adding markdown support

This commit is contained in:
manetta 2022-02-21 17:47:04 +01:00
parent bfc4f02735
commit 3f236e77ff

View File

@ -1,8 +1,9 @@
import feedparser
from simpledatabase import SimpleDatabase
import json
from datetime import datetime, date, timedelta
from backports.zoneinfo import ZoneInfo
from datetime import date, timedelta
import pypandoc
import re
def update():
""" Update all feeds """
@ -32,7 +33,7 @@ def update():
year = post['published_parsed'][0]
month = post['published_parsed'][1]
day = post['published_parsed'][2]
post_date = datetime(year, month, day, tzinfo=ZoneInfo("Europe/Amsterdam"))
post_date = date(year, month, day)
if not str(post_date) in tmp['all_posts_sorted']:
tmp['all_posts_sorted'][str(post_date)] = []
@ -56,23 +57,23 @@ def latest(num):
dates = [key for key in db['all_posts_sorted'].keys()]
dates.sort(reverse=True)
request = []
feed = []
for date in dates:
posts = db['all_posts_sorted'][date]
for post in posts:
if len(request) < int(num):
request.append(post)
if len(feed) < int(num):
feed.append(post)
else:
break
return request
return feed
def today():
""" Collect posts from today """
db = load()
today = date.today()
request = []
feed = []
for date_str, posts in db['all_posts_sorted'].items():
year = int(date_str.split('-')[0])
@ -83,15 +84,15 @@ def today():
# Check if any posts are published today
if d == today:
for post in posts:
request.append(post)
feed.append(post)
return request
return feed
def past(days):
""" Collect posts from a number of past <days> """
db = load()
point_in_the_past = date.today() - timedelta(int(days))
request = []
feed = []
for date_str, posts in db['all_posts_sorted'].items():
year = int(date_str.split('-')[0])
@ -101,6 +102,38 @@ def past(days):
if d > point_in_the_past:
for post in posts:
request.append(post)
feed.append(post)
return request
feed.reverse()
return feed
def md(feed):
md_feed = ''
for post in feed:
post_content = pypandoc.convert_text(
post['summary'], 'md', format='html'
)
if post['links']:
for link in post['links']:
if link['rel'] == 'enclosure':
if 'pdf' in link['type']:
post_content += f"\n<{ link['href'] }>\n"
post_content = re.sub(r'\n.*(-)\1{5,}.*\n', "", post_content) # remove all ------ lines from varia website posts
len_link = len(post['link']) + 4
len_line_dash = len_link * '-'
len_line_space = len_link * ' '
len_date_space = (len_link - len(post['published']) - 2 ) * ' '
md_feed += "------------------------- \n\n"
md_feed += f"# { post['title'] }" + "{.post_title} \n\n"
md_feed += f"""| |{ len_line_space }|
|-----------:|{ len_line_dash }|
| **posted** | { post['published'] }{ len_date_space } |
| **from** | <{ post['link'] }> |
"""
md_feed += f"{ post_content } \n\n"
return md_feed