crawler: use UPSERT statements

Avoid potential race conditions

morss/crawler.py

@@ -585,14 +585,8 @@ class SQLiteCache(BaseCache):
         value[3] = sqlite3.Binary(value[3]) # data
         value = tuple(value)
 
-        if url in self:
         with self.con:
-                self.con.execute('UPDATE data SET code=?, msg=?, headers=?, data=?, timestamp=? WHERE url=?',
-                    value + (url,))
-
-        else:
-            with self.con:
-                self.con.execute('INSERT INTO data VALUES (?,?,?,?,?,?)', (url,) + value)
+            self.con.execute('INSERT INTO data VALUES (?,?,?,?,?,?) ON CONFLICT(url) DO UPDATE SET code=?, msg=?, headers=?, data=?, timestamp=?', (url,) + value + value)
 
 
 import pymysql.cursors
@@ -622,14 +616,9 @@ class MySQLCacheHandler(BaseCache):
         return row[1:]
 
     def __setitem__(self, url, value): # (code, msg, headers, data, timestamp)
-        if url in self:
         with self.cursor() as cursor:
-                cursor.execute('UPDATE data SET code=%s, msg=%s, headers=%s, data=%s, timestamp=%s WHERE url=%s',
-                    value + (url,))
-
-        else:
-            with self.cursor() as cursor:
-                cursor.execute('INSERT INTO data VALUES (%s,%s,%s,%s,%s,%s)', (url,) + value)
+            cursor.execute('INSERT INTO data VALUES (%s,%s,%s,%s,%s,%s) ON DUPLICATE KEY UPDATE code=%s, msg=%s, headers=%s, data=%s, timestamp=%s',
+                (url,) + value + value)
 
 
 if __name__ == '__main__':

morss/morss.py

@@ -279,7 +279,7 @@ def ItemBefore(item, options):
 
 def ItemAfter(item, options):
     if options.clip and item.desc and item.content:
-        item.content = item.desc + "<br/><br/><center>* * *</center><br/><br/>" + item.content
+        item.content = item.desc + "<br/><br/><hr/><br/><br/>" + item.content
         del item.desc
 
     if options.nolink and item.content:
@@ -303,7 +303,7 @@ def FeedFetch(url, options):
         delay = 0
 
     try:
-        req = crawler.adv_get(url=url, follow='rss', delay=delay, timeout=TIMEOUT * 2)
+        req = crawler.adv_get(url=url, follow=('rss' if not options.items else None), delay=delay, timeout=TIMEOUT * 2)
 
     except (IOError, HTTPException):
         raise MorssException('Error downloading feed')