Implement fetching website metadata

bookmarks/migrations/0001_initial.py

@@ -1,4 +1,4 @@
-# Generated by Django 2.2.2 on 2019-06-28 22:16
+# Generated by Django 2.2.2 on 2019-06-28 23:49
 
 from django.conf import settings
 from django.db import migrations, models
@@ -21,8 +21,8 @@ class Migration(migrations.Migration):
                 ('url', models.URLField()),
                 ('title', models.CharField(max_length=512)),
                 ('description', models.TextField()),
-                ('website_title', models.CharField(max_length=512)),
-                ('website_description', models.TextField()),
+                ('website_title', models.CharField(blank=True, max_length=512, null=True)),
+                ('website_description', models.TextField(blank=True, null=True)),
                 ('unread', models.BooleanField(default=True)),
                 ('date_added', models.DateTimeField()),
                 ('date_modified', models.DateTimeField()),

bookmarks/models.py

@@ -7,8 +7,8 @@ class Bookmark(models.Model):
     url = models.URLField()
     title = models.CharField(max_length=512)
     description = models.TextField()
-    website_title = models.CharField(max_length=512)
-    website_description = models.TextField()
+    website_title = models.CharField(max_length=512, blank=True, null=True)
+    website_description = models.TextField(blank=True, null=True)
     unread = models.BooleanField(default=True)
     date_added = models.DateTimeField()
     date_modified = models.DateTimeField()

bookmarks/services/bookmarks.py

@@ -1,3 +1,5 @@
+import requests
+from bs4 import BeautifulSoup
 from django.contrib.auth.models import User
 from django.utils import timezone
 
@@ -24,7 +26,22 @@ def update_bookmark(bookmark: Bookmark):
 
 
 def _update_website_metadata(bookmark: Bookmark):
-    # TODO: Load website metadata
-    bookmark.website_title = 'Title from website'
-    bookmark.website_description = 'Description from website'
-    pass
+    # noinspection PyBroadException
+    try:
+        page_text = load_page(bookmark.url)
+        soup = BeautifulSoup(page_text, 'html.parser')
+
+        title = soup.title.string if soup.title is not None else None
+        description_tag = soup.find('meta', attrs={'name': 'description'})
+        description = description_tag['content'] if description_tag is not None else None
+
+        bookmark.website_title = title
+        bookmark.website_description = description
+    except Exception:
+        bookmark.website_title = None
+        bookmark.website_description = None
+
+
+def load_page(url: str):
+    r = requests.get(url)
+    return r.text

requirements.txt

@@ -1,3 +1,11 @@
+beautifulsoup4==4.7.1
+certifi==2019.6.16
+chardet==3.0.4
 Django==2.2.2
+django-picklefield==2.0
+idna==2.8
 pytz==2019.1
+requests==2.22.0
+soupsieve==1.9.2
 sqlparse==0.3.0
+urllib3==1.25.3