various improvements to the crawler (better use of coroutines, test if an article should be updated). tags are now retrieved for the k-means clustering (previously achived with the content of articles)

1 files changed, 22 insertions, 0 deletions

diff --git a/src/web/models/tag.py b/src/web/models/tag.py
new file mode 100644
index 00000000..8d7fe4d4
--- /dev/null
+++ b/src/web/models/tag.py
@@ -0,0 +1,22 @@
+#! /usr/bin/env python
+# -*- coding: utf-8 -*-
+
+from sqlalchemy import Column, ForeignKey, Integer, String
+from sqlalchemy.orm import relationship
+
+from bootstrap import db
+
+
+class Tag(db.Model):
+    text = Column(String, primary_key=True, unique=False)
+
+    # foreign keys
+    article_id = Column(Integer, ForeignKey('article.id', ondelete='CASCADE'),
+                        primary_key=True)
+
+    # relationships
+    article = relationship('Article', back_populates='tag_objs',
+                           foreign_keys=[article_id])
+
+    def __init__(self, text):
+        self.text = text