Script to rip all videos from https://floatplane.rip/

floatplane_ripper.py

#!/usr/bin/env python3

# Rip floatplane.rip
# by terorie :P

import sys
import requests
import lxml.html
from clint.textui import progress

session = requests.Session()

if len(sys.argv) != 2:
	print("Usage: ./linusriptips.py <site>")
	exit(1)

main_r = session.get(sys.argv[1])

if main_r.status_code != 200:
	print("Failed getting", sys.argv[1])
	exit(1)

main_doc = lxml.html.fromstring(main_r.text)

cards = main_doc.find_class('card mb-4 box-shadow')

for card in cards:
	card_onclick = card.get('onclick')
	if not card_onclick.startswith("location.href='"):
		continue
	if not card_onclick.endswith("'"):
		continue

	video_link = card_onclick[15:len(card_onclick)-1]
	if not video_link.startswith("https://floatplane.rip/video/"):
		continue
	name = video_link[29:] + "_1080.mp4"

	print("Found video:", name)

	video_r = session.get(video_link)
	if video_r.status_code != 200:
		print("Failed getting", video_link)
		continue
	
	video_doc = lxml.html.fromstring(video_r.text)

	metas = video_doc.cssselect("meta")
	src = None
	for meta in metas:
		prop = meta.get('property')
		if prop != "og:video":
			continue
		src = meta.get("content")

	if src is None:
		print("Failed extracting video URL from", video_link)
		continue

	src_r = session.get(src, stream=True)
	with open(name, 'wb') as f:
		print("Downloading", name)
		total_length = int(src_r.headers.get('content-length'))
		for chunk in progress.bar(src_r.iter_content(chunk_size=1024), expected_size=(total_length/1024) + 1):
			if chunk:
				f.write(chunk)
		f.flush()