amr/discorss
amr/discorss
1
0
Fork 0
Code Issues 1 Pull requests Projects 1 Releases 1 Packages Wiki Activity Actions

Changed formatting, added some comments, moved config file location

Browse source
This commit is contained in:
A.M. Rowsell 2025-02-07 20:24:14 -05:00
parent 6305604056
commit d15578f7b2
Signed by: amr
GPG key ID: 0B6E2D8375CF79A9
1 changed files with 31 additions and 11 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

42
discorss.py
View file

@ -19,29 +19,41 @@ import time
import os import os
import re import re
config_file_path = r"/etc/discorss.conf" config_dir = os.environ.get('XDG_CONFIG_HOME')
# config_file_path = r"discorss.conf" if config_dir is None:
config_file_path = r"~/.config/discorss/discorss.conf"
config_dir = r"~/.config/discorss"
else:
config_file_path = config_dir + r"/discorss/discorss.conf"
log_file_path = r"/var/log/discorss" log_file_path = r"/var/log/discorss"
# log_file_path = r"./log" # log_file_path = r"./log"
log_file_name = r"/app.log" log_file_name = r"/app.log"
# Yes, I know you "can't parse HTML with regex", but # Yes, I know you "can't parse HTML with regex", but
# just watch me. # just watch me.
html_filter = re.compile(r"\<\/?([A-Za-z \"\=])*\>") html_filter = re.compile(r"\<\/?([A-Za-z \"\=])*\>")
success_codes = ['200', '201', '202', '203', '204', '205', '206'] success_codes = ["200", "201", "202", "203", "204", "205", "206"]
# This function gets and formats the brief excerpt that goes in the embed
# Different feeds put summaries in different fields, so we pick the best
# one and limit it to 150 characters.
# TODO: make the character limit smarter, as to split at a natural point
def get_description(feed): def get_description(feed):
try: try:
temporary_string = str(feed.entries[0]["summary_detail"]["value"]) temporary_string = str(feed.entries[0]["summary_detail"]["value"])
temporary_string = html_filter.sub("", temporary_string) temporary_string = html_filter.sub("", temporary_string)
desc = ( desc = (
temporary_string[:150] if len(temporary_string) > 150 else temporary_string temporary_string[:150]
if len(temporary_string) > 150
else temporary_string
) )
except KeyError: except KeyError:
temporary_string = str(feed.entries[0]["description"]) temporary_string = str(feed.entries[0]["description"])
temporary_string = html_filter.sub("", temporary_string) temporary_string = html_filter.sub("", temporary_string)
desc = ( desc = (
temporary_string[:150] if len(temporary_string) > 150 else temporary_string temporary_string[:150]
if len(temporary_string) > 150
else temporary_string
) )
return desc return desc
@ -49,13 +61,14 @@ def get_description(feed):
def main(): def main():
os.environ["TZ"] = "America/Toronto" os.environ["TZ"] = "America/Toronto"
time.tzset() time.tzset()
# Check for log and config files/paths, create empty directories if needed
try: try:
Path(log_file_path).mkdir(parents=True, exist_ok=True) Path(log_file_path).mkdir(parents=True, exist_ok=True)
except FileExistsError: except FileExistsError:
print("This path already exists and is not a directory!") print("The logfile path {} already exists and is not a directory!".format(log_file_path))
# Load and read the config file
if not Path(config_file_path).exists(): if not Path(config_file_path).exists():
print("No config file! Snarf. Directories were created for you.") print("No config file at {}! Snarf.\n{} was created for you.".format(config_file_path, config_dir))
Path(config_file_path).mkdir(parents=True, exist_ok=True)
return return
with open(config_file_path, "r") as config_file: with open(config_file_path, "r") as config_file:
app_config = json.load(config_file) app_config = json.load(config_file)
@ -63,7 +76,9 @@ def main():
try: try:
last_check = app_config["lastupdate"] last_check = app_config["lastupdate"]
except KeyError: except KeyError:
last_check = now - 21600 # first run, no lastupdate, check up to 6 hours ago last_check = (
now - 21600
) # first run, no lastupdate, check up to 6 hours ago
for i, hook in enumerate(app_config["feeds"]): for i, hook in enumerate(app_config["feeds"]):
# Get the feed # Get the feed
feed = feedparser.parse(hook["url"]) feed = feedparser.parse(hook["url"])
@ -71,7 +86,9 @@ def main():
published_time = published_time + hook["offset"] published_time = published_time + hook["offset"]
print("Parsing feed {}...".format(hook["name"])) print("Parsing feed {}...".format(hook["name"]))
# Hash the title of the latest post and use that to determine if it's been posted # Hash the title of the latest post and use that to determine if it's been posted
new_hash = hashlib.sha3_512(bytes(feed.entries[0]["title"], 'utf-8')).hexdigest() new_hash = hashlib.sha3_512(
bytes(feed.entries[0]["title"], "utf-8")
).hexdigest()
try: try:
if hook["lasthash"] != new_hash: if hook["lasthash"] != new_hash:
app_config["feeds"][i]["lasthash"] = new_hash app_config["feeds"][i]["lasthash"] = new_hash
@ -90,7 +107,10 @@ def main():
"name": "DiscoRSS", "name": "DiscoRSS",
# "url": "https://git.frzn.dev/amr/discorss", # "url": "https://git.frzn.dev/amr/discorss",
}, },
"author": {"name": str(hook["name"]), "url": str(hook["siteurl"])}, "author": {
"name": str(hook["name"]),
"url": str(hook["siteurl"]),
},
"fields": [ "fields": [
{ {
"name": "Excerpt from post:", "name": "Excerpt from post:",