This is a simple python scraping for the FilmAffinity.

pip install python-filmaffinity

Optional Pydantic models:

pip install "python-filmaffinity[models]"

git clone git@github.com:sergiormb/python_filmaffinity.git
cd python_filmaffinity
python -m pip install -e ".[dev]"

beautifulsoup4 >= 4.9.1
requests >= 2.24.0
requests-cache >= 1.0.0

Python 3.9 or newer is required.

FilmAffinity does not provide a public API for this package. The library uses HTML scraping, so selectors can break when FilmAffinity changes its layout.

import python_filmaffinity
service = python_filmaffinity.FilmAffinity()
movie = service.get_movie(title='Celda 211')
movie['title']
Celda 211
movie['rating']
7.7
movie['directors']
['Daniel Monzón']
movie['actors']
['Luis Tosar', 'Alberto Ammann', 'Antonio Resines', 'Carlos Bardem', 'Marta Etura', 'Vicente Romero', 'Manuel Morón', 'Manolo Solo', 'Fernando Soto', 'Luis Zahera', 'Patxi Bisquert', 'Félix Cubero', 'Josean Bengoetxea', 'Juan Carlos Mangas', 'Jesús Carroza']

The public API keeps returning dictionaries by default. Install the models extra and pass as_model=True to receive Pydantic models:

service = python_filmaffinity.FilmAffinity()
movie = service.get_movie(id='495280', as_model=True)
movie.title

Export helpers accept dictionaries, lists and models:

movies = service.search(title='Batman')
python_filmaffinity.to_json(movies, 'movies.json')
python_filmaffinity.to_csv(movies, 'movies.csv')
python_filmaffinity.to_markdown(movies, 'movies.md')

filmaffinity search "Batman" --top 5
filmaffinity movie 197671 --images --json
filmaffinity top --kind filmaffinity --top 10

python -m pip install -e ".[dev]"
python -m pytest
RUN_INTEGRATION=1 python -m pytest -m integration
python -m build
twine check dist/*

The persistent sqlite cache is stored in the user's cache directory by default. Use cache_backend="memory" for runs that should not write to disk.

• Spanish: 'es'
• USA, UK: 'en'
• México: 'mx'
• Argentina: 'ar'
• Chile: 'cl'
• Colombia: 'co'
• Example

import python_filmaffinity
service = python_filmaffinity.FilmAffinity(lang='en')

• Example

movies = service.search(cast='Nicolas Cage')

• Example

movies = service.get_movie(title='Avatar')
movies = service.get_movie(id='495280')

• Example

movies = service.top_filmaffinity()
movies = service.top_filmaffinity(from_year=2010, to_year=2011)

• Example

movies = service.top_premieres()

• Example

movies = service.top_netflix()
movies = service.top_hbo(top=5)
movies = service.top_filmin()
movies = service.top_movistar()
movies = service.top_rakuten()
movies = service.top_tv_series()

• Example

movies = service.recommend_netflix()
movies = service.recommend_hbo()
movies = service.recommend_filmin()
movies = service.recommend_movistar()
movies = service.recommend_rakuten()

• Added the filmaffinity command line interface.
• Added optional Pydantic models via as_model=True.
• Added JSON, CSV and Markdown export helpers.
• Moved the default persistent cache to the user's cache directory.
• Renamed the PyPI publishing workflow to publish-to-pypi.yml.

• Updated scraping for the current FilmAffinity layout.
• Replaced the deprecated user-agent dependency with an internal header pool.
• Added fast parser tests and optional live integration tests.
• Modernized packaging metadata and GitHub Actions.

• Scrapping updated

• Fixed errors in get_country

• When images are requested, lets provide also the country where they were published (@jcea)
• Correctly provide the trailers listed in filmaffinity (@jcea)
• Spurious search in youtube deleted (@jcea)
• Extract correctly when multiple genres (@jcea)
• Added "writers", "music", "cinematography" and "producers" (@jcea)
• Regression processing "original_title" in searches (@jcea)

• Deleted spaces at the end of the title (@jcea)
• Added original_title (@jcea)
• Fix directors scraping (@jcea)

• Search by genre

• Fixed errors

• Adds proxies and random user-agent in headers

• Changed description

• Fixed errors

• Fixed errors with SSL

• Replaces cachetools for requests-cache

• Add images
• Fixed errors

• Fixes encoding for the analyzed results
• Disabled limitations for all the supported languages
• Change of name to the main class.
• Adds initial language check and raise error if this is not in support
• Adds basic exceptions

• Add cachetools

• Fixed errors

• Top new DVDs
• Get movie with trailer
• Top TV series
• Return movies list with raiting

• Top Netlfix, HBO and Filmin
• Recommendation from Netflix, HBO or Filmin
• Fixed errors

• Search movies by title, year, director or cast.
• Get the filmaffinity top and search by year
• Get the premieres top

• Initial release.

• Sergio Pino, sergiormb88@gmail.com, sergiormb.github.io

• opacam https://github.com/opacam
• jcea - https://www.jcea.es/ - https://blog.jcea.es/ - https://github.com/jcea

The MIT License (MIT)

Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:

The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.

THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.