mirror of
https://github.com/bellingcat/facebook-downloader.git
synced 2026-06-11 21:18:31 +03:00
Refactored for pypi
This commit is contained in:
Richard Mwewa
129
.gitignore
vendored
129
.gitignore
vendored
@@ -1,129 +0,0 @@
|
||||
# Byte-compiled / optimized / DLL files
|
||||
__pycache__/
|
||||
*.py[cod]
|
||||
*$py.class
|
||||
|
||||
# C extensions
|
||||
*.so
|
||||
|
||||
# Distribution / packaging
|
||||
.Python
|
||||
build/
|
||||
develop-eggs/
|
||||
dist/
|
||||
downloads/
|
||||
eggs/
|
||||
.eggs/
|
||||
lib/
|
||||
lib64/
|
||||
parts/
|
||||
sdist/
|
||||
var/
|
||||
wheels/
|
||||
pip-wheel-metadata/
|
||||
share/python-wheels/
|
||||
*.egg-info/
|
||||
.installed.cfg
|
||||
*.egg
|
||||
MANIFEST
|
||||
|
||||
# PyInstaller
|
||||
# Usually these files are written by a python script from a template
|
||||
# before PyInstaller builds the exe, so as to inject date/other infos into it.
|
||||
*.manifest
|
||||
*.spec
|
||||
|
||||
# Installer logs
|
||||
pip-log.txt
|
||||
pip-delete-this-directory.txt
|
||||
|
||||
# Unit test / coverage reports
|
||||
htmlcov/
|
||||
.tox/
|
||||
.nox/
|
||||
.coverage
|
||||
.coverage.*
|
||||
.cache
|
||||
nosetests.xml
|
||||
coverage.xml
|
||||
*.cover
|
||||
*.py,cover
|
||||
.hypothesis/
|
||||
.pytest_cache/
|
||||
|
||||
# Translations
|
||||
*.mo
|
||||
*.pot
|
||||
|
||||
# Django stuff:
|
||||
*.log
|
||||
local_settings.py
|
||||
db.sqlite3
|
||||
db.sqlite3-journal
|
||||
|
||||
# Flask stuff:
|
||||
instance/
|
||||
.webassets-cache
|
||||
|
||||
# Scrapy stuff:
|
||||
.scrapy
|
||||
|
||||
# Sphinx documentation
|
||||
docs/_build/
|
||||
|
||||
# PyBuilder
|
||||
target/
|
||||
|
||||
# Jupyter Notebook
|
||||
.ipynb_checkpoints
|
||||
|
||||
# IPython
|
||||
profile_default/
|
||||
ipython_config.py
|
||||
|
||||
# pyenv
|
||||
.python-version
|
||||
|
||||
# pipenv
|
||||
# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
|
||||
# However, in case of collaboration, if having platform-specific dependencies or dependencies
|
||||
# having no cross-platform support, pipenv may install dependencies that don't work, or not
|
||||
# install all needed dependencies.
|
||||
#Pipfile.lock
|
||||
|
||||
# PEP 582; used by e.g. github.com/David-OConnor/pyflow
|
||||
__pypackages__/
|
||||
|
||||
# Celery stuff
|
||||
celerybeat-schedule
|
||||
celerybeat.pid
|
||||
|
||||
# SageMath parsed files
|
||||
*.sage.py
|
||||
|
||||
# Environments
|
||||
.env
|
||||
.venv
|
||||
env/
|
||||
venv/
|
||||
ENV/
|
||||
env.bak/
|
||||
venv.bak/
|
||||
|
||||
# Spyder project settings
|
||||
.spyderproject
|
||||
.spyproject
|
||||
|
||||
# Rope project settings
|
||||
.ropeproject
|
||||
|
||||
# mkdocs documentation
|
||||
/site
|
||||
|
||||
# mypy
|
||||
.mypy_cache/
|
||||
.dmypy.json
|
||||
dmypy.json
|
||||
|
||||
# Pyre type checker
|
||||
.pyre/
|
||||
78
README.md
78
README.md
@@ -1,62 +1,70 @@
|
||||
# Facebook-Downloader
|
||||
A program for downloading Facebook videos
|
||||
A program for downloading Facebook videos, given a video url
|
||||
|
||||
# Installation
|
||||
**1. Clone the project**
|
||||
**Install from PyPI**
|
||||
```
|
||||
git clone https://github.com/rly0nheart/Facebook-Downloader.git
|
||||
pip install facebook-downloader
|
||||
```
|
||||
|
||||
**2. Move to Facebook-Downloader directory**
|
||||
### Note
|
||||
> In order to run the program, You will need to have the FireFox browser installed on your pc
|
||||
> The program is dependent on selenium, so in order to run it, you will have to download and properly setup geckodriver (setup instructions available below)
|
||||
>>
|
||||
|
||||
# Geckodriver setup
|
||||
## Linux
|
||||
**1. Go to the geckodriver [releases page](https://github.com/mozilla/geckodriver/releases/). Find the latest version of the driver for your platform and download it**
|
||||
|
||||
**2. Extract the downloaded file**
|
||||
```
|
||||
cd Facebook-Downloader
|
||||
tar -xvzf geckodriver*
|
||||
```
|
||||
|
||||
**3. Install dependencies**
|
||||
## Note
|
||||
> *This will install tqdm, selenium, and requests*
|
||||
> > *You will need to have Firefox installed to run the program*
|
||||
> > > *For user convenience, the program will come with a geckodriver.exe binary*
|
||||
**3. Make it executable**
|
||||
```
|
||||
pip install -r requirements.txt
|
||||
chmod +x geckodriver
|
||||
```
|
||||
|
||||
**4. Add geckodriver to your system path**
|
||||
```
|
||||
export PATH=$PATH:/path/to/downloaded/geckodriver
|
||||
```
|
||||
|
||||
### Note
|
||||
> If you encounter issues with the above commands, then you should run them as root (with sudo)
|
||||
|
||||
|
||||
## Windows
|
||||
**1. Go to the geckodriver [releases page](https://github.com/mozilla/geckodriver/releases/). Find the geckodriver.exe binary for your platform and download it**
|
||||
|
||||
**2. Move the downloaded executable to** *C:\Users\yourusername\AppData\Local\Programs\Python\Python310*
|
||||
|
||||
### Note
|
||||
> The numbers on the directory 'Python310' will depend on the version of Python you have
|
||||
|
||||
## Mac OS
|
||||
* [Set up Selenium & GeckoDriver (Mac)](https://medium.com/dropout-analytics/selenium-and-geckodriver-on-mac-b411dbfe61bc)
|
||||
|
||||
|
||||
# Usage
|
||||
```
|
||||
python downloader.py <facebook-url>
|
||||
facebook_downloader <video-url>
|
||||
```
|
||||
|
||||
> *Alternatively, you could grant execution permission to the downloader and run it as shown below*
|
||||
|
||||
**1. Grant execution permission**
|
||||
```
|
||||
chmod +x downloader.py
|
||||
```
|
||||
|
||||
**2. Run downloader**
|
||||
```
|
||||
./downloader.py <facebook-url>
|
||||
```
|
||||
|
||||
## Example
|
||||
```
|
||||
python downloader.py https://www.facebook.com/PageName/videos/VideoID
|
||||
```
|
||||
|
||||
## Note
|
||||
> Upon run, the downloader will first check for updates. If found, users will be prompted to download the updates
|
||||
### Note
|
||||
> Upon run, the program will first check for updates. If found, users will be notified about the update
|
||||
|
||||
|
||||
# Optional Arguments
|
||||
| Flag | Description |
|
||||
|---------|:-----------:|
|
||||
| *-A/--audio* | download audio only (coming soon) |
|
||||
| *-o/--output* | output filename |
|
||||
| *-v/--version* | show program's version number and exit |
|
||||
| *-a/--audio* | download file as audio |
|
||||
| *-o/--output* | output file name |
|
||||
|
||||
# Donations
|
||||
If you would like to donate, you could Buy A Coffee for the developer using the button below
|
||||
|
||||
<a href="https://www.buymeacoffee.com/189381184" target="_blank"><img src="https://cdn.buymeacoffee.com/buttons/default-orange.png" alt="Buy Me A Coffee" height="41" width="174"></a>
|
||||
|
||||
Your support will be much appreciated!
|
||||
Your support will be much appreciated!
|
||||
100
downloader.py
100
downloader.py
@@ -1,100 +0,0 @@
|
||||
import time
|
||||
import logging
|
||||
import argparse
|
||||
import requests
|
||||
from tqdm import tqdm
|
||||
from selenium import webdriver
|
||||
from selenium.webdriver.common.by import By
|
||||
from selenium.webdriver.common.keys import Keys
|
||||
from selenium.webdriver.support.ui import WebDriverWait
|
||||
from selenium.webdriver.support import expected_conditions
|
||||
|
||||
|
||||
option = webdriver.FirefoxOptions()
|
||||
option.add_argument('--headless')
|
||||
driver = webdriver.Firefox(options=option)
|
||||
program_version_number = "2022.1.0.0"
|
||||
downloading_url = "https://getfvid.com"
|
||||
update_check_endpoint = "https://api.github.com/repos/rly0nheart/facebook-downloader/releases/latest"
|
||||
|
||||
|
||||
def notice():
|
||||
notice_msg = f"""
|
||||
facebook-downloader {program_version_number} Copyright (C) 2022 Richard Mwewa
|
||||
|
||||
This program is free software: you can redistribute it and/or modify
|
||||
it under the terms of the GNU General Public License as published by
|
||||
the Free Software Foundation, either version 3 of the License, or
|
||||
(at your option) any later version.
|
||||
"""
|
||||
print(notice_msg)
|
||||
|
||||
|
||||
def check_and_get_updates():
|
||||
notice()
|
||||
response = requests.get(update_check_endpoint).json()
|
||||
if response['tag_name'] == program_version_number:
|
||||
"""Ignore if the program is up to date"""
|
||||
pass
|
||||
else:
|
||||
update_prompt = input(f"[?] A new release is available ({response['tag_name']}). Would you like to install it? (y/n) ")
|
||||
if update_prompt.lower() == "y":
|
||||
files_to_update = ['downloader.py', 'geckodriver.exe', 'README.md', 'requirements.txt']
|
||||
for file in tqdm(files_to_update, desc=f'Updating'):
|
||||
data = requests.get(f'https://raw.githubusercontent.com/rly0nheart/facebook-downloader/master/{file}')
|
||||
with open(file, "wb") as f:
|
||||
f.write(data.content)
|
||||
f.close()
|
||||
print("Updated: Re-run program.")
|
||||
else:
|
||||
pass
|
||||
|
||||
|
||||
def download_video(url, output):
|
||||
driver.get(downloading_url) # Opening getfvid.com, a website that downloads facebook videos
|
||||
url_entry_field = driver.find_element(By.NAME, "url") # Find the url entry field
|
||||
url_entry_field.send_keys(url) # write facebook url in the entry field
|
||||
url_entry_field.send_keys(Keys.ENTER) # press enter
|
||||
print('Please standby (20 seconds)...')
|
||||
time.sleep(20) # Sleep for at least 20 seconds to wait for the next page to load
|
||||
driver.refresh
|
||||
|
||||
"""
|
||||
HD: "/html/body/div[2]/div/div/div[1]/div/div[2]/div/div[3]/p[1]/a"
|
||||
SD: "/html/body/div[2]/div/div/div[1]/div/div[2]/div/div[3]/p[2]/a"
|
||||
Audio: "/html/body/div[2]/div/div/div[1]/div/div[2]/div/div[3]/p[3]/a"
|
||||
"""
|
||||
|
||||
download_btn = WebDriverWait(driver, 20).until(expected_conditions.presence_of_element_located((By.XPATH, '/html/body/div[2]/div/div/div[1]/div/div[2]/div/div[3]/p[1]/a'))) # Find the download button (this clicks the first button which returns a video in hd)
|
||||
download_url = download_btn.get_attribute('href')
|
||||
|
||||
with requests.get(download_url, stream=True) as response:
|
||||
response.raise_for_status()
|
||||
with open(f'downloads/{output}.mp4', 'wb') as file:
|
||||
for chunk in tqdm(response.iter_content(chunk_size=8192), desc=f'Downloading: {output}.mp4'):
|
||||
file.write(chunk)
|
||||
print(f'Downloaded: {file.name}')
|
||||
driver.close()
|
||||
|
||||
|
||||
parser = argparse.ArgumentParser(description='facebook-downloader — by Richard Mwewa')
|
||||
parser.add_argument('url', help='facebook video url (eg. https://www.facebook.com/PageName/videos/VideoID')
|
||||
parser.add_argument('-A', '--audio', help=argparse.SUPPRESS, action='store_true')
|
||||
parser.add_argument('-o', '--output', help='output filename')
|
||||
parser.add_argument('-v', '--version', version='2022.1.0.0', action='version')
|
||||
args = parser.parse_args()
|
||||
url = args.url
|
||||
output = args.output
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
try:
|
||||
check_and_get_updates()
|
||||
download_video(url, output)
|
||||
|
||||
except KeyboardInterrupt:
|
||||
print('Process interrupted with Ctrl+C.')
|
||||
|
||||
except Exception as e:
|
||||
print('An error occured:', e)
|
||||
|
||||
@@ -1 +0,0 @@
|
||||
|
||||
0
facebook_downloader/__init__.py
Normal file
0
facebook_downloader/__init__.py
Normal file
88
facebook_downloader/downloader.py
Normal file
88
facebook_downloader/downloader.py
Normal file
@@ -0,0 +1,88 @@
|
||||
import os
|
||||
import argparse
|
||||
import requests
|
||||
from tqdm import tqdm
|
||||
from selenium import webdriver
|
||||
from selenium.webdriver.common.by import By
|
||||
from selenium.webdriver.common.keys import Keys
|
||||
from selenium.webdriver.support.ui import WebDriverWait
|
||||
from selenium.webdriver.support import expected_conditions
|
||||
|
||||
|
||||
class FacebookDownloader:
|
||||
def __init__(self):
|
||||
parser = argparse.ArgumentParser(description='facebook-downloader — by Richard Mwewa')
|
||||
parser.add_argument('url', help='facebook video url (eg. https://www.facebook.com/PageName/videos/VideoID')
|
||||
parser.add_argument('-a', '--audio', help='download file as audio', action='store_true')
|
||||
parser.add_argument('-o', '--output', help='output filename')
|
||||
self.args = parser.parse_args()
|
||||
|
||||
option = webdriver.FirefoxOptions()
|
||||
option.add_argument('--headless')
|
||||
self.driver = webdriver.Firefox(options=option)
|
||||
|
||||
self.program_version_number = "2022.1.0.0"
|
||||
self.downloading_url = "https://getfvid.com"
|
||||
self.update_check_endpoint = "https://api.github.com/repos/rly0nheart/facebook-downloader/releases/latest"
|
||||
|
||||
|
||||
def notice(self):
|
||||
notice_msg = f"""
|
||||
facebook-downloader {self.program_version_number} Copyright (C) 2022 Richard Mwewa
|
||||
|
||||
This program is free software: you can redistribute it and/or modify
|
||||
it under the terms of the GNU General Public License as published by
|
||||
the Free Software Foundation, either version 3 of the License, or (at your option) any later version.
|
||||
"""
|
||||
print(notice_msg)
|
||||
|
||||
|
||||
def check_updates(self):
|
||||
self.notice()
|
||||
response = requests.get(self.update_check_endpoint).json()
|
||||
if response['tag_name'] == self.program_version_number:
|
||||
"""Ignore if the program is up to date"""
|
||||
pass
|
||||
else:
|
||||
print(f"[!] A new release is available ({response['tag_name']}). Run 'pip install --upgrade facebook-downloader' to get the updates.")
|
||||
|
||||
|
||||
def download_type(self):
|
||||
if self.args.audio:
|
||||
download_type_element = "/html/body/div[2]/div/div/div[1]/div/div[2]/div/div[3]/p[3]/a"
|
||||
else:
|
||||
download_type_element = "/html/body/div[2]/div/div/div[1]/div/div[2]/div/div[3]/p[1]/a"
|
||||
|
||||
return download_type_element
|
||||
|
||||
|
||||
def path_finder(self):
|
||||
directory_list = [os.path.join('downloads', 'videos'), os.path.join('downloads', 'audio')]
|
||||
for directory in directory_list:
|
||||
os.makedirs(directory, exist_ok=True)
|
||||
|
||||
|
||||
def download_video(self):
|
||||
self.path_finder()
|
||||
self.check_updates()
|
||||
self.driver.get(self.downloading_url) # Opening getfvid.com, a website that downloads facebook videos
|
||||
url_entry_field = self.driver.find_element(By.NAME, "url") # Find the url entry field
|
||||
url_entry_field.send_keys(self.args.url) # write facebook url in the entry field
|
||||
url_entry_field.send_keys(Keys.ENTER) # press enter
|
||||
print('Please standby (20 seconds)...')
|
||||
self.driver.refresh
|
||||
"""
|
||||
HD: "/html/body/div[2]/div/div/div[1]/div/div[2]/div/div[3]/p[1]/a"
|
||||
SD: "/html/body/div[2]/div/div/div[1]/div/div[2]/div/div[3]/p[2]/a"
|
||||
Audio: "/html/body/div[2]/div/div/div[1]/div/div[2]/div/div[3]/p[3]/a"
|
||||
"""
|
||||
download_btn = WebDriverWait(self.driver, 20).until(expected_conditions.presence_of_element_located((By.XPATH, self.download_type()))) # Find the download button (this clicks the first button which returns a video in hd)
|
||||
download_url = download_btn.get_attribute('href')
|
||||
|
||||
with requests.get(download_url, stream=True) as response:
|
||||
response.raise_for_status()
|
||||
with open(os.path.join('downloads', 'videos', f'{self.args.output}.mp4'), 'wb') as file:
|
||||
for chunk in tqdm(response.iter_content(chunk_size=8192), desc=f'Downloading: {self.args.output}.mp4'):
|
||||
file.write(chunk)
|
||||
print(f'Downloaded: {file.name}')
|
||||
self.driver.close()
|
||||
12
facebook_downloader/main.py
Normal file
12
facebook_downloader/main.py
Normal file
@@ -0,0 +1,12 @@
|
||||
from facebook_downloader.downloader import FacebookDownloader
|
||||
|
||||
def main():
|
||||
try:
|
||||
start = FacebookDownloader()
|
||||
start.download_video()
|
||||
|
||||
except KeyboardInterrupt:
|
||||
print('Process interrupted with Ctrl+C.')
|
||||
|
||||
except Exception as e:
|
||||
print('An error occured:', e)
|
||||
BIN
geckodriver.exe
BIN
geckodriver.exe
Binary file not shown.
@@ -1,3 +0,0 @@
|
||||
tqdm
|
||||
selenium
|
||||
requests
|
||||
31
setup.py
Normal file
31
setup.py
Normal file
@@ -0,0 +1,31 @@
|
||||
import setuptools
|
||||
|
||||
with open('README.md', 'r', encoding='utf-8') as file:
|
||||
long_description = file.read()
|
||||
|
||||
setuptools.setup(
|
||||
name='facebook-downloader',
|
||||
version='2022.1.0.0',
|
||||
author='Richard Mwewa',
|
||||
author_email='rly0nheart@duck.com',
|
||||
packages=['facebook_downloader'],
|
||||
description='Facebook video downloader',
|
||||
long_description=long_description,
|
||||
long_description_content_type='text/markdown',
|
||||
url='https://github.com/rly0nheart/facebook-downloader',
|
||||
license='GNU General Public License v3 (GPLv3)',
|
||||
install_requires=['requests', 'selenium', 'tqdm'],
|
||||
classifiers=[
|
||||
'Development Status :: 5 - Production/Stable',
|
||||
'Intended Audience :: Information Technology',
|
||||
'License :: OSI Approved :: GNU General Public License v3 (GPLv3)',
|
||||
'Operating System :: OS Independent',
|
||||
'Natural Language :: English',
|
||||
'Programming Language :: Python :: 3'
|
||||
],
|
||||
entry_points={
|
||||
'console_scripts': [
|
||||
'facebook_downloader=facebook_downloader.main:main',
|
||||
]
|
||||
},
|
||||
)
|
||||
@@ -1,6 +0,0 @@
|
||||
from downloader import download_video
|
||||
|
||||
def test_download_video():
|
||||
# I find this video very interesting, enjoy! ;)
|
||||
url = 'https://www.facebook.com/VICE/videos/663211078474482'
|
||||
download_video(url, output='test_video_making-a-weed-smoothie')
|
||||
Reference in New Issue
Block a user