Collect all available information.

Fixes: https://todo.sr.ht/~mcepl/devel/23

1 files changed, 34 insertions, 10 deletions

diff --git a/xml2static_rst.py b/xml2static_rst.py
index be936a2..54989a8 100644
--- a/xml2static_rst.py
+++ b/xml2static_rst.py
@@ -1,5 +1,6 @@
 #!/usr/bin/python3
 
+from datetime import datetime
 import logging
 import sys
 from os.path import basename, exists, normpath, splitext
@@ -11,10 +12,10 @@ from urllib.parse import urlparse
 from xml.etree import ElementTree as ET
 
 ns = {'dflt': 'http://disqus.com',
-      'dsi': 'http://disqus.com/disqus-internals',
-      'dsq': 'http://www.w3.org/2001/XMLSchema-instance'}
+      'dsq': 'http://disqus.com/disqus-internals',
+      'xsi': 'http://www.w3.org/2001/XMLSchema-instance'}
 logging.basicConfig(format='%(levelname)s:%(funcName)s:%(message)s',
-                    level=logging.INFO)
+                    level=logging.DEBUG)
 log = logging.getLogger()
 
 def init(filename: str) -> ET.Element:
@@ -30,7 +31,7 @@ def init(filename: str) -> ET.Element:
 def collect_threads(root: ET.Element) -> Dict[int, Dict[str, str|List]]:
     threads: Dict[int, Dict[str, str|List]] = {}
     for thread in root.findall("dflt:thread", ns):
-        thread_id = int(thread.get(f"{{{ns['dsi']}}}id", 0))
+        thread_id = int(thread.get(f"{{{ns['dsq']}}}id", 0))
         thread_link = thread.findtext("dflt:link", '', ns).strip()
         if thread_id not in threads:
             threads[thread_id] = {}
@@ -49,11 +50,26 @@ def collect_posts(root: ET.Element, threads: dict) -> dict:
         is_del = com_post.findtext('dflt:isDeleted', '', ns) == 'true'
         if not (is_spam or is_del):
             print('.', end='', file=sys.stderr, flush=True)
+            comment_id = int(com_post.get(f"{{{ns['dsq']}}}id", 0))
             thread = com_post.find('dflt:thread', ns)
-            thread_id = int(thread.get(f"{{{ns['dsi']}}}id", 0))
+            thread_id = int(thread.get(f"{{{ns['dsq']}}}id", 0))
             blurb = threads[thread_id]['blurb']
             if blurb not in out:
-                out[blurb] = ""
+                out[blurb] = {}
+                out[blurb]['msg'] = ''
+
+            parent = com_post.find('dflt:parent', ns)
+            if parent is not None:
+                parent_id = int(parent.get(f"{{{ns['dsq']}}}id", 0))
+            else:
+                parent_id = 0
+
+            created_str = com_post.findtext('dflt:createdAt', '', ns).strip()
+            if created_str:
+                created_at = datetime.strptime(created_str, "%Y-%m-%dT%H:%M:%SZ")
+            else:
+                created_at = datetime.fromtimestamp(0)
+
             html_msg = com_post.find('dflt:message', ns)
             if html_msg is not None:
                 html_msg = html_msg.text
@@ -61,10 +77,18 @@ def collect_posts(root: ET.Element, threads: dict) -> dict:
                                 stderr=DEVNULL, stdout=PIPE, stdin=PIPE,
                                 encoding='utf-8')
                 html_msg = pd_proc.communicate(html_msg)[0]
-                out[blurb] += html_msg  + '\n'
+                if created_at:
+                    html_msg = f":date: {created_at:%d.%m.%Y}\n\n{html_msg}"
+                if parent_id:
+                    html_msg = f":parentID#: {parent_id}\n{html_msg}"
+                if comment_id:
+                    html_msg = f":commentID#: {comment_id}\n{html_msg}"
+                out[blurb]['msg'] += html_msg  + '\n'
+
+
     print('', file=sys.stderr)
     return out
-    
+
 # if not os.path.exists('comments/'):
 #     os.mkdir('comments')
 
@@ -73,6 +97,6 @@ if __name__=='__main__':
     threads = collect_threads(root)
     posts = collect_posts(root, threads)
     for post in posts:
-        if len(posts[post].strip()) > 0:
-            print(post + '\n' + posts[post])
+        print('\n' + post)
+        pprint(posts[post])