From f4512b36da1fc9f461745c1f43e2dba10161ad8d Mon Sep 17 00:00:00 2001
From: Pekka Helenius <fincer89@hotmail.com>
Date: Mon, 4 May 2020 22:33:07 +0300
Subject: [PATCH] Remove unnecessary list structure

---
 pysitemap/base_crawler.py          | 86 +++++++++++++++---------------
 pysitemap/format_processors/xml.py | 17 +++---
 2 files changed, 50 insertions(+), 53 deletions(-)

diff --git a/pysitemap/base_crawler.py b/pysitemap/base_crawler.py
index def9fbc..ceabea7 100644
--- a/pysitemap/base_crawler.py
+++ b/pysitemap/base_crawler.py
@@ -197,8 +197,7 @@ class Crawler:
 #                        print("warning: ignoring tag data value:", key)
 
                 if len(arg_dict) == 1:
-                    tag.append(arg_dict)
-            tags.append(tag)
+                    tags.append(arg_dict)
         return tags
 
     async def addtagdata(self, tagdata, url, source_url_field,
@@ -209,48 +208,47 @@ class Crawler:
         :return: dictionary of validated tags (of single type)
         """
         tags = []
-        for data in tagdata:
-            for tag in data:
-                if not source_url_field in tag:
-                    continue
-                if not await self.contains(tag[source_url_field], excludes, rlist=True):
-
-                    if this_domain:
-                        if not tag[source_url_field].startswith('http'):
-                            for tag_root_url in tag_root_urls:
-                                if url.startswith(tag_root_url):
-                                    tag[source_url_field] = tag_root_url + tag[source_url_field]
-                                    break
-                    else:
-                        if not tag[source_url_field].startswith('http'):
-                            continue
-
-                    if (tag[source_url_field].startswith('http') and
-                        data not in done_list and
-                        tag[source_url_field] not in self.busy and
-                        tag[source_url_field] not in self.todo_queue):
-                        self.todo_queue.add(tag[source_url_field])
-                        # Acquire semaphore
-                        await self.sem.acquire()
-                        # Create async task
-                        task = asyncio.ensure_future(self.mimechecker(tag[source_url_field], mimetype))
-                        # Add collback into task to release semaphore
-                        task.add_done_callback(lambda t: self.sem.release())
-                        # Callback to remove task from tasks
-                        task.add_done_callback(self.tasks.remove)
-                        # Add task into tasks
-                        self.tasks.add(task)
-                        try:
-                            result = await asyncio.wait_for(task, timeout=20)
-                            if (result):
-                                tags.append(data)
-
-                        except asyncio.TimeoutError:
-                            print("couldn't add tag data:", tag[source_url_field])
-                            task.cancel()
-                            pass
-
-            done_list.extend(tags)
+        for tag in tagdata:
+            if not source_url_field in tag:
+                continue
+            if not await self.contains(tag[source_url_field], excludes, rlist=True):
+
+                if this_domain:
+                    if not tag[source_url_field].startswith('http'):
+                        for tag_root_url in tag_root_urls:
+                            if url.startswith(tag_root_url):
+                                tag[source_url_field] = tag_root_url + tag[source_url_field]
+                                break
+                else:
+                    if not tag[source_url_field].startswith('http'):
+                        continue
+
+                if (tag[source_url_field].startswith('http') and
+                    tag not in done_list and
+                    tag[source_url_field] not in self.busy and
+                    tag[source_url_field] not in self.todo_queue):
+                    self.todo_queue.add(tag[source_url_field])
+                    # Acquire semaphore
+                    await self.sem.acquire()
+                    # Create async task
+                    task = asyncio.ensure_future(self.mimechecker(tag[source_url_field], mimetype))
+                    # Add collback into task to release semaphore
+                    task.add_done_callback(lambda t: self.sem.release())
+                    # Callback to remove task from tasks
+                    task.add_done_callback(self.tasks.remove)
+                    # Add task into tasks
+                    self.tasks.add(task)
+                    try:
+                        result = await asyncio.wait_for(task, timeout=20)
+                        if (result):
+                            tags.append(tag)
+
+                    except asyncio.TimeoutError:
+                        print("couldn't add tag data:", tag[source_url_field])
+                        task.cancel()
+                        pass
+
+        done_list.extend(tags)
         return tags
 
     async def process(self, url):
diff --git a/pysitemap/format_processors/xml.py b/pysitemap/format_processors/xml.py
index 1b274a2..b8fb3ba 100644
--- a/pysitemap/format_processors/xml.py
+++ b/pysitemap/format_processors/xml.py
@@ -39,15 +39,14 @@ class XMLWriter():
 
                 if len(image_data) > 0:
                     for image in image_data:
-                        for arg in image:
-                            image_xml = ""
-                            if 'src' in arg:          image_xml += "<image:loc>{}</image:loc>".format(arg['src'])
-                            if 'title' in arg:        image_xml += "<image:title>{}</image:title>".format(arg['title'])
-                            if 'caption' in arg:      image_xml += "<image:caption>{}</image:caption>".format(arg['caption'])
-                            if 'geo_location' in arg: image_xml += "<image:geo_location>{}</image:geo_location>".format(arg['geo_location'])
-                            if 'license' in arg:      image_xml += "<image:license>{}</image:license>".format(arg['license'])
-
-                            url += "<image:image>{}</image:image>".format(image_xml)
+                        image_xml = ""
+                        if 'src' in image:          image_xml += "<image:loc>{}</image:loc>".format(image['src'])
+                        if 'title' in image:        image_xml += "<image:title>{}</image:title>".format(image['title'])
+                        if 'caption' in image:      image_xml += "<image:caption>{}</image:caption>".format(image['caption'])
+                        if 'geo_location' in image: image_xml += "<image:geo_location>{}</image:geo_location>".format(image['geo_location'])
+                        if 'license' in image:      image_xml += "<image:license>{}</image:license>".format(image['license'])
+
+                        url += "<image:image>{}</image:image>".format(image_xml)
 
                 await writer('<url>{}</url>\n'.format(url))