Parse HTML instead of RSS (to get more content)

This commit is contained in:
octt 2022-08-15 22:32:34 +00:00
parent 1bfd002a03
commit 60d5b90866
1 changed files with 87 additions and 47 deletions

View File

@ -4,6 +4,7 @@ import feedparser
import os
import urllib.request
import email, smtplib, ssl
from bs4 import BeautifulSoup
from email import encoders
from email.mime.base import MIMEBase
from email.mime.multipart import MIMEMultipart
@ -18,60 +19,97 @@ Password = "Example"
Server = "smtp.example.com"
Port = 465
OnlyOwnPosts = False
MailSend = False
LocalSave = True
MailSend = True
NoSpacesFile = False
StripWS = '\t\r\n'
def MakePathStr(Str):
for c in ('<>:"/\\|?* '):
for c in ('<>:"/\\|?*'):
Str = Str.replace(c, '_')
if NoSpacesFile:
Str = Str.replace(' ', '_')
return Str
def Main():
Feeds = [feedparser.parse(URL)['entries'] for URL in URLs]
for Feed in Feeds:
Feed.reverse() # Order from oldest to newest
for Entry in Feed:
if os.path.isfile('MastodonFeedToHTML.db'):
with open('MastodonFeedToHTML.db', 'r') as Db:
if Entry['id'] in Db.read().splitlines():
continue
for URL in URLs:
URL = URL.rstrip('/').rstrip('/with_replies') + '/with_replies'
Usertag = f"{URL.split('/')[-2]}@{URL.split('/')[-3]}"
try:
Response = urllib.request.urlopen(URL)
Data = Response.read()
Soup = BeautifulSoup(Data, 'html.parser')
Feed = Soup.find_all('div', class_='entry')
Feed.reverse() # Order from oldest to newest
try:
print(f"{Entry['id']} - {Entry['title']}")
for Entry in Feed:
Attached = ''
HTML = f"""\
<h1>{Entry['title']}</h1>
GlobalId = Entry.find('a', class_='u-url')['href'].lstrip('https://').lstrip('http://')
LocalId = GlobalId.split('/')[-1]
Username = Entry.find('a', class_='status__display-name').get_text().strip(StripWS)
Content = Entry.find('div', class_='e-content')
StatusPrepend = Entry.find('div', class_='status__prepend')
StatusPrepend = StatusPrepend.get_text().strip(StripWS)[len(Username):] if StatusPrepend else ''
StatusPrepend = ' ' + StatusPrepend.strip(StripWS) if StatusPrepend else ''
if OnlyOwnPosts and StatusPrepend:
continue
Title = Content.get_text().strip(StripWS)
Title = f"{Usertag}{StatusPrepend}: {Title[:32]}..."
for Emoji in Entry.find_all('img', class_='custom-emoji'):
Emoji['style'] = 'max-height:1em;'
Attachments = Entry.find('ul', class_='attachment-list__list')
if Attachments:
for Attachment in Attachments:
Href, Alt = '', ''
Attachment = str(Attachment).strip(StripWS).replace("'",'"').split('"')
for i,e in enumerate(Attachment):
if e.endswith('<a href='):
Href = Attachment[i+1]
elif e.endswith('title='):
Alt = "'".join(Attachment[i+1:-1])
if Href:
Response = urllib.request.urlopen(Href)
Data = Response.read()
Type = 'img' if Href.lower().endswith(('.png','.jpg','.jpeg')) else 'img'
Mime = f"image/{Href.lower().split('.')[-1]}"
Opening = f'<{Type} alt="{Alt}" title="{Alt}"' if Type == 'img' else f'<{Type} controls'
Closing = '>' if Type == 'img' else f"></{Type}>"
Attached += f"""{Opening} style="max-width:100%;max-height:100vh;" src="data:{Mime};base64,{base64.b64encode(Data).decode()}"{Closing}\n"""
Entry.find('img', class_='u-photo account__avatar')['style'] = 'max-height:2em;'#'display:none; visibility:hidden;'
Entry.find('div', class_='status__action-bar').replace_with('')
<div id="content">
{Entry['summary']}
if os.path.isfile('MastodonFeedToHTML.db'):
with open('MastodonFeedToHTML.db', 'r') as Db:
if GlobalId in Db.read().splitlines():
pass #continue
print(f"-> {LocalId} - {Title}")
HTML = f"""\
<h1>{Title}</h1>
<div>
{Entry}
{{ Replace:Attached }}
</div>
<br><hr><br>
<p>Published on {Entry['published']}</p>
<p>From <a href="{Entry['link']}">{Entry['link']}</a></p>
<br>
<h3>JSON dump</h3>
<div style="overflow-x:scroll;">
<xmp>
{Entry}
</xmp>
</div>
<p><i>Via <a href="https://gitlab.com/-/snippets/2388397">https://gitlab.com/-/snippets/2388397</a></i></p>
"""
Message = MIMEMultipart()
Message['From'] = Sender
Message['To'] = ', '.join(Receivers)
Message['Subject'] = Entry['title']
Message.attach(MIMEText(HTML.replace('{ Replace:Attached }', ''), 'html'))
#print(HTML)
for Link in Entry['links']:
if MailSend:
Message = MIMEMultipart()
Message['From'] = Sender
Message['To'] = ', '.join(Receivers)
Message['Subject'] = Entry['title']
Message.attach(MIMEText(HTML.replace('{ Replace:Attached }', ''), 'html'))
for Link in []:#Entry['links']:
if Link['type'].startswith(('audio/', 'image/', 'video/')):
Response = urllib.request.urlopen(Link['href'])
Data = Response.read()
@ -79,14 +117,16 @@ def Main():
Opening = f"<{Type}" if Type == 'img' else f"<{Type} controls"
Closing = '>' if Type == 'img' else f"></{Type}>"
Attached += f"""{Opening} style="max-width:100%;max-height:100vh;" src="data:{Link['type']};base64,{base64.b64encode(Data).decode()}"{Closing}\n"""
File = MIMEBase(Link['type'].split('/')[0], Link['type'].split('/')[1])
File.set_payload(Data)
encoders.encode_base64(File)
File.add_header(
"Content-Disposition",
f"attachment; filename= {Link['href'].split('/')[-1]}",
)
Message.attach(File)
if MailSend:
File = MIMEBase(Link['type'].split('/')[0], Link['type'].split('/')[1])
File.set_payload(Data)
encoders.encode_base64(File)
File.add_header(
"Content-Disposition",
f"attachment; filename= {Link['href'].split('/')[-1]}",
)
Message.attach(File)
if MailSend:
with smtplib.SMTP_SSL(Server, Port, context=ssl.create_default_context()) as Client:
@ -94,18 +134,18 @@ def Main():
Client.sendmail(Sender, Receivers, Message.as_string())
if LocalSave:
LocalBackupDir = MakePathStr(Entry['title_detail']['base'].lstrip('https://').lstrip('http://'))
LocalBackupDir = MakePathStr(Usertag)
if not os.path.isdir(LocalBackupDir):
os.mkdir(LocalBackupDir)
FileName = MakePathStr(f"{Entry['id'].split('/')[-1]} - {Entry['title']}")
FileName = MakePathStr(f"{GlobalId.split('/')[-1]} - {Title}")
with open(f'{LocalBackupDir}/{FileName}.html', 'w') as File:
File.write(HTML.replace('{ Replace:Attached }', Attached))
with open('MastodonFeedToHTML.db', 'a') as Db:
Db.write(Entry['id'] + '\n')
pass #Db.write(GlobalId + '\n')
except Exception:
raise
except Exception:
raise
if __name__ == '__main__':
Main()