From 66c5298507f2911341a67ffc9b44e44514093f8b Mon Sep 17 00:00:00 2001
From: cquest <cquest@openstreetmap.fr>
Date: Sat, 5 Nov 2022 09:45:06 +0100
Subject: [PATCH] support RSS feeds

---
 tootbot.py | 63 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 63 insertions(+)

diff --git a/tootbot.py b/tootbot.py
index c114334..f8ed4b2 100755
--- a/tootbot.py
+++ b/tootbot.py
@@ -76,6 +76,69 @@ except:
 if source[:4] == 'http':
     d = feedparser.parse(source)
     twitter = None
+    for t in reversed(d.entries):
+        # check if this tweet has been processed
+        if id in t:
+            id = t.id
+        else:
+            id = t.title
+        db.execute('SELECT * FROM tweets WHERE tweet = ? AND twitter = ?  and mastodon = ? and instance = ?', (id, source, mastodon, instance))  # noqa
+        last = db.fetchone()
+        dt = t.published_parsed
+        age = datetime.now()-datetime(dt.tm_year, dt.tm_mon, dt.tm_mday,
+                                    dt.tm_hour, dt.tm_min, dt.tm_sec)
+        # process only unprocessed tweets less than 1 day old, after delay
+        if last is None and age < timedelta(days=days) and age > timedelta(days=delay):
+            c = t.title
+            if twitter and t.author.lower() != ('(@%s)' % twitter).lower():
+                c = ("RT https://twitter.com/%s\n" % t.author[2:-1]) + c
+            toot_media = []
+            # get the pictures...
+            if 'summary' in t:
+                for p in re.finditer(r"https://pbs.twimg.com/[^ \xa0\"]*", t.summary):
+                    media = requests.get(p.group(0))
+                    media_posted = mastodon_api.media_post(
+                        media.content, mime_type=media.headers.get('content-type'))
+                    toot_media.append(media_posted['id'])
+
+            if 'links' in t:
+                for l in t.links:
+                    if l.type in ('image/jpg', 'image/png'):
+                        media = requests.get(l.url)
+                        media_posted = mastodon_api.media_post(
+                            media.content, mime_type=media.headers.get('content-type'))
+                        toot_media.append(media_posted['id'])
+
+            # replace short links by original URL
+            m = re.search(r"http[^ \xa0]*", c)
+            if m is not None:
+                l = m.group(0)
+                r = requests.get(l, allow_redirects=False)
+                if r.status_code in {301, 302}:
+                    c = c.replace(l, r.headers.get('Location'))
+
+            # remove ellipsis
+            c = c.replace('\xa0…', ' ')
+
+            if 'authors' in t:
+                c = c + '\nSource: ' + t.authors[0].name
+            c = c + '\n\n' + t.link
+
+            if tags:
+                c = c + '\n' + tags
+
+            if toot_media is not None:
+                toot = mastodon_api.status_post(c,
+                                                in_reply_to_id=None,
+                                                media_ids=toot_media,
+                                                sensitive=False,
+                                                visibility='public',
+                                                spoiler_text=None)
+                if "id" in toot:
+                    db.execute("INSERT INTO tweets VALUES ( ? , ? , ? , ? , ? )",
+                            (id, toot["id"], source, mastodon, instance))
+                    sql.commit()
+
 else:
     d = feedparser.parse('http://twitrss.me/twitter_user_to_rss/?user='+source)
     twitter = source