rssfeed 0.2__tar.gz → 0.4.0__tar.gz

{rssfeed-0.2 → rssfeed-0.4.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: rssfeed
-Version: 0.2
+Version: 0.4.0
 Summary: A simple rss/atom feed parser
 Keywords: rssfeed,rss,feed,atom,feedparser
 Author: p7e4

{rssfeed-0.2 → rssfeed-0.4.0}/pyproject.toml

@@ -27,7 +27,7 @@ classifiers = [
     "License :: OSI Approved :: GNU General Public License v3 (GPLv3)",
     "Topic :: Text Processing :: Markup :: XML",
 ]
-version = "0.2"
+version = "0.4.0"
 
 [project.license]
 text = "GPLv3"

rssfeed-0.4.0/rssfeed/lib.py

@@ -0,0 +1,62 @@
+from dateutil.parser import parse as timeParse
+from xml.etree import ElementTree
+
+__version__ = "0.4.0"
+
+class ParseError(Exception):
+    pass
+
+def parse(data):
+    parser = ElementTree.XMLPullParser(("start", "end"))
+    try:
+        parser.feed(data)
+        parser.close()
+    except ElementTree.ParseError as e:
+        raise ParseError("xml parse fail") from e
+
+    items = list()
+    lastTag = str()
+    for event, elem in parser.read_events():
+        tag = elem.tag.split("}", 1)[1] if elem.tag.startswith("{") else elem.tag
+        text = elem.text.strip() if elem.text else str()
+        if event == "start":
+            if tag in ("channel", "RDF", "feed", "item", "entry"):
+                items.append({
+                    "title": str(),
+                    "author": str(),
+                    "timestamp": 0,
+                    "url": str(),
+                    "content": str()
+                })
+        else:
+            i = items[-1]
+            match tag:
+                case "content" | "description" | "encoded" | "summary":
+                    i["content"] = text
+                case "updated" | "pubDate" | "published" | "lastBuildDate":
+                    if text.isdigit():
+                        i["timestamp"] = int(text)
+                    elif text:
+                        try:
+                            i["timestamp"] = int(timeParse(text).timestamp())
+                        except Exception as e:
+                            raise ParseError("time parse fail") from e
+                case "link":
+                    i["url"] = text or elem.get("href")
+                case "name" if lastTag == "author":
+                    i["author"] = text
+                case "title":
+                    i[tag] = text
+
+            lastTag = tag
+
+    if not items:
+        raise ParseError("not valid result")
+
+    feed = {
+        "name": items[0]["title"],
+        "lastupdate": items[0]["timestamp"],
+        "items": items[1:]
+    }
+
+    return feed

rssfeed-0.2/rssfeed/lib.py

@@ -1,81 +0,0 @@
-from dateutil.parser import parse as timeParse
-from xml.etree import ElementTree
-
-__version__ = "0.2"
-
-def parse(data):
-    if not data or not (data:=data.lstrip()):
-        return
-    if not any((data.startswith(i) for i in ("<?xml ", "<rss ", "<feed "))):
-        return
-    parser = ElementTree.XMLPullParser(("start", "end"), _parser=ElementTree.XMLParser(encoding='utf-8'))
-    try:
-        parser.feed(data)
-        parser.close()
-    except ElementTree.ParseError:
-        return
-
-    items = list()
-    authorTag = False
-    for event, elem in parser.read_events():
-        tag = elem.tag.split("}", 1)[1] if elem.tag.startswith("{") else elem.tag
-        text = elem.text.strip() if elem.text else str()
-        if event == "start":
-            if tag in ("channel", "RDF", "feed", "item", "entry"):
-                items.append({
-                    "title": str(),
-                    "author": str(),
-                    "timestamp": 0,
-                    "url": str(),
-                    "content": str()
-                })
-            elif tag == "author":
-                authorTag = True
-        else:
-            match tag:
-                case "guid":
-                    tag = "id"
-                case "summary" | "description" | "encoded":
-                    tag = "content"
-                case "updated" | "pubDate" | "published" | "lastBuildDate":
-                    if text.isdigit():
-                        items[-1]["timestamp"] = int(text)
-                    elif text:
-                        try:
-                            items[-1]["timestamp"] = int(timeParse(text).timestamp())
-                        except:
-                            pass
-                    continue
-                case "link":
-                    items[-1]["url"] = elem.get("href") if text and elem.get("href") else text
-                    continue
-                case "author":
-                    authorTag = False
-                    continue
-                case "name" if authorTag:
-                    tag = "author"
-                case "title" | "id" | "content":
-                    pass
-                case _:
-                    continue
-
-            items[-1][tag] = text
-
-    if not items: return
-    feed = items.pop(0)
-    feed = {
-        "name": feed["title"],
-        "lastupdate": feed["timestamp"],
-        "items": items
-    }
-    for item in items:
-        if item.get("id"):
-            if not item["url"] and item["id"].startswith("http"):
-                item["url"] = item["id"]
-            del item["id"]
-
-        if feed["lastupdate"] < item["timestamp"]:
-            feed["lastupdate"] = item["timestamp"]
-
-    return feed
-