amr/discorss
amr/discorss
1
3
Fork 0
Code Issues Pull requests Projects Releases 4 Packages Wiki Activity Actions

bugfix: corrected variable name causing errors, renamed some others

Browse source
This commit is contained in:
A.M. Rowsell 2026-06-11 20:41:51 -04:00
commit 84c0b40edf
Signed by: amr
GPG key ID: E0879EDBDB0CA7B1
1 changed files with 17 additions and 16 deletions
Download patch file Download diff file Expand all files Collapse all files

33
discorss.py
View file

@ -58,6 +58,7 @@ class Discorss:
self.img_src_filter = re.compile(r'<img[^>]+src=["\']([^"\']+)["\']', re.I) self.img_src_filter = re.compile(r'<img[^>]+src=["\']([^"\']+)["\']', re.I)
self.success_codes = [200, 201, 202, 203, 204, 205, 206] self.success_codes = [200, 201, 202, 203, 204, 205, 206]
self.app_config = {} self.app_config = {}
print(f"Logging to {self.log_file_path}")
async def _fetch_feed(self, hook): async def _fetch_feed(self, hook):
response = await asyncio.to_thread( response = await asyncio.to_thread(
@ -98,20 +99,20 @@ class Discorss:
async def _process_feed(self, hook, last_check): async def _process_feed(self, hook, last_check):
self.logger.debug("Parsing feed %s...", hook["name"]) self.logger.debug("Parsing feed %s...", hook["name"])
feeds = await self._fetch_feed(hook) feed = await self._fetch_feed(hook)
latest_post = None latest_post = None
prev_best = 0 prev_best = 0
bad_time = False bad_time = False
self.logger.debug("About to sort through entries for feed %s ...", hook["name"]) self.logger.debug("About to sort through entries for feed %s ...", hook["name"])
for feed in feeds["entries"]: for post in feed["entries"]:
try: try:
published_time = time.mktime(feed["published_parsed"]) published_time = time.mktime(post["published_parsed"])
published_time = published_time + hook["offset"] published_time = published_time + hook["offset"]
except KeyError: except KeyError:
published_time = time.mktime(feed["updated_parsed"]) published_time = time.mktime(post["updated_parsed"])
bad_time = True bad_time = True
if published_time > prev_best: if published_time > prev_best:
latest_post = feed latest_post = post
prev_best = published_time prev_best = published_time
if latest_post is None: if latest_post is None:
@ -251,9 +252,9 @@ class Discorss:
# This function gets and formats the brief excerpt that goes in the embed # 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 # Different feeds put summaries in different fields, so we pick the best
# one and limit it to 250 characters. # one and limit it to 250 characters.
def get_description(self, feed, length=250, min_length=150, addons=None): def get_description(self, post, length=250, min_length=150, addons=None):
try: try:
temporary_string = str(feed["summary_detail"]["value"]) temporary_string = str(post["summary_detail"]["value"])
temporary_string = self.html_filter.sub("", temporary_string) temporary_string = self.html_filter.sub("", temporary_string)
while length > min_length: while length > min_length:
if temporary_string[length - 1 : length] == " ": if temporary_string[length - 1 : length] == " ":
@ -261,7 +262,7 @@ class Discorss:
else: else:
length -= 1 length -= 1
except KeyError: except KeyError:
temporary_string = str(feed["description"]) temporary_string = str(post["description"])
temporary_string = self.html_filter.sub("", temporary_string) temporary_string = self.html_filter.sub("", temporary_string)
while length > min_length: while length > min_length:
if temporary_string[length - 1 : length] == " ": if temporary_string[length - 1 : length] == " ":
@ -276,28 +277,28 @@ class Discorss:
# attempting to extract image previews from feeds which primarily feature # attempting to extract image previews from feeds which primarily feature
# images, like NASA's Picture of the Day feed # images, like NASA's Picture of the Day feed
def get_image_url(self, feed): def get_image_url(self, post):
image_candidates = [] image_candidates = []
# check the most common fields, this should catch the majority of image # check the most common fields, this should catch the majority of image
# feeds' embedded urls # feeds' embedded urls
for media in feed.get("media_content", []): for media in post.get("media_content", []):
if self.is_image_url(media.get("url"), media.get("type")): if self.is_image_url(media.get("url"), media.get("type")):
image_candidates.append(media["url"]) image_candidates.append(media["url"])
for enclosure in feed.get("enclosures", []): for enclosure in post.get("enclosures", []):
if self.is_image_url(enclosure.get("href"), enclosure.get("type")): if self.is_image_url(enclosure.get("href"), enclosure.get("type")):
image_candidates.append(enclosure["href"]) image_candidates.append(enclosure["href"])
for link in feed.get("links", []): for link in post.get("links", []):
if self.is_image_url(link.get("href"), link.get("type")): if self.is_image_url(link.get("href"), link.get("type")):
image_candidates.append(link["href"]) image_candidates.append(link["href"])
for media in feed.get("media_thumbnail", []): for media in post.get("media_thumbnail", []):
if self.is_image_url(media.get("url"), media.get("type")): if self.is_image_url(media.get("url"), media.get("type")):
image_candidates.append(media["url"]) image_candidates.append(media["url"])
for field in ["summary_detail", "content"]: for field in ["summary_detail", "content"]:
value = feed.get(field) value = post.get(field)
if isinstance(value, list): if isinstance(value, list):
values = [item.get("value", "") for item in value] values = [item.get("value", "") for item in value]
elif isinstance(value, dict): elif isinstance(value, dict):
@ -308,7 +309,7 @@ class Discorss:
match = self.img_src_filter.search(str(text)) match = self.img_src_filter.search(str(text))
if match and self.is_image_url(match.group(1)): if match and self.is_image_url(match.group(1)):
image_candidates.append(match.group(1)) image_candidates.append(match.group(1))
self.logger.debug("Found the following image candidates in %s...", feed["name"]) self.logger.debug("Found the following image candidates in %s...", post["title"])
for i in image_candidates: for i in image_candidates:
self.logger.debug("%s", i) self.logger.debug("%s", i)
if len(image_candidates) > 0: if len(image_candidates) > 0:
@ -336,7 +337,7 @@ class Discorss:
logging.basicConfig( logging.basicConfig(
filename=self.log_file_path, filename=self.log_file_path,
encoding="utf-8", encoding="utf-8",
level=logging.ERROR, level=logging.INFO,
datefmt="%m/%d/%Y %H:%M:%S", datefmt="%m/%d/%Y %H:%M:%S",
format="%(asctime)s [%(threadName)s] -> %(levelname)s: %(message)s", format="%(asctime)s [%(threadName)s] -> %(levelname)s: %(message)s",
) )