Applying nice styles.

vitorfs · Apr 11, 2020 · a1de7a4 · a1de7a4
1 parent 3af9540
commit a1de7a4
Show file tree

Hide file tree

Showing 5 changed files with 73 additions and 42 deletions.
diff --git a/bootcamp/news/metadatareader.py b/bootcamp/news/metadatareader.py
@@ -4,18 +4,31 @@
 from bs4 import BeautifulSoup, Comment
 from urllib.parse import urljoin
 
+
 class Metadata:
     url = ""
-    type = "" # https://ogp.me/#types
+    type = ""  # https://ogp.me/#types
     title = ""
     description = ""
     image = ""
 
     def __str__(self):
-        return "{url: " + self.url + ", type: " + self.type + ", title: " + self.title + ", description: " + self.description + ", image: " + self.image + "}"
+        return (
+            "{url: "
+            + self.url
+            + ", type: "
+            + self.type
+            + ", title: "
+            + self.title
+            + ", description: "
+            + self.description
+            + ", image: "
+            + self.image
+            + "}"
+        )
 
-class Metadatareader:
 
+class Metadatareader:
     @staticmethod
     def get_metadata_from_url_in_text(text):
         # look for the first url in the text
@@ -48,13 +61,21 @@ def get_url_metadata(url):
         for meta in soup.findAll("meta"):
             # priorize using Open Graph Protocol
             # https://ogp.me/
-            metadata.type = Metadatareader.get_meta_property(meta, "og:type", metadata.type)
-            metadata.title = Metadatareader.get_meta_property(meta, "og:title", metadata.title)
-            metadata.description = Metadatareader.get_meta_property(meta, "og:description", metadata.description)
-            metadata.image = Metadatareader.get_meta_property(meta, "og:image", metadata.image)
+            metadata.type = Metadatareader.get_meta_property(
+                meta, "og:type", metadata.type
+            )
+            metadata.title = Metadatareader.get_meta_property(
+                meta, "og:title", metadata.title
+            )
+            metadata.description = Metadatareader.get_meta_property(
+                meta, "og:description", metadata.description
+            )
+            metadata.image = Metadatareader.get_meta_property(
+                meta, "og:image", metadata.image
+            )
             if metadata.image:
                 metadata.image = urljoin(url, metadata.image)
-            
+
         if not metadata.title and soup.title:
             # use page title
             metadata.title = soup.title.text
@@ -68,28 +89,36 @@ def get_url_metadata(url):
         if not metadata.description and soup.body:
             # use text from body
             for text in soup.body.find_all(string=True):
-                if text.parent.name != "script" and text.parent.name != "style" and not isinstance(text, Comment):
+                if (
+                    text.parent.name != "script"
+                    and text.parent.name != "style"
+                    and not isinstance(text, Comment)
+                ):
                     metadata.description += text
 
         if metadata.description:
             # remove white spaces and break lines
             metadata.description = re.sub("\n|\r|\t", " ", metadata.description)
             metadata.description = re.sub(" +", " ", metadata.description)
             metadata.description = metadata.description.strip()
-            
+
         return metadata
 
     @staticmethod
     def get_final_url(url, timeout=5):
         # get final url after all redirections
         # get http response header
         # look for the "Location: " header
-        proc = subprocess.Popen([
-                    "curl",
-                    "-Ls",#follow redirect 301 and silently
-                    "-I",#don't download html body
-                    url
-                ], stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+        proc = subprocess.Popen(
+            [
+                "curl",
+                "-Ls",  # follow redirect 301 and silently
+                "-I",  # don't download html body
+                url,
+            ],
+            stdout=subprocess.PIPE,
+            stderr=subprocess.PIPE,
+        )
         try:
             out, err = proc.communicate(timeout=timeout)
         except TimeoutExpired:
@@ -104,13 +133,17 @@ def get_final_url(url, timeout=5):
     @staticmethod
     def get_url_content(url, timeout=5):
         # get url html
-        proc = subprocess.Popen([
-                    "curl",
-                    "-i",
-                    "-k",#ignore ssl certificate requisite
-                    "-L",#follow redirect 301
-                    url
-                ], stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+        proc = subprocess.Popen(
+            [
+                "curl",
+                "-i",
+                "-k",  # ignore ssl certificate requisite
+                "-L",  # follow redirect 301
+                url,
+            ],
+            stdout=subprocess.PIPE,
+            stderr=subprocess.PIPE,
+        )
         try:
             out, err = proc.communicate(timeout=timeout)
         except TimeoutExpired:
@@ -122,4 +155,4 @@ def get_url_content(url, timeout=5):
     def get_meta_property(meta, property_name, default_value=""):
         if "property" in meta.attrs and meta.attrs["property"] == property_name:
             return meta.attrs["content"]
-        return default_value
+        return default_value
diff --git a/bootcamp/news/migrations/0002_auto_20200405_1227.py b/bootcamp/news/migrations/0002_auto_20200405_1227.py
@@ -6,33 +6,33 @@
 class Migration(migrations.Migration):
 
     dependencies = [
-        ('news', '0001_initial'),
+        ("news", "0001_initial"),
     ]
 
     operations = [
         migrations.AddField(
-            model_name='news',
-            name='meta_description',
+            model_name="news",
+            name="meta_description",
             field=models.TextField(max_length=255, null=True),
         ),
         migrations.AddField(
-            model_name='news',
-            name='meta_image',
+            model_name="news",
+            name="meta_image",
             field=models.CharField(max_length=255, null=True),
         ),
         migrations.AddField(
-            model_name='news',
-            name='meta_title',
+            model_name="news",
+            name="meta_title",
             field=models.CharField(max_length=255, null=True),
         ),
         migrations.AddField(
-            model_name='news',
-            name='meta_type',
+            model_name="news",
+            name="meta_type",
             field=models.CharField(max_length=255, null=True),
         ),
         migrations.AddField(
-            model_name='news',
-            name='meta_url',
+            model_name="news",
+            name="meta_url",
             field=models.CharField(max_length=2048, null=True),
         ),
     ]
diff --git a/bootcamp/news/models.py b/bootcamp/news/models.py
@@ -48,14 +48,14 @@ def __str__(self):
         return str(self.content)
 
     def save(self, *args, **kwargs):
-        #extract metada from content url
+        # extract metada from content url
         metadata = Metadatareader.get_metadata_from_url_in_text(self.content)
         self.meta_url = metadata.url[0:2048]
         self.meta_type = metadata.type[0:255]
         self.meta_title = metadata.title[0:255]
         self.meta_description = metadata.description[0:255]
         self.meta_image = metadata.image[0:255]
-        
+
         super().save(*args, **kwargs)
         if not self.reply:
             channel_layer = get_channel_layer()

diff --git a/bootcamp/news/templatetags/urlize_target_blank.py b/bootcamp/news/templatetags/urlize_target_blank.py
@@ -5,7 +5,8 @@
 
 register = template.Library()
 
+
 @register.filter(is_safe=True, needs_autoescape=True)
 @stringfilter
 def urlize_target_blank(value, autoescape=None):
-    return value.replace('<a', '<a target="_blank"')
+    return value.replace("<a", '<a target="_blank"')
diff --git a/bootcamp/news/views.py b/bootcamp/news/views.py
@@ -74,10 +74,7 @@ def get_thread(request):
     news = News.objects.get(pk=news_id)
     news_html = render_to_string("news/news_single.html", {"news": news})
     thread_html = render_to_string(
-        "news/news_thread.html", {
-            "thread": news.get_thread(),
-            "request": request
-        }
+        "news/news_thread.html", {"thread": news.get_thread(), "request": request}
     )
     return JsonResponse({"uuid": news_id, "news": news_html, "thread": thread_html})