├── .gitignore
├── .idea
    ├── .gitignore
    ├── Instagram-Comments-Scraper.iml
    ├── inspectionProfiles
    │   └── profiles_settings.xml
    ├── misc.xml
    ├── modules.xml
    └── vcs.xml
├── LICENSE.md
├── README.md
├── __pycache__
    └── excel_exporter.cpython-36.pyc
├── _config.yml
├── excel_exporter.py
├── requirements.txt
└── scraper.py


/.gitignore:
--------------------------------------------------------------------------------
1 | *.pyc
2 | *.xlsx
3 | __pycache__/
4 | ~lock.*
5 | chromedriver_linux64.zip
6 | .venv
7 | .idea
8 | 


--------------------------------------------------------------------------------
/.idea/.gitignore:
--------------------------------------------------------------------------------
1 | 
2 | # Default ignored files
3 | /workspace.xml


--------------------------------------------------------------------------------
/.idea/Instagram-Comments-Scraper.iml:
--------------------------------------------------------------------------------
 1 | <?xml version="1.0" encoding="UTF-8"?>
 2 | <module type="PYTHON_MODULE" version="4">
 3 |   <component name="NewModuleRootManager">
 4 |     <content url="file://$MODULE_DIR$" />
 5 |     <orderEntry type="inheritedJdk" />
 6 |     <orderEntry type="sourceFolder" forTests="false" />
 7 |   </component>
 8 |   <component name="TemplatesService">
 9 |     <option name="TEMPLATE_FOLDERS">
10 |       <list>
11 |         <option value="$MODULE_DIR$/.venv/lib/python3.8/site-packages/pandas/io/formats/templates" />
12 |       </list>
13 |     </option>
14 |   </component>
15 |   <component name="TestRunnerService">
16 |     <option name="PROJECT_TEST_RUNNER" value="Unittests" />
17 |   </component>
18 | </module>


--------------------------------------------------------------------------------
/.idea/inspectionProfiles/profiles_settings.xml:
--------------------------------------------------------------------------------
1 | <component name="InspectionProjectProfileManager">
2 |   <settings>
3 |     <option name="USE_PROJECT_PROFILE" value="false" />
4 |     <version value="1.0" />
5 |   </settings>
6 | </component>


--------------------------------------------------------------------------------
/.idea/misc.xml:
--------------------------------------------------------------------------------
1 | <?xml version="1.0" encoding="UTF-8"?>
2 | <project version="4">
3 |   <component name="JavaScriptSettings">
4 |     <option name="languageLevel" value="ES6" />
5 |   </component>
6 |   <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.8 (Instagram-Comments-Scraper)" project-jdk-type="Python SDK" />
7 | </project>


--------------------------------------------------------------------------------
/.idea/modules.xml:
--------------------------------------------------------------------------------
1 | <?xml version="1.0" encoding="UTF-8"?>
2 | <project version="4">
3 |   <component name="ProjectModuleManager">
4 |     <modules>
5 |       <module fileurl="file://$PROJECT_DIR$/.idea/Instagram-Comments-Scraper.iml" filepath="$PROJECT_DIR$/.idea/Instagram-Comments-Scraper.iml" />
6 |     </modules>
7 |   </component>
8 | </project>


--------------------------------------------------------------------------------
/.idea/vcs.xml:
--------------------------------------------------------------------------------
1 | <?xml version="1.0" encoding="UTF-8"?>
2 | <project version="4">
3 |   <component name="VcsDirectoryMappings">
4 |     <mapping directory="$PROJECT_DIR$" vcs="Git" />
5 |   </component>
6 | </project>


--------------------------------------------------------------------------------
/LICENSE.md:
--------------------------------------------------------------------------------
 1 | MIT License
 2 | 
 3 | Copyright (c) 2018 Agi Maulana
 4 | 
 5 | Permission is hereby granted, free of charge, to any person obtaining a copy
 6 | of this software and associated documentation files (the "Software"), to deal
 7 | in the Software without restriction, including without limitation the rights
 8 | to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
 9 | copies of the Software, and to permit persons to whom the Software is
10 | furnished to do so, subject to the following conditions:
11 | 
12 | The above copyright notice and this permission notice shall be included in all
13 | copies or substantial portions of the Software.
14 | 
15 | THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
16 | IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
17 | FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
18 | AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
19 | LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
20 | OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
21 | SOFTWARE.
22 | 


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
 1 | > I don't actively maintain this repository.
 2 | >
 3 | > 
 4 | > Why this scraper doesn't work on my side?
 5 | > 
 6 | > As I observed on the current Instagram website the website could respond with different elements or pages so this scraper might not work for some people. 
 7 | 
 8 | # Instagram Comments Scraper
 9 | 
10 | ## Installation
11 | 1. Clone:
12 |    `git clone git@github.com:AgiMaulana/Instagram-Comments-Scraper.git`
13 | 
14 |     or `git clone https://github.com/AgiMaulana/Instagram-Comments-Scraper.git`
15 |     
16 |     or download the [zip](https://github.com/AgiMaulana/Instagram-Comments-Scraper/archive/master.zip)
17 |    
18 | 3. Create Virtual Environment (Recommended)<br/> 
19 |     - `pip install virtualenv`
20 |     - `virtualenv .venv`  
21 |     
22 | 4. Activate the virtual environment
23 |     - `source .venv/bin/activate`
24 | 
25 | 5. Install dependencies
26 |     - `pip install -r requirements.txt`
27 | 
28 | 6. Login
29 |     - `username.send_keys ('USER-NAME')` change with your username
30 |     - `password.send_keys('PASSWORD')` change with your password
31 |        - We don't store your password
32 | 
33 | 7. Run 
34 |     - `python scraper.py post-url total-load-more-click`
35 |    
36 |     Change the URL with your post target. <br/>
37 |     For example: `python scraper.py https://www.instagram.com/p/CBHH2KjI6BW/ 5` 
38 |  
39 | 8. Deactivate the virtual environment
40 |     - `deactivate`
41 | 
42 | ## License
43 | This project is under the [MIT License](https://github.com/AgiMaulana/instagram-comments-scraper/blob/master/LICENSE.md)
44 | 


--------------------------------------------------------------------------------
/__pycache__/excel_exporter.cpython-36.pyc:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/AgiMaulana/Instagram-Comments-Scraper/6b6b1a13ae783b45ebae9031aa5b7e9ab6e02363/__pycache__/excel_exporter.cpython-36.pyc


--------------------------------------------------------------------------------
/_config.yml:
--------------------------------------------------------------------------------
1 | theme: jekyll-theme-cayman


--------------------------------------------------------------------------------
/excel_exporter.py:
--------------------------------------------------------------------------------
 1 | import pandas as pd
 2 | from pandas import ExcelWriter
 3 | import os.path
 4 | 
 5 | def export(names, comments):
 6 |     fname = 'comments.xlsx'
 7 |     temp = {}
 8 |     temp_names = []
 9 |     temp_comments = []
10 |     # if os.path.isfile(fname):
11 |     #     saved = pd.read_excel(fname)
12 |     #     temp_names.extend(saved['name'])
13 |     #     temp_comments.extend(saved['comment'])
14 |     # temp_names.extend(names)
15 |     # temp_comments.extend(comments)
16 |     temp.update({'name': names, 'comment': comments})
17 |     df = pd.DataFrame(temp)
18 | 
19 | 
20 | 
21 |     df.to_excel(fname)
22 | 


--------------------------------------------------------------------------------
/requirements.txt:
--------------------------------------------------------------------------------
1 | selenium
2 | pandas
3 | xlrd
4 | openpyxl


--------------------------------------------------------------------------------
/scraper.py:
--------------------------------------------------------------------------------
 1 | from selenium import webdriver
 2 | import time
 3 | import sys
 4 | from selenium.webdriver.common.by import By
 5 | 
 6 | service = webdriver.FirefoxService(executable_path="path_to_geckodriver")
 7 | 
 8 | driver = webdriver.Firefox(service=service)
 9 | 
10 | url="https://www.instagram.com/"
11 | 
12 | driver.get(url) 
13 | 
14 | time.sleep (2)
15 | 
16 | """
17 | On the first project of me which we entered Twitter without using password,we use XPaths of
18 | elements but in Instagram,when we refresh our website,id number of login url changes so we need
19 | to use something different to use that link through Python Selenium. Either we can choose class name
20 | or name selectors to use that.
21 | """
22 | username=driver.find_element(By.NAME,"username")
23 | username.send_keys ('USER-NAME')
24 | 
25 | password =driver.find_element (By.NAME,"password")
26 | password.send_keys('PASSWORD')
27 | password.submit()
28 | 
29 | 
30 | time.sleep(10)
31 | 
32 | 
33 | 
34 | driver.get(sys.argv[1])
35 | 
36 | time.sleep(4)
37 | 
38 | 
39 | 
40 | # load "sys.argv[2]" comments 
41 | try:
42 |     load_more_comment = driver.find_element(By.XPATH,'/html/body/div[2]/div/div/div[2]/div/div/div/div[1]/div[1]/div[2]/section/main/div/div[1]/div/div[2]/div/div[2]/div/div/ul/li/div/button')
43 |     print("Found {}".format(str(load_more_comment)))
44 |     i = 0
45 |     while load_more_comment.is_displayed() and i < int(sys.argv[2]):
46 |         load_more_comment.click()
47 |         time.sleep(7)
48 |         load_more_comment = driver.find_element(By.XPATH,'/html/body/div[2]/div/div/div[2]/div/div/div/div[1]/div[1]/div[2]/section/main/div/div[1]/div/div[2]/div/div[2]/div/div/ul/li/div/button')
49 |         print(i)
50 |         print("Found {}".format(str(load_more_comment)))
51 |         i += 1
52 | except Exception as e:
53 |     print(e)
54 |     pass
55 | 
56 | 
57 | 
58 | user_names = []
59 | user_comments = []
60 | comment = driver.find_elements(By.CLASS_NAME,'_a9ym')
61 | for c in comment:
62 |     container = c.find_element(By.CLASS_NAME,'_a9zr')
63 |     name = container.find_element(By.CLASS_NAME,'_a9zc').text
64 |     content = container.find_element(By.TAG_NAME,'span').text
65 |     content = content.replace('\n', ' ').strip().rstrip()
66 |     user_names.append(name)
67 |     user_comments.append(content)
68 | 
69 | user_names.pop(0)
70 | user_comments.pop(0)
71 | # print(user_names)
72 | # print(user_comments)
73 | import excel_exporter
74 | excel_exporter.export(user_names, user_comments)
75 | 
76 | driver.close()
77 | 


--------------------------------------------------------------------------------