More steps towards parsing the file.

2 files changed, 28 insertions, 4 deletions

diff --git a/comments.xml b/comments.xml
index cd257b1..ffe98a9 100644
--- a/comments.xml
+++ b/comments.xml
@@ -8680,7 +8680,7 @@ xsi:schemaLocation="http://disqus.com/api/schemas/1.0/disqus.xsd http://disqus.c
     </message>
     <createdAt>2021-11-18T16:16:33Z</createdAt>
     <isDeleted>false</isDeleted>
-    <isSpam>false</isSpam>
+    <isSpam>true</isSpam>
     <author>
       <name>morgan</name>
       <isAnonymous>false</isAnonymous>
diff --git a/xml2static_rst.py b/xml2static_rst.py
index 9bbe0d6..f5c0d68 100644
--- a/xml2static_rst.py
+++ b/xml2static_rst.py
@@ -1,6 +1,8 @@
 #!/usr/bin/python3
 
-import os.path
+from os.path import basename, exists, normpath, splitext
+from pprint import pprint
+from urllib.parse import urlparse
 from xml.etree import ElementTree as ET
 
 ns = {'dflt': 'http://disqus.com',
@@ -9,9 +11,31 @@ ns = {'dflt': 'http://disqus.com',
 
 tree = ET.parse("comments.xml")
 root = tree.getroot()
+threads = {}
+for thread in root.findall("dflt:thread", ns):
+    thread_id = thread.attrib[f"{{{ns['xsi']}}}id"]
+    thread_link = thread.find("dflt:link", ns).text.strip()
+    if thread_id not in threads:
+        threads[thread_id] = {}
+    threads[thread_id]['link'] = thread_link
+    threads[thread_id]['blurb'] = splitext(basename(normpath(urlparse(thread_link).path)))[0].strip()
+    threads[thread_id]['msgs'] = []
+
+out = {}
 for com_post in root.findall("dflt:post", ns):
     if com_post.find('dflt:isSpam', ns).text == 'false':
-        print(ET.tostring(com_post, encoding='unicode', default_namespace=ns['dflt']))
-
+        thread = com_post.find('dflt:thread', ns)
+        thread_id = thread.attrib[f"{{{ns['xsi']}}}id"]
+        blurb = threads[thread_id]['blurb']
+        if blurb not in out:
+            out[blurb] = ""
+        msg = com_post.find('dflt:message', ns).text
+        if msg is not None:
+            out[blurb] += msg  + '\n'
+    
+for post in out:
+    if len(out[post].strip()) > 0:
+        print(post + '\n' + out[post])
+    
 # if not os.path.exists('comments/'):
 #     os.mkdir('comments')