blankie
/
blankx.gitlab.io
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Remove beautifulsoup4

This commit is contained in:
blank X 2021-07-21 15:14:30 +07:00
parent 17e046bf2f
commit e7bd1c80e5
Signed by: blankie
GPG Key ID: CC15FC822C7F61F5
2 changed files with 13 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
gensbbsrss.py
View File

@ -1,11 +1,10 @@
import os
from io import BytesIO
from datetime import datetime
from xml.etree import ElementTree
from bs4 import BeautifulSoup
with open('index.html') as file:
soup = BeautifulSoup(file.read())
sbbsbase = soup.find('link', rel='canonical')['href']
tree = ElementTree.ElementTree().parse('index.html')
sbbsbase = tree.find('./head/link[@rel="canonical"]').attrib['href']
feed = ElementTree.Element('rss', version='2.0')
channel = ElementTree.SubElement(feed, 'channel')
@ -17,23 +16,26 @@ description = ElementTree.SubElement(channel, 'description')
description.text = 'just a showcase of software being broken :)'
language = ElementTree.SubElement(channel, 'language')
language.text = 'en-us'
file = BytesIO()
def parse_file(i):
with open(i) as file:
soup = BeautifulSoup(file.read())
tree = ElementTree.ElementTree().parse(i)
item = ElementTree.Element('item')
title = ElementTree.SubElement(item, 'title')
title.text = soup.h1.string
title.text = tree.find('body').find('h1').text
link = ElementTree.SubElement(item, 'link')
link.text = soup.find('link', rel='canonical')['href']
link.text = tree.find('./head/link[@rel="canonical"]').attrib['href']
guid = ElementTree.SubElement(item, 'guid')
guid.text = f'sbbs/{os.path.splitext(i)[0]}'
description = ElementTree.SubElement(item, 'description')
description.text = str(soup.find('div', class_='content'))
return (datetime.fromisoformat(soup.find('meta', {'name': 'created'})['content']), item)
ElementTree.ElementTree(tree.find('./body/div[@class="content"]')).write(file, 'utf-8', method='html')
description.text = file.getvalue().decode()
file.seek(0)
file.truncate(0)
return (datetime.fromisoformat(tree.find('./head/meta[@name="created"]').attrib['content']), item)
for date, i in sorted(map(parse_file, filter(lambda i: i not in ('index.html', 'index.xml'), os.listdir('.'))), reverse=True, key=lambda i: i[0]):
# http://johnbokma.com/blog/2019/10/09/rfc-822-and-rfc-3339-dates-in-python.html
ctime = date.ctime()
pubdate = ElementTree.SubElement(i, 'pubDate')
pubdate.text = f"{ctime[0:3]}, {date.day:02d} {ctime[4:7]} {date.strftime(' %Y %H:%M:%S %z')}"
channel.append(i)
ElementTree.ElementTree(feed).write('index.xml', 'utf-8')
ElementTree.ElementTree(feed).write('index.xml', 'utf-8', True)

1
requirements.txt
View File

@ -1,2 +1 @@
feedparser
beautifulsoup4