twoot.py

@@ -173,10 +173,7 @@ Only used by `get_timeline()`.
 :param thread_url: url of the first tweet in thread
 :return: list of tuples with url of tweet replied-to (or None) and content of tweet
 """
-def _get_rest_of_thread(session, headers, nitter_url, thread_url, first_item):
-    # Add first item to timeline
-    timeline = [(None, first_item)]
-
+def _get_rest_of_thread(session, headers, nitter_url, thread_url):
     logging.debug("Downloading tweets in thread from separate page")
     # Download page with thread
     url = nitter_url + thread_url
@@ -209,19 +206,15 @@ def _get_rest_of_thread(session, headers, nitter_url, thread_url, first_item):
     list = after_tweet.find_all('div', class_='timeline-item')
 
     # Build timeline of tuples
+    timeline = []
     previous_tweet_url = thread_url
     for item in list:
             timeline.append((previous_tweet_url, item))
             # Get the url of the tweet
-            tweet_link_tag = item.find('a', class_='tweet-link')
-            if tweet_link_tag is not None:
-                previous_tweet_url = tweet_link_tag.get('href').strip('#m')
-            else:
-                previous_tweet_url = None
+            previous_tweet_url = item.find('a', class_='tweet-link')
+            if previous_tweet_url is  None:
                 logging.error('Thread tweet is missing link tag')
 
-    # return timeline in reverse chronological order
-    timeline.reverse()
     return timeline
 
 
@@ -296,10 +289,12 @@ def get_timeline(nitter_url):
             # Get the url of the tweet
             thread_link_tag = item.find('a', class_='tweet-link')
             if thread_link_tag is not None:
-                thread_url = thread_link_tag.get('href').strip('#m')
+                thread_url = thread_link_tag.get('href')
+
+            timeline.append((thread_url, first_item))
 
             # Get the rest of the items of the thread
-            timeline.extend(_get_rest_of_thread(session, headers, nitter_url, thread_url, first_item))
+            timeline.extend(_get_rest_of_thread(session, headers, nitter_url, thread_url))
         else:
             # Ignore other classes
             continue
@@ -964,7 +959,7 @@ def main(argv):
     tweets = []
     out_date_cnt = 0
     in_db_cnt = 0
-    for replied_to_tweet, status in timeline:
+    for reply_to, status in timeline:
         # Extract tweet ID and status ID
         tweet_id = status.find('a', class_='tweet-link').get('href').strip('#m')
         status_id = tweet_id.split('/')[3]
@@ -1127,7 +1122,7 @@ def main(argv):
             "tweet_text": tweet_text,
             "video": video_file,
             "photos": photos,
-            "replied_to_tweet": replied_to_tweet,
+            "reply-to": reply_to,
         }
         tweets.append(tweet)
 
@@ -1195,25 +1190,13 @@ def main(argv):
                             TypeError):  # Media cannot be uploaded (invalid format, dead link, etc.)
                         pass
 
-        # Find in database toot id of replied_to_tweet
-        replied_to_toot = None
-        if tweet['replied_to_tweet'] is not None:
-            logging.debug("Searching db for toot corresponding to replied-to-tweet " + tweet['replied_to_tweet'])
-            db.execute("SELECT toot_id FROM toots WHERE tweet_id=?", [tweet['replied_to_tweet']])
-            replied_to_toot = db.fetchone()
-
-            if replied_to_toot is None:
-                logging.warning('Replied-to tweet %s not found in database', tweet['replied_to_tweet'])
-            else:
-                logging.debug("toot %s found", replied_to_toot)
-
         # Post toot
         toot = {}
         try:
             if len(media_ids) == 0:
-                toot = mastodon.status_post(tweet['tweet_text'], replied_to_toot)
+                toot = mastodon.status_post(tweet['tweet_text'])
             else:
-                toot = mastodon.status_post(tweet['tweet_text'], replied_to_toot, media_ids=media_ids)
+                toot = mastodon.status_post(tweet['tweet_text'], media_ids=media_ids)
 
         except MastodonAPIError:
             # Assuming this is an: