltk_tokens_ignored = tuple(args.overridetokensignore) 869 | 870 | # are we grabbing news headlines from yahoo finance or twitter 871 | if args.newsheadlines: 872 | try: 873 | url = "https://finance.yahoo.com/quote/%s/?p=%s" % (args.symbol, args.symbol) 874 | 875 | logger.info('NLTK tokens required: ' + str(nltk_tokens_required)) 876 | logger.info('NLTK tokens ignored: ' + str(nltk_tokens_ignored)) 877 | logger.info("Scraping news for %s from %s ..." % (args.symbol, url)) 878 | 879 | # create instance of NewsHeadlineListener 880 | newslistener = NewsHeadlineListener(url, args.frequency) 881 | except KeyboardInterrupt: 882 | print("Ctrl-c keyboard interrupt, exiting...") 883 | sys.exit(0) 884 | 885 | else: 886 | # create instance of the tweepy tweet stream listener 887 | tweetlistener = TweetStreamListener() 888 | 889 | # set twitter keys/tokens 890 | auth = OAuthHandler(consumer_key, consumer_secret) 891 | auth.set_access_token(access_token, access_token_secret) 892 | api = API(auth) 893 | 894 | # create instance of the tweepy stream 895 | stream = Stream(auth, tweetlistener) 896 | 897 | # grab any twitter users from links in web page at url 898 | if args.url: 899 | twitter_users = get_twitter_users_from_url(args.url) 900 | if len(twitter_users) > 0: 901 | twitter_feeds = twitter_users 902 | else: 903 | logger.info("No twitter users found in links on web page, exiting") 904 | sys.exit(1) 905 | 906 | # grab twitter users from file 907 | if args.file: 908 | twitter_users = get_twitter_users_from_file(args.file) 909 | if len(twitter_users) > 0: 910 | useridlist = twitter_users 911 | else: 912 | logger.info("No twitter users found in file, exiting") 913 | sys.exit(1) 914 | elif args.keywords is None: 915 | # build user id list from user names 916 | logger.info("Looking up Twitter user ids from usernames... (use -f twitteruserids.txt for cached user ids)") 917 | useridlist = [] 918 | while True: 919 | for u in twitter_feeds: 920 | try: 921 | # get user id from screen name using twitter api 922 | user = api.get_user(screen_name=u) 923 | uid = str(user.id) 924 | if uid not in useridlist: 925 | useridlist.append(uid) 926 | time.sleep(randrange(2, 5)) 927 | except TweepError as te: 928 | # sleep a bit in case twitter suspends us 929 | logger.warning("Tweepy exception: twitter api error caused by: %s" % te) 930 | logger.info("Sleeping for a random amount of time and retrying...") 931 | time.sleep(randrange(2,30)) 932 | continue 933 | except KeyboardInterrupt: 934 | logger.info("Ctrl-c keyboard interrupt, exiting...") 935 | stream.disconnect() 936 | sys.exit(0) 937 | break 938 | 939 | if len(useridlist) > 0: 940 | logger.info('Writing twitter user ids to text file %s' % twitter_users_file) 941 | try: 942 | f = open(twitter_users_file, "wt", encoding='utf-8') 943 | for i in useridlist: 944 | line = str(i) + "\n" 945 | if type(line) is bytes: 946 | line = line.decode('utf-8') 947 | f.write(line) 948 | f.close() 949 | except (IOError, OSError) as e: 950 | logger.warning("Exception: error writing to file caused by: %s" % e) 951 | pass 952 | except Exception as e: 953 | raise 954 | 955 | try: 956 | # search twitter for keywords 957 | logger.info('Stock symbol: ' + str(args.symbol)) 958 | logger.info('NLTK tokens required: ' + str(nltk_tokens_required)) 959 | logger.info('NLTK tokens ignored: ' + str(nltk_tokens_ignored)) 960 | logger.info('Listening for Tweets (ctrl-c to exit)...') 961 | if args.keywords is None: 962 | logger.info('No keywords entered, following Twitter users...') 963 | logger.info('Twitter Feeds: ' + str(twitter_feeds)) 964 | logger.info('Twitter User Ids: ' + str(useridlist)) 965 | stream.filter(follow=useridlist, languages=['en']) 966 | else: 967 | # keywords to search on twitter 968 | # add keywords to list 969 | keywords = args.keywords.split(',') 970 | if args.addtokens: 971 | # add tokens to keywords to list 972 | for f in nltk_tokens_required: 973 | keywords.append(f) 974 | logger.info('Searching Twitter for keywords...') 975 | logger.info('Twitter keywords: ' + str(keywords)) 976 | stream.filter(track=keywords, languages=['en']) 977 | except TweepError as te: 978 | logger.debug("Tweepy Exception: Failed to get tweets caused by: %s" % te) 979 | except KeyboardInterrupt: 980 | print("Ctrl-c keyboard interrupt, exiting...") 981 | stream.disconnect() 982 | sys.exit(0) 983 | -------------------------------------------------------------------------------- /startup.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | echo "*******************************************************" 4 | echo 5 | cat << EndOfBanner 6 | _ _ 7 | _| |_ _ _ _| |_ _ _ _ 8 | | __| |_ ___ ___| |_| __|_|___| |_| |_ 9 | |__ | _| . | _| '_|__ | | . | | _| 10 | |_ _|_| |___|___|_,_|_ _|_|_ |_|_|_| 11 | |_| |_| |___| 12 | :) = +$ :( = -$ 13 | GitHub repo https://github.com/shirosaidev/stocksight 14 | 15 | EndOfBanner 16 | 17 | echo "stocksight docker container started" 18 | echo "shell into the container and run python sentiment.py -h" 19 | echo 20 | echo "*******************************************************" 21 | 22 | while true; do 23 | sleep 3600 24 | done 25 | -------------------------------------------------------------------------------- /stockprice.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # -*- coding: utf-8 -*- 3 | """stockprice.py - get stock price from Yahoo and add to 4 | Elasticsearch. 5 | See README.md or https://github.com/shirosaidev/stocksight 6 | for more information. 7 | 8 | Copyright (C) Chris Park 2018-2020 9 | stocksight is released under the Apache 2.0 license. See 10 | LICENSE for the full license text. 11 | """ 12 | 13 | import time 14 | import requests 15 | import re 16 | import argparse 17 | import logging 18 | import sys 19 | from elasticsearch import Elasticsearch 20 | from random import randint 21 | 22 | # import elasticsearch host 23 | from config import elasticsearch_host, elasticsearch_port, elasticsearch_user, elasticsearch_password 24 | 25 | from sentiment import STOCKSIGHT_VERSION 26 | __version__ = STOCKSIGHT_VERSION 27 | 28 | # url to fetch stock price from, SYMBOL will be replaced with symbol from cli args 29 | url = "https://query1.finance.yahoo.com/v8/finance/chart/SYMBOL?region=US&lang=en-US&includePrePost=false&interval=2m&range=5d&corsDomain=finance.yahoo.com&.tsrc=finance" 30 | 31 | # create instance of elasticsearch 32 | es = Elasticsearch(hosts=[{'host': elasticsearch_host, 'port': elasticsearch_port}], 33 | http_auth=(elasticsearch_user, elasticsearch_password)) 34 | 35 | class GetStock: 36 | 37 | def get_price(self, url, symbol): 38 | import re 39 | 40 | while True: 41 | 42 | logger.info("Grabbing stock data for symbol %s..." % symbol) 43 | 44 | try: 45 | 46 | # add stock symbol to url 47 | url = re.sub("SYMBOL", symbol, url) 48 | # get stock data (json) from url 49 | try: 50 | r = requests.get(url) 51 | data = r.json() 52 | except (requests.HTTPError, requests.ConnectionError, requests.ConnectTimeout) as re: 53 | logger.error("Exception: exception getting stock data from url caused by %s" % re) 54 | raise 55 | logger.debug(data) 56 | # build dict to store stock info 57 | try: 58 | D = {} 59 | D['symbol'] = symbol 60 | D['last'] = data['chart']['result'][0]['indicators']['quote'][0]['close'][-1] 61 | if D['last'] is None: 62 | D['last'] = data['chart']['result'][0]['indicators']['quote'][0]['close'][-2] 63 | D['date'] = time.strftime('%Y-%m-%dT%H:%M:%S', time.gmtime()) # time now in gmt (utc) 64 | try: 65 | D['change'] = (data['chart']['result'][0]['indicators']['quote'][0]['close'][-1] - 66 | data['chart']['result'][0]['indicators']['quote'][0]['close'][-2]) / \ 67 | data['chart']['result'][0]['indicators']['quote'][0]['close'][-2] * 100 68 | except TypeError: 69 | D['change'] = (data['chart']['result'][0]['indicators']['quote'][0]['close'][-2] - 70 | data['chart']['result'][0]['indicators']['quote'][0]['close'][-3]) / \ 71 | data['chart']['result'][0]['indicators']['quote'][0]['close'][-3] * 100 72 | pass 73 | D['high'] = data['chart']['result'][0]['indicators']['quote'][0]['high'][-1] 74 | if D['high'] is None: 75 | D['high'] = data['chart']['result'][0]['indicators']['quote'][0]['high'][-2] 76 | D['low'] = data['chart']['result'][0]['indicators']['quote'][0]['low'][-1] 77 | if D['low'] is None: 78 | D['low'] = data['chart']['result'][0]['indicators']['quote'][0]['low'][-2] 79 | D['vol'] = data['chart']['result'][0]['indicators']['quote'][0]['volume'][-1] 80 | if D['vol'] is None: 81 | D['vol'] = data['chart']['result'][0]['indicators']['quote'][0]['volume'][-2] 82 | logger.debug(D) 83 | except KeyError as e: 84 | logger.error("Exception: exception getting stock data caused by %s" % e) 85 | raise 86 | 87 | # check before adding to ES 88 | if D['last'] is not None and D['high'] is not None and D['low'] is not None: 89 | logger.info("Adding stock data to Elasticsearch...") 90 | # add stock price info to elasticsearch 91 | es.index(index=args.index, 92 | doc_type="stock", 93 | body={"symbol": D['symbol'], 94 | "price_last": D['last'], 95 | "date": D['date'], 96 | "change": D['change'], 97 | "price_high": D['high'], 98 | "price_low": D['low'], 99 | "vol": D['vol'] 100 | }) 101 | else: 102 | logger.warning("Some stock data had null values, not adding to Elasticsearch") 103 | 104 | except Exception as e: 105 | logger.error("Exception: can't get stock data, trying again later, reason is %s" % e) 106 | pass 107 | 108 | logger.info("Will get stock data again in %s sec..." % args.frequency) 109 | time.sleep(args.frequency) 110 | 111 | 112 | if __name__ == '__main__': 113 | 114 | # parse cli args 115 | parser = argparse.ArgumentParser() 116 | parser.add_argument("-i", "--index", metavar="INDEX", default="stocksight", 117 | help="Index name for Elasticsearch (default: stocksight)") 118 | parser.add_argument("-d", "--delindex", action="store_true", 119 | help="Delete existing Elasticsearch index first") 120 | parser.add_argument("-s", "--symbol", metavar="SYMBOL", 121 | help="Stock symbol to use, example: TSLA") 122 | parser.add_argument("-f", "--frequency", metavar="FREQUENCY", default=120, type=int, 123 | help="How often in seconds to retrieve stock data (default: 120 sec)") 124 | parser.add_argument("-v", "--verbose", action="store_true", 125 | help="Increase output verbosity") 126 | parser.add_argument("--debug", action="store_true", 127 | help="Debug message output") 128 | parser.add_argument("-q", "--quiet", action="store_true", 129 | help="Run quiet with no message output") 130 | parser.add_argument("-V", "--version", action="version", 131 | version="stocksight v%s" % STOCKSIGHT_VERSION, 132 | help="Prints version and exits") 133 | args = parser.parse_args() 134 | 135 | # set up logging 136 | logger = logging.getLogger('stocksight') 137 | logger.setLevel(logging.INFO) 138 | eslogger = logging.getLogger('elasticsearch') 139 | eslogger.setLevel(logging.WARNING) 140 | requestslogger = logging.getLogger('requests') 141 | requestslogger.setLevel(logging.WARNING) 142 | logging.addLevelName( 143 | logging.INFO, "\033[1;32m%s\033[1;0m" 144 | % logging.getLevelName(logging.INFO)) 145 | logging.addLevelName( 146 | logging.WARNING, "\033[1;31m%s\033[1;0m" 147 | % logging.getLevelName(logging.WARNING)) 148 | logging.addLevelName( 149 | logging.ERROR, "\033[1;41m%s\033[1;0m" 150 | % logging.getLevelName(logging.ERROR)) 151 | logging.addLevelName( 152 | logging.DEBUG, "\033[1;33m%s\033[1;0m" 153 | % logging.getLevelName(logging.DEBUG)) 154 | logformatter = '%(asctime)s [%(levelname)s][%(name)s] %(message)s' 155 | loglevel = logging.INFO 156 | logging.basicConfig(format=logformatter, level=loglevel) 157 | if args.verbose: 158 | logger.setLevel(logging.INFO) 159 | eslogger.setLevel(logging.INFO) 160 | requestslogger.setLevel(logging.INFO) 161 | if args.debug: 162 | logger.setLevel(logging.DEBUG) 163 | eslogger.setLevel(logging.DEBUG) 164 | requestslogger.setLevel(logging.DEBUG) 165 | if args.quiet: 166 | logger.disabled = True 167 | eslogger.disabled = True 168 | requestslogger.disabled = True 169 | 170 | # print banner 171 | if not args.quiet: 172 | c = randint(1, 4) 173 | if c == 1: 174 | color = '31m' 175 | elif c == 2: 176 | color = '32m' 177 | elif c == 3: 178 | color = '33m' 179 | elif c == 4: 180 | color = '35m' 181 | 182 | banner = """\033[%s 183 | _ _ 184 | _| |_ _ _ _| |_ _ _ _ 185 | | __| |_ ___ ___| |_| __|_|___| |_| |_ 186 | |__ | _| . | _| '_|__ | | . | | _| 187 | |_ _|_| |___|___|_,_|_ _|_|_ |_|_|_| 188 | |_| |_| |___| 189 | :) = +$ :( = -$ v%s 190 | https://github.com/shirosaidev/stocksight 191 | \033[0m""" % (color, STOCKSIGHT_VERSION) 192 | print(banner + '\n') 193 | 194 | # set up elasticsearch mappings and create index 195 | mappings = { 196 | "mappings": { 197 | "stock": { 198 | "properties": { 199 | "symbol": { 200 | "type": "keyword" 201 | }, 202 | "price_last": { 203 | "type": "float" 204 | }, 205 | "date": { 206 | "type": "date" 207 | }, 208 | "change": { 209 | "type": "float" 210 | }, 211 | "price_high": { 212 | "type": "float" 213 | }, 214 | "price_low": { 215 | "type": "float" 216 | }, 217 | "vol": { 218 | "type": "integer" 219 | } 220 | } 221 | } 222 | } 223 | } 224 | 225 | if args.symbol is None: 226 | print("No stock symbol, see -h for help.") 227 | sys.exit(1) 228 | 229 | if args.delindex: 230 | logger.info('Deleting existing Elasticsearch index ' + args.index) 231 | es.indices.delete(index=args.index, ignore=[400, 404]) 232 | 233 | logger.info('Creating new Elasticsearch index or using existing ' + args.index) 234 | es.indices.create(index=args.index, body=mappings, ignore=[400, 404]) 235 | 236 | # create instance of GetStock 237 | stockprice = GetStock() 238 | 239 | try: 240 | # get stock price 241 | stockprice.get_price(symbol=args.symbol, url=url) 242 | except Exception as e: 243 | logger.warning("Exception: Failed to get stock data caused by: %s" % e) 244 | except KeyboardInterrupt: 245 | print("Ctrl-c keyboard interrupt, exiting...") 246 | sys.exit(0) 247 | -------------------------------------------------------------------------------- /twitteruserids.txt: -------------------------------------------------------------------------------- 1 | 44196397 2 | 20402945 3 | 44060322 4 | 18193185 5 | 2884771 6 | 2467791 7 | 15897179 8 | 28571999 9 | 28164923 10 | 455309376 11 | 1754641 12 | 21328656 13 | 1357098067 14 | 14216123 15 | 14096763 16 | 861619895485726722 17 | 1534167900 18 | 22522178 19 | 71567590 20 | 168679374 21 | 16228398 22 | 33216611 23 | 332617373 24 | 426159377 25 | 60783724 26 | 253167239 27 | 553713584 28 | 40129171 29 | 714051110 30 | 101002059 31 | 5695632 32 | 807095 33 | --------------------------------------------------------------------------------