Merge pull request #4 from elreydetoda/master

Extending rss parsing for rough Podcast support
dhvcc · Apr 13, 2021 · d28ef06 · d28ef06
2 parents 1fbdc34 + ea5e79f
commit d28ef06
Show file tree

Hide file tree

Showing 2 changed files with 56 additions and 2 deletions.
diff --git a/rss_parser/_parser.py b/rss_parser/_parser.py
@@ -1,4 +1,5 @@
 from bs4 import BeautifulSoup
+from typing import Optional
 
 from .models import RSSFeed
 
@@ -15,6 +16,17 @@ def __init__(self, xml: str, limit=None):
     def get_soup(xml: str, parser: str = "xml") -> BeautifulSoup:
         return BeautifulSoup(xml, parser)
 
+    @staticmethod
+    def check_none(item: object, default: str, item_dict: Optional[str] = None, default_dict: Optional[str] = None):
+        if item:
+            return item[item_dict]
+        else:
+            if default_dict:
+                return default[default_dict]
+            else:
+                return default
+
+
     def parse(self) -> RSSFeed:
         main_soup = self.get_soup(self.xml)
         self.raw_data = {
@@ -44,7 +56,26 @@ def parse(self) -> RSSFeed:
                 "description_images": [
                     {"alt": image.get("alt", ""), "source": image.get("src")}
                     for image in description_soup.findAll('img')
-                ]
+                ],
+                "enclosure": {
+                        'content': '',
+                        'attrs': {
+                             'url': item.enclosure['url'] ,
+                             'length': item.enclosure['length'] ,
+                             'type': item.enclosure['type']
+                            }
+                },
+                "itunes": {
+                    'content': '',
+                    'attrs': {
+                        'href': self.check_none(
+                            item.find("itunes:image"),
+                            main_soup.find("itunes:image"),
+                            'href',
+                            'href'
+                            )
+                    }
+                }
             }
             self.raw_data["feed"].append(item_dict)
 

diff --git a/rss_parser/models.py b/rss_parser/models.py
@@ -2,12 +2,26 @@
 
 from pydantic import BaseModel
 
+class ItunesAttrs(BaseModel):
+    href: str
+
+class Itunes(BaseModel):
+    content: str
+    attrs: Optional[ItunesAttrs]
+
+class EnclosureAttrs(BaseModel):
+    url: str
+    length: int
+    type: str
+
+class Enclosure(BaseModel):
+    content: str
+    attrs: Optional[EnclosureAttrs]
 
 class DescriptionImage(BaseModel):
     alt: Optional[str]
     source: str
 
-
 class FeedItem(BaseModel):
     title: str
     link: str
@@ -16,7 +30,16 @@ class FeedItem(BaseModel):
     description: str
     description_links: Optional[List[str]]
     description_images: Optional[List[DescriptionImage]]
+    enclosure: Optional[Enclosure]
+    itunes: Optional[Itunes]
+
+    # https://stackoverflow.com/questions/10994229/how-to-make-an-object-properly-hashable#answer-38259091
+    # added this, so you can call/use in a set() on the FeedItem's to ensure no duplicates in a list.
+    def __hash__(self):
+        return hash(self.title.strip())
 
+    def __eq__(self,other):
+        return self.title.strip() == other.title.strip()
 
 class RSSFeed(BaseModel):
     title: str