A simple script to scrape specified French movie poster images and automatically fetch english posters from TMDB and merge them together

poster_merger.py

import os

import httpx
from wand.image import Image


french_poster_urls = {
	"step_up": "https://fr.web.img4.acsta.net/c_1240_1680/medias/nmedia/18/62/86/83/18673315.jpg",
	"step_up_2": "https://fr.web.img6.acsta.net/c_1240_1680/medias/nmedia/18/65/68/91/18926786.jpg",
	"friends_with_benefits": "https://fr.web.img4.acsta.net/c_1240_1680/medias/nmedia/18/82/69/35/19757410.jpg",
	"cruel_intentions": "https://fr.web.img2.acsta.net/c_1240_1680/medias/04/33/19/043319_af.jpg",
	"no_strings_attached": "https://fr.web.img5.acsta.net/c_1240_1680/medias/nmedia/18/82/66/93/19631095.jpg",
	"whats_your_number": "https://fr.web.img6.acsta.net/c_1240_1680/medias/nmedia/18/85/71/40/19802001.jpg",
	"made_in_dagenham": "https://fr.web.img3.acsta.net/c_1240_1680/medias/nmedia/18/82/79/20/19637240.jpg",
	"eurotrip": "https://imgr.cineserie.com/2006/08/398939.jpg",
	"wild_things": "https://fr.web.img6.acsta.net/c_1240_1680/pictures/210/250/21025068_20130806171618329.jpg",
	"tangled": "https://fr.web.img4.acsta.net/c_1240_1680/medias/nmedia/00/02/45/11/sextrouble.jpg",
	"out_cold": "https://fr.web.img2.acsta.net/c_1240_1680/medias/nmedia/00/02/45/04/snowsex.jpg",
	"not_another_teen_movie": "https://fr.web.img6.acsta.net/c_1240_1680/medias/nmedia/00/02/43/37/affsexacademy.jpg",
	"the_hangover": "https://fr.web.img4.acsta.net/c_1240_1680/medias/nmedia/18/70/03/08/19109117.jpg",
	"the_other_guys": "https://fr.web.img3.acsta.net/c_1240_1680/medias/nmedia/18/78/58/16/19499827.jpg",
}

tmdb_search_index_overrides = {
	"tangled": 2,
}


def find_and_save_posters(movie_code: str, french_poster_url: str):
	movie_search = movie_code.replace("_", " ")
	params = {
		"api_key": TMDB_API_KEY,
		"query": movie_search,
		"include_adult": "false",
		"language": "en-US",
		"page": "1",
	}
	with httpx.Client(follow_redirects=True) as client:
		response = client.get("https://api.themoviedb.org/3/search/movie", params=params)
		search_results = response.json()
		search_cursor = tmdb_search_index_overrides.get(movie_code, 0)
		poster_path = search_results["results"][search_cursor]["poster_path"]
		poster_url = f"https://image.tmdb.org/t/p/original{poster_path}"
		orig_poster_res = client.get(poster_url)
		with open(f"posters/{movie_code}-original.jpg", "wb") as f:
			f.write(orig_poster_res.read())
		french_poster_res = client.get(french_poster_url)
		with open(f"posters/{movie_code}-french.jpg", "wb") as f:
			f.write(french_poster_res.read())


def scale_and_combine(image1_path, image2_path, output_path, padding=10):
	with Image(filename=image1_path) as img1, Image(filename=image2_path) as img2:
		height1 = img1.height
		height2 = img2.height
		target_height = min(height1, height2)
		img1.transform(resize=f"x{target_height}")
		img2.transform(resize=f"x{target_height}")
		combined_width = img1.width + img2.width + padding
		with Image(width=combined_width, height=target_height, background=None) as combined:
			combined.composite(img1, left=0, top=0)
			combined.composite(img2, left=img1.width + padding, top=0)
			combined.save(filename=output_path)


if __name__ == "__main__":
	if not os.path.exists("posters"):
		os.makedirs("posters")
	for movie_code, french_poster_url in french_poster_urls.items():
		print("Scraping:", movie_code)
		find_and_save_posters(movie_code, french_poster_url)
		print("Combining:", movie_code)
		scale_and_combine(
			f"posters/{movie_code}-original.jpg",
			f"posters/{movie_code}-french.jpg",
			f"posters/{movie_code}-merged.jpg",
		)
		print(movie_code, "complete.")
	print("Done.")