amr/discorss
amr/discorss
1
0
Fork 0
Code Issues Pull requests Projects 1 Releases 2 Packages Wiki Activity Actions

Various small fixes, see full commit message

Browse source 
* Changed the preview length to 250 characters
* Changed the version in the user-agent string
* Cleaned up paths, switching to user paths
* Updated html regex filter to correctly remove : . /
* Various formatting changes from black
* Wrapped published_time in try/except
This commit is contained in:
A.M. Rowsell 2025-02-13 21:16:55 -05:00
parent 6709c14b1d
commit bb3edcbfc7
Signed by: amr
GPG key ID: 0B6E2D8375CF79A9
1 changed files with 28 additions and 21 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

49
discorss.py
View file

@ -19,10 +19,11 @@ import time
import os
import re
config_dir = os.environ.get('XDG_CONFIG_HOME')
config_dir = os.environ.get("XDG_CONFIG_HOME")
home_dir = Path.home()
if config_dir is None:
config_file_path = r"~/.config/discorss/discorss.conf"
config_dir = r"~/.config/discorss"
config_file_path = str(home_dir) + "/.config/discorss/discorss.conf"
config_dir = str(home_dir) + "/.config/discorss"
else:
config_file_path = config_dir + r"/discorss/discorss.conf"
log_file_path = r"/var/log/discorss"
@ -30,30 +31,26 @@ log_file_path = r"/var/log/discorss"
log_file_name = r"/app.log"
# Yes, I know you "can't parse HTML with regex", but
# 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"]
# 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.
# one and limit it to 250 characters.
# TODO: make the character limit smarter, as to split at a natural point
def get_description(feed):
try:
temporary_string = str(feed.entries[0]["summary_detail"]["value"])
temporary_string = html_filter.sub("", temporary_string)
desc = (
temporary_string[:150]
if len(temporary_string) > 150
else temporary_string
temporary_string[:250] if len(temporary_string) > 250 else temporary_string
)
except KeyError:
temporary_string = str(feed.entries[0]["description"])
temporary_string = html_filter.sub("", temporary_string)
desc = (
temporary_string[:150]
if len(temporary_string) > 150
else temporary_string
temporary_string[:250] if len(temporary_string) > 250 else temporary_string
)
return desc
@ -62,13 +59,22 @@ def main():
os.environ["TZ"] = "America/Toronto"
time.tzset()
# Check for log and config files/paths, create empty directories if needed
# TODO: make this cleaner
try:
Path(log_file_path).mkdir(parents=True, exist_ok=True)
except FileExistsError:
print("The logfile path {} already exists and is not a directory!".format(log_file_path))
print(
"The logfile path {} already exists and is not a directory!".format(
log_file_path
)
)
if not Path(config_file_path).exists():
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)
print(
"No config file at {}! Snarf.\n{} was created for you.".format(
config_file_path, config_dir
)
)
Path(config_dir).mkdir(parents=True, exist_ok=True)
return
with open(config_file_path, "r") as config_file:
app_config = json.load(config_file)
@ -76,15 +82,16 @@ def main():
try:
last_check = app_config["lastupdate"]
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"]):
# Get the feed
feed = feedparser.parse(hook["url"])
published_time = time.mktime(feed.entries[0]["published_parsed"])
published_time = published_time + hook["offset"]
print("Parsing feed {}...".format(hook["name"]))
feed = feedparser.parse(hook["url"])
try:
published_time = time.mktime(feed.entries[0]["published_parsed"])
published_time = published_time + hook["offset"]
except KeyError:
published_time = now - 10 # Not sure what a sensible default here is
# 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")
@ -122,7 +129,7 @@ def main():
"attachments": [],
}
custom_header = {
"user-agent": "DiscoRSS (https://git.frzn.dev/amr/discorss, 0.2rc1)",
"user-agent": "DiscoRSS (https://git.frzn.dev/amr/discorss, 0.2rc2)",
"content-type": "application/json",
}
webhook_string = json.dumps(webhook)