rsstube/scripts/rsstube.py

#!/usr/bin/python3

import sys,importlib

from utils import debug,notify,warn,error,success
import opml

network = True
verbosity = 3
args = {}
arg_count = 0
output_format = "url"
output_opml = None
output_filename = None
output = None

config = None
try:
	from pathlib import Path
	home = str(Path.home())
	local_config_path = home + "/.config/rsstube/config"
	config = open(local_config_path,"r")
except FileNotFoundError:
	try:
		global_config_path = "/etc/rsstube/config"
		config = open(global_config_path,"r")
	except FileNotFoundError:
		# no change
		config = None
file_params = ""
if not config is None:
	for line in config:
		line = line.strip()
		# comment lines should begin with # after stripping
		if line != "" and line[0] != "#":
			file_params += " " + line
from options import options

def process_args (
	network,
	verbosity,
	args,
	arg_count,
	output_format,
	output_filename,
	network_new,
	verbosity_new,
	args_new,
	arg_count_new,
	output_format_new,
	output_filename_new
):
	if network_new == False:
		network = network_new
	if not verbosity_new is None:
		verbosity = verbosity_new
	for i in args_new:
		args[i] = args_new[i]
	arg_count = arg_count_new
	if output_format_new != "":
		output_format = output_format_new
	if not output_filename_new is None:
		output_filename = output_filename_new
	return network,verbosity,args,arg_count,output_format,output_filename

# config file options
if not file_params == "":
	network_new,verbosity_new,args_new,arg_count_new,output_format_new,output_filename_new = options(file_params.split())
	network,verbosity,args,arg_count,output_format,output_filename = process_args(
		network,
		verbosity,
		args,
		arg_count,
		output_format,
		output_filename,
		network_new,
		verbosity_new,
		args_new,
		arg_count_new,
		output_format_new,
		output_filename_new
	)

# command-line options
network_new,verbosity_new,args_new,arg_count_new,output_format_new,output_filename_new = options(sys.argv[1:])
network,verbosity,args,arg_count,output_format,output_filename = process_args(
	network,
	verbosity,
	args,
	arg_count,
	output_format,
	output_filename,
	network_new,
	verbosity_new,
	args_new,
	arg_count_new,
	output_format_new,
	output_filename_new
)

if output_format == "opml":
	debug ("Formatting output as OPML.", verbosity)
	output_opml = opml.Opml("rsstube feeds")

if not output_filename is None and output_filename != "":
	debug ("Output will be saved in " + output_filename, verbosity)
	output = open(output_filename, "w")

if len(sys.argv) == arg_count+1:
	error ("Please provide one or more URL.", verbosity)

for url in sys.argv[arg_count+1:]:
	from determine_site import determine_site
	debug ("Attempting to determine site...", verbosity)
	site = determine_site (url)
	if not site is None:
		debug ("Site identified as " + site, verbosity)
		notify ("Trying " + site + " extractor...", verbosity)

		# get appropriate extractor
		extractor = importlib.import_module("extractors." + site)
		feed = extractor.extract(url, None, network, verbosity, args)
		if feed is None:
			error ("Unable to get RSS feed for " + url, verbosity, site)
		else:
			if not output_opml is None:
				output_opml.add_feed (feed, site + ": " + url, url)
			else:
				success (feed, output)
	elif network:
		from download_page import download
		page = download (None, url, args, verbosity)
		if page is None:
			error ("Failed to download " + url, verbosity)
			continue

		# try to get feed for common software like PeerTube
		debug ("Attempting to determine software from page...", verbosity)
		from determine_software import determine_software
		software = determine_software (page)
		if not software is None:
			debug ("Software identified as " + software, verbosity)
			notify ("Trying " + software + " extractor...", verbosity)
			extractor = importlib.import_module("extractors." + software)
			feed = extractor.extract(url, page, network, verbosity, args)
			if feed is None:
				notify ("Unable to get RSS feed for " + url + " with " + software + " extractor", verbosity, software)
			else:
				if not output_opml is None:
					output_opml.add_feed (feed, software + ": " + url, url)
				else:
					success (feed, output)
				continue

		# try generic extractor even if software is known
		debug ("Trying generic extractor...", verbosity)
		extractor = importlib.import_module("extractors.generic")
		feed = extractor.extract(url, page, network, verbosity, args)
		if feed is None:
			error ("Unable to get RSS feed for " + url, verbosity, "generic")
		else:
			if not output_opml is None:
				output_opml.add_feed (feed, url, url)
			else:
				success (feed, output)
	else:
		error ("Unable to get RSS feed for " + url + " without downloading page", verbosity)

if not output_opml is None:
	success (output_opml.get_opml(), output)

if not output is None:
	output.close()