[locofocos]

Hello! This is my first recipe. It's for the site https://www.theflipside.io/ Hope it's useful to someone. They don't have an RSS feed.

Caveats:

I'm probably not using "feeds" properly. I'm hardcoding it inside parse_index, but this site only has a single feed so I didn't bother to consume "feeds".

Dates aren't being parsed, so "oldest_article" doesn't take effect.

Otherwise, I'm pretty happy with the output!

#!/usr/bin/env python
# vim:fileencoding=utf-8
from calibre.web.feeds.news import BasicNewsRecipe

class AdvancedUserRecipe1659410049(BasicNewsRecipe):
    title          = 'The Flip Side'
    oldest_article = 50 # dates aren't being parsed so this doesn't have any effect
    max_articles_per_feed = 25
    auto_cleanup   = False
    
    remove_tags_before  = [
        dict(name='div', class_='menu-button-nav')
    ]
    remove_tags_after = [
        dict(name='div', class_='on-the-bright-side')
    ]
    remove_tags = [
        dict(name='div', class_='on-the-bright-side'),
        dict(name='img', class_='archives')
    ]


    feeds          = [
        ('The Flip Side', 'https://www.theflipside.io/archives'),
    ]
    
    def parse_index(self):
        articles = []
        
        soup = self.index_to_soup('https://www.theflipside.io/archives')
        
        for div in soup.findAll(True, attrs={'class':['collection-item']}):
            month = div.find_all('h4')[0].get_text()
            day =  div.find_all('h4')[1].get_text()
            date = month + " " + day
            title = div.find("h3").get_text() + ' - ' + date 
            description = ''
            url = "https://www.theflipside.io" + div.find("a")['href']
            
            article = dict(month=month, date=date, title=title, description=description, url=url)
            
            articles.append(article)
            
        return [('The Flip Side', articles)]

    
    def get_article_url(self, article):
        result = re.search('<a href="([^>]*)">', article.summary)
        url = result.group(1)
        return url
    
    # Convert all links to text
    # https://www.mobileread.com/forums/showpost.php?p=1231995&postcount=9
    def preprocess_html(self, soup):
        for alink in soup.findAll('a'):
            if alink.string is not None:
               tstr = alink.string
               alink.replaceWith(tstr)
        return soup