rssfeed 0.1__tar.gz → 0.3__tar.gz

rssfeed-0.3/PKG-INFO

@@ -0,0 +1,73 @@
+Metadata-Version: 2.1
+Name: rssfeed
+Version: 0.3
+Summary: A simple rss/atom feed parser
+Keywords: rssfeed,rss,feed,atom,feedparser
+Author: p7e4
+License: GPLv3
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.12
+Classifier: License :: OSI Approved :: GNU General Public License v3 (GPLv3)
+Classifier: Topic :: Text Processing :: Markup :: XML
+Project-URL: Repository, https://github.com/p7e4/rssfeed
+Project-URL: Issues, https://github.com/p7e4/rssfeed/issues
+Requires-Python: >=3.12
+Requires-Dist: python-dateutil>=2.9
+Description-Content-Type: text/markdown
+
+# rssfeed
+
+A simple rss/atom feed parser
+
+## Installation
+
+`pip install rssfeed`
+
+## Get Started
+
+``` python
+import requests
+import rssfeed
+
+feed = rssfeed.parse(requests.get("https://www.solidot.org/index.rss").text)
+print(feed)
+```
+```
+{
+  "name": "奇客Solidot–传递最新科技情报",
+  "lastupdate": 1717423475,
+  "items": [
+    {
+      "title": "中国科学家使用细胞疗法治愈一名患者的糖尿病",
+      "author": "",
+      "timestamp": 1717410594,
+      "url": "https://www.solidot.org/story?sid=78338",
+      "content": "《南华早报》报道，中国科学家利用细胞疗法成功治愈了一名患者的糖尿病。研究报告发表在《Cell Discovery》期刊 ..."
+    },
+    {
+      "title": "Steam 平台 Linux 玩家四分之三使用 AMD CPU",
+      "author": "",
+      "timestamp": 1717404736,
+      "url": "https://www.solidot.org/story?sid=78337",
+      "content": "根据 Valve 公布的 Steam 硬件和软件调查，Linux 份额在过去的五月增长了 0.42% 至 2.32%，macOS 增至 1.47% ..."
+    },
+    {
+      "title": "Hugging Face 称黑客窃取了 Spaces 平台的身份验证令牌",
+      "author": "",
+      "timestamp": 1717400574,
+      "url": "https://www.solidot.org/story?sid=78336",
+      "content": "Hugging Face 官方博客披露黑客窃取了其 Spaces 平台的身份验证令牌。Spaces 是社区用户创建和递交 AI 应用的库 ..."
+    }
+    ...
+  ]
+}
+```
+
+## Warning
+
+rssfeed **does not** escape any HTML tags, which mean if you does not check the content and display it somewhere html can be rendered, it may lead to [Cross-site scripting](https://developer.mozilla.org/en-US/docs/Glossary/Cross-site_scripting) attacks.
+
+## Changelog
+
+[Changelog.md](/Changelog.md)
+

rssfeed-0.3/README.md

@@ -0,0 +1,56 @@
+# rssfeed
+
+A simple rss/atom feed parser
+
+## Installation
+
+`pip install rssfeed`
+
+## Get Started
+
+``` python
+import requests
+import rssfeed
+
+feed = rssfeed.parse(requests.get("https://www.solidot.org/index.rss").text)
+print(feed)
+```
+```
+{
+  "name": "奇客Solidot–传递最新科技情报",
+  "lastupdate": 1717423475,
+  "items": [
+    {
+      "title": "中国科学家使用细胞疗法治愈一名患者的糖尿病",
+      "author": "",
+      "timestamp": 1717410594,
+      "url": "https://www.solidot.org/story?sid=78338",
+      "content": "《南华早报》报道，中国科学家利用细胞疗法成功治愈了一名患者的糖尿病。研究报告发表在《Cell Discovery》期刊 ..."
+    },
+    {
+      "title": "Steam 平台 Linux 玩家四分之三使用 AMD CPU",
+      "author": "",
+      "timestamp": 1717404736,
+      "url": "https://www.solidot.org/story?sid=78337",
+      "content": "根据 Valve 公布的 Steam 硬件和软件调查，Linux 份额在过去的五月增长了 0.42% 至 2.32%，macOS 增至 1.47% ..."
+    },
+    {
+      "title": "Hugging Face 称黑客窃取了 Spaces 平台的身份验证令牌",
+      "author": "",
+      "timestamp": 1717400574,
+      "url": "https://www.solidot.org/story?sid=78336",
+      "content": "Hugging Face 官方博客披露黑客窃取了其 Spaces 平台的身份验证令牌。Spaces 是社区用户创建和递交 AI 应用的库 ..."
+    }
+    ...
+  ]
+}
+```
+
+## Warning
+
+rssfeed **does not** escape any HTML tags, which mean if you does not check the content and display it somewhere html can be rendered, it may lead to [Cross-site scripting](https://developer.mozilla.org/en-US/docs/Glossary/Cross-site_scripting) attacks.
+
+## Changelog
+
+[Changelog.md](/Changelog.md)
+

{rssfeed-0.1 → rssfeed-0.3}/pyproject.toml

@@ -1,7 +1,5 @@
 [build-system]
-requires = [
-    "pdm-backend",
-]
+requires = []
 build-backend = "pdm.backend"
 
 [project]
@@ -21,8 +19,7 @@ keywords = [
     "rss",
     "feed",
     "atom",
-    "rssparse",
-    "feedparse",
+    "feedparser",
 ]
 classifiers = [
     "Programming Language :: Python :: 3",
@@ -30,7 +27,7 @@ classifiers = [
     "License :: OSI Approved :: GNU General Public License v3 (GPLv3)",
     "Topic :: Text Processing :: Markup :: XML",
 ]
-version = "0.1"
+version = "0.3"
 
 [project.license]
 text = "GPLv3"
@@ -38,7 +35,6 @@ text = "GPLv3"
 [project.urls]
 Repository = "https://github.com/p7e4/rssfeed"
 Issues = "https://github.com/p7e4/rssfeed/issues"
-Changelog = "https://github.com/p7e4/rssfeed/blob/main/changelog.md"
 
 [tool.pdm.version]
 source = "file"

{rssfeed-0.1 → rssfeed-0.3}/rssfeed/lib.py

@@ -1,14 +1,15 @@
 from dateutil.parser import parse as timeParse
 from xml.etree import ElementTree
 
-__version__ = "0.1"
+__version__ = "0.3"
 
 def parse(data):
+    assert type(data) == str, "data argument must be a string"
     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'))
+    parser = ElementTree.XMLPullParser(("start", "end"))
     try:
         parser.feed(data)
         parser.close()
@@ -16,7 +17,7 @@ def parse(data):
         return
 
     items = list()
-    authorTag = False
+    path = list()
     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()
@@ -29,49 +30,45 @@ def parse(data):
                     "url": str(),
                     "content": str()
                 })
-            elif tag == "author":
-                authorTag = True
+            path.append(tag)
         else:
             match tag:
-                case "guid":
-                    tag = "id"
                 case "summary" | "description" | "encoded":
                     tag = "content"
                 case "updated" | "pubDate" | "published" | "lastBuildDate":
-                    items[-1]["timestamp"] = int(text) if text.isdigit() else int(timeParse(text).timestamp())
+                    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
+                    items[-1]["url"] = text or elem.get("href")
                     continue
                 case "author":
                     authorTag = False
                     continue
-                case "name" if authorTag:
+                case "name" if path[-2] == "author":
                     tag = "author"
-                case "title" | "id" | "content":
+                case "title" | "content":
                     pass
                 case _:
                     continue
 
             items[-1][tag] = text
+            path.pop()
 
     if not items: return
-    feed = items.pop(0)
     feed = {
-        "name": feed["title"],
-        "lastupdate": feed["timestamp"],
-        "items": items
+        "name": items[0]["title"],
+        "lastupdate": items[0]["timestamp"],
+        "items": items[1:]
     }
-    for item in items:
-        if item.get("id"):
-            if not item["url"] and item["id"].startswith("http"):
-                item["url"] = item["id"]
-            # if not item["url"].startswith("http"):
-            #     item["url"] = f"https://{item["url"]}"
-            del item["id"]
-
-        if feed["lastupdate"] < item["timestamp"]:
-            feed["lastupdate"] = item["timestamp"]
+    # for item in items:
+    #     if feed["lastupdate"] < item["timestamp"]:
+    #         feed["lastupdate"] = item["timestamp"]
 
     return feed
 

rssfeed-0.1/PKG-INFO

@@ -1,27 +0,0 @@
-Metadata-Version: 2.1
-Name: rssfeed
-Version: 0.1
-Summary: A simple rss/atom feed parser
-Keywords: rssfeed,rss,feed,atom,rssparse,feedparse
-Author: p7e4
-License: GPLv3
-Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.12
-Classifier: License :: OSI Approved :: GNU General Public License v3 (GPLv3)
-Classifier: Topic :: Text Processing :: Markup :: XML
-Project-URL: Repository, https://github.com/p7e4/rssfeed
-Project-URL: Issues, https://github.com/p7e4/rssfeed/issues
-Project-URL: Changelog, https://github.com/p7e4/rssfeed/blob/main/changelog.md
-Requires-Python: >=3.12
-Requires-Dist: python-dateutil>=2.9
-Description-Content-Type: text/markdown
-
-# rssfeed
-
-A simple rss/atom feed parser
-
-## Installation
-
-`$ pip install --upgrade rssfeed`
-
-

rssfeed-0.1/README.md

@@ -1,9 +0,0 @@
-# rssfeed
-
-A simple rss/atom feed parser
-
-## Installation
-
-`$ pip install --upgrade rssfeed`
-
-