├── .gitignore ├── LICENSE ├── README.md ├── requirements.txt ├── settings.txt └── src ├── __pycache__ └── whatsapp_scrapper.cpython-39.pyc ├── main.py └── whatsapp_scrapper.py /.gitignore: -------------------------------------------------------------------------------- 1 | env/ 2 | geckodriver.log 3 | .vscode 4 | mysettings.txt -------------------------------------------------------------------------------- /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 2018 Jose Manuel Gama Estrada 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 | # :speech_balloon: WhatsApp-Scraping 2 | 3 | Python script to get WhatsApp information from WhatsApp Web 4 | 5 | # Requirements 6 | 7 | All the libraries that we are going to use are in the [requirements.txt](requirements.txt) file. 8 | You can install it with PIP in the terminal with: 9 | 10 | ``` 11 | sudo pip install -r requirements.txt 12 | ``` 13 | 14 | In order to make this project work you need to have a profile in your browser where you already scanned the QR with your account then we are going to use that account for launching the Selenium driver. 15 | 16 | ## Selenium 17 | 18 | Selenium requires a driver to interface with the chosen browser. Firefox, for example, requires geckodriver, which needs to be installed before the below examples can be run. Make sure it’s in your PATH, e. g., place it in /usr/bin or /usr/local/bin. 19 | 20 | Failure to observe this step will give you an error selenium.common.exceptions.WebDriverException: Message: ‘geckodriver’ executable needs to be in PATH. 21 | 22 | Other supported browsers will have their own drivers available. Links to some of the more popular browser drivers follow. 23 | 24 | - [Chrome](https://chromedriver.chromium.org/downloads) 25 | - [Edge](https://developer.microsoft.com/en-us/microsoft-edge/tools/webdriver/) 26 | - [Firefox](https://github.com/mozilla/geckodriver/releases) 27 | - [Safari](https://webkit.org/blog/6900/webdriver-support-in-safari-10/) 28 | 29 | > For more information you can go to the [Selenium Website](http://selenium-python.readthedocs.io/installation.html) at the installation section. 30 | 31 | ### Chrome driver 32 | 33 | #### Windows 34 | 35 | For Windows we recommend that you download the [Chrome driver](https://chromedriver.chromium.org/downloads) and save it in your chrome directory _(default path: C:\Program Files (x86)\Google\Chrome)_. 36 | 37 | In the requirements.txt file you can set the path to the chrome driver DRIVER_PATH = C:\Program Files (x86)\Google\Chrome\chromedriver. With this configuration the script will know where to find the driver. 38 | 39 | # Settings 40 | 41 | **AT THIS MOMENT THE PROJECT ONLY WORKS WITH FIREFOX AND CHROME** 42 | 43 | ## Browser Profile `FIREFOX_PATH` 44 | 45 | You need to setup your configuration in the [settings.txt](settings.txt) file. 46 | In this file you need to specify the profile of your browser where you already scan the QR whit your WhatsaApp account 47 | 48 |

49 | 50 |

51 | 52 | For example we are using the default Firefox profile so we open Firefox and go to https://web.whatsapp.com/ then we scan our QR to login then we can close Firefox and go to search for our profile file that we have in `/home/user/.mozilla/firefox/xxxxxxxx.default`, now that we localized our file we add the direction to our [settings.txt](settings.txt) file in the FIREFOX_PATH 53 | 54 | ## Browser Profile `CHROME_PATH` 55 | 56 | For Chrome you can open Chrome browser, in the navigation bar you can go to `chrome://version/` and copy the **Profile path** to set it in the [settings.txt](settings.txt) file in the BROWSER_PATH 57 | -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JMGama/WhatsApp-Scraping/8411b988c1e690e3be908372e32562adf45277e8/requirements.txt -------------------------------------------------------------------------------- /settings.txt: -------------------------------------------------------------------------------- 1 | [config] 2 | BROWSER = firefox or chrome 3 | BROWSER_PATH = /home/user/.mozilla/firefox/xxxxxxxx.default or /home/user/.config/google-chrome/Default (this paths are for Linux) 4 | NAME = person 5 | PAGE = https://web.whatsapp.com/ 6 | DRIVER_PATH = /path/to/chromedriver 7 | -------------------------------------------------------------------------------- /src/__pycache__/whatsapp_scrapper.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/JMGama/WhatsApp-Scraping/8411b988c1e690e3be908372e32562adf45277e8/src/__pycache__/whatsapp_scrapper.cpython-39.pyc -------------------------------------------------------------------------------- /src/main.py: -------------------------------------------------------------------------------- 1 | import configparser 2 | import time 3 | 4 | from whatsapp_scrapper import WhatsappScrapper 5 | 6 | 7 | def load_settings(): 8 | """ 9 | Loading and assigning global variables from our settings.txt file 10 | """ 11 | config_parser = configparser.RawConfigParser() 12 | config_file_path = 'settings.txt' 13 | config_parser.read(config_file_path) 14 | 15 | browser = config_parser.get('config', 'BROWSER') 16 | browser_path = config_parser.get('config', 'BROWSER_PATH') 17 | name = config_parser.get('config', 'NAME') 18 | page = config_parser.get('config', 'PAGE') 19 | driver_path = config_parser.get('config', 'DRIVER_PATH') 20 | 21 | settings = { 22 | 'browser': browser, 23 | 'browser_path': browser_path, 24 | 'name': name, 25 | 'page': page, 26 | 'driver_path': driver_path 27 | } 28 | return settings 29 | 30 | 31 | def main(): 32 | """ 33 | Loading all the configuration and opening the website 34 | (Browser profile where whatsapp web is already scanned) 35 | """ 36 | settings = load_settings() 37 | scrapper = WhatsappScrapper( 38 | settings['page'], settings['browser'], settings['browser_path'], settings['driver_path']) 39 | 40 | if scrapper.open_conversation(settings['name']): 41 | # scrapper.send_message("hola") 42 | previous_in_message = None 43 | while True: 44 | last_in_message, message_emojis, quote, quote_emojis, quote_by = scrapper.read_last_in_message() 45 | 46 | if previous_in_message != last_in_message: 47 | print(last_in_message, message_emojis, 48 | quote, quote_emojis, quote_by) 49 | previous_in_message = last_in_message 50 | 51 | time.sleep(1) 52 | 53 | 54 | if __name__ == '__main__': 55 | main() 56 | -------------------------------------------------------------------------------- /src/whatsapp_scrapper.py: -------------------------------------------------------------------------------- 1 | """ 2 | Importing the libraries that we are going to use 3 | for loading the settings file and scraping the website 4 | """ 5 | 6 | from selenium import webdriver 7 | from selenium.common.exceptions import (NoSuchElementException, 8 | StaleElementReferenceException) 9 | from selenium.webdriver.common.by import By 10 | from selenium.webdriver.support import expected_conditions as EC 11 | from selenium.webdriver.support.ui import WebDriverWait 12 | 13 | 14 | class WhatsappScrapper(): 15 | def __init__(self, page, browser, browser_path, driver_path): 16 | self.page = page 17 | self.browser = browser 18 | self.browser_path = browser_path 19 | self.driver_path = driver_path 20 | self.driver = self.load_driver() 21 | 22 | # Open the web page with the given browser 23 | self.driver.get(self.page) 24 | 25 | def load_driver(self): 26 | """ 27 | Load the Selenium driver depending on the browser 28 | (Edge and Safari are not running yet) 29 | """ 30 | driver = None 31 | if self.browser == 'firefox': 32 | firefox_profile = webdriver.FirefoxProfile( 33 | self.browser_path) 34 | driver = webdriver.Firefox(firefox_profile) 35 | elif self.browser == 'chrome': 36 | chrome_options = webdriver.ChromeOptions() 37 | if self.browser_path: 38 | chrome_options.add_argument('user-data-dir=' + 39 | self.browser_path) 40 | driver = webdriver.Chrome(self.driver_path, options=chrome_options) 41 | elif self.browser == 'safari': 42 | pass 43 | elif self.browser == 'edge': 44 | pass 45 | 46 | return driver 47 | 48 | def open_conversation(self, name): 49 | """ 50 | Function that search the specified user by the 'name' and opens the conversation. 51 | """ 52 | 53 | while True: 54 | for chatter in self.driver.find_elements_by_xpath("//div[@id='pane-side']/div/div/div/div"): 55 | chatter_path = ".//span[@title='{}']".format( 56 | name) 57 | 58 | # Wait until the chatter box is loaded in DOM 59 | try: 60 | WebDriverWait(self.driver, 10).until( 61 | EC.presence_of_element_located( 62 | (By.XPATH, "//span[contains(@title,'{}')]".format( 63 | name))) 64 | ) 65 | except StaleElementReferenceException: 66 | WebDriverWait(self.driver, 10).until( 67 | EC.presence_of_element_located( 68 | (By.XPATH, "//span[contains(@title,'{}')]".format( 69 | name))) 70 | ) 71 | 72 | try: 73 | chatter_name = chatter.find_element_by_xpath( 74 | chatter_path).text 75 | if chatter_name == name: 76 | chatter.find_element_by_xpath( 77 | ".//div/div").click() 78 | return True 79 | except Exception as e: 80 | pass 81 | 82 | def read_last_in_message(self): 83 | """ 84 | Reading the last message that you got in from the chatter 85 | """ 86 | message = "" 87 | message_emojis = [] 88 | quote = "" 89 | quote_emojis = [] 90 | quote_by = "" 91 | 92 | for messages in self.driver.find_elements_by_xpath( 93 | "//div[contains(@class,'message-in')]"): 94 | try: 95 | 96 | # Get message 97 | message_container = messages.find_element_by_xpath( 98 | ".//div[@class='copyable-text']") 99 | 100 | message = message_container.find_element_by_xpath( 101 | ".//span[contains(@class,'copyable-text')]" 102 | ).text 103 | 104 | # Get emojis 105 | for emoji in message_container.find_elements_by_xpath( 106 | ".//img[contains(@class,'copyable-text')]" 107 | ): 108 | message_emojis.append( 109 | emoji.get_attribute("data-plain-text")) 110 | 111 | # Get quoted message 112 | quote_container = message_container.find_element_by_xpath( 113 | ".//span[contains(@class,'quoted-mention')]") 114 | 115 | quote = quote_container.text 116 | 117 | quote_by = message_container.find_element_by_xpath( 118 | ".//span[contains(@class,'i0jNr')]").text 119 | 120 | # Get quoted emojis 121 | for emoji in quote_container.find_elements_by_xpath( 122 | ".//img[contains(@class,'emoji')]" 123 | ): 124 | quote_emojis.append(emoji.get_attribute("alt")) 125 | 126 | except NoSuchElementException as e: # In case there are only emojis in the message 127 | try: 128 | message_container = messages.find_element_by_xpath( 129 | ".//div[contains(@class,'copyable-text')]") 130 | 131 | for emoji in message_container.find_elements_by_xpath( 132 | ".//img[contains(@class,'copyable-text')]" 133 | ): 134 | message_emojis.append( 135 | emoji.get_attribute("data-plain-text")) 136 | except NoSuchElementException: 137 | pass 138 | 139 | return message, message_emojis, quote, quote_emojis, quote_by 140 | 141 | def send_message(self, text): 142 | """ 143 | Send a message to the chatter. 144 | You need to open a conversation with open_conversation() 145 | before you can use this function. 146 | """ 147 | 148 | input_text = self.driver.find_element_by_xpath( 149 | "//div[@id='main']/footer/div/div[2]/div/div[@contenteditable='true']") 150 | 151 | input_text.click() 152 | input_text.send_keys(text) 153 | 154 | send_button = self.driver.find_element_by_xpath( 155 | "//div[@id='main']/footer/div/div[3]/button") 156 | send_button.click() 157 | 158 | return True 159 | --------------------------------------------------------------------------------