rssfeed 0.3__tar.gz → 0.4.1__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- rssfeed-0.4.1/PKG-INFO +119 -0
- rssfeed-0.4.1/README.md +101 -0
- {rssfeed-0.3 → rssfeed-0.4.1}/pyproject.toml +3 -2
- rssfeed-0.4.1/rssfeed/__init__.py +3 -0
- rssfeed-0.4.1/rssfeed/lib.py +89 -0
- rssfeed-0.3/PKG-INFO +0 -73
- rssfeed-0.3/README.md +0 -56
- rssfeed-0.3/rssfeed/__init__.py +0 -1
- rssfeed-0.3/rssfeed/lib.py +0 -74
- {rssfeed-0.3 → rssfeed-0.4.1}/LICENSE +0 -0
rssfeed-0.4.1/PKG-INFO
ADDED
|
@@ -0,0 +1,119 @@
|
|
|
1
|
+
Metadata-Version: 2.1
|
|
2
|
+
Name: rssfeed
|
|
3
|
+
Version: 0.4.1
|
|
4
|
+
Summary: A simple rss/atom feed parser
|
|
5
|
+
Keywords: rssfeed,rss,feed,atom,opml
|
|
6
|
+
Author: p7e4
|
|
7
|
+
License: GPLv3
|
|
8
|
+
Classifier: Programming Language :: Python :: 3
|
|
9
|
+
Classifier: Programming Language :: Python :: 3.12
|
|
10
|
+
Classifier: Programming Language :: Python :: 3.13
|
|
11
|
+
Classifier: License :: OSI Approved :: GNU General Public License v3 (GPLv3)
|
|
12
|
+
Classifier: Topic :: Text Processing :: Markup :: XML
|
|
13
|
+
Project-URL: Repository, https://github.com/p7e4/rssfeed
|
|
14
|
+
Project-URL: Issues, https://github.com/p7e4/rssfeed/issues
|
|
15
|
+
Requires-Python: >=3.12
|
|
16
|
+
Requires-Dist: python-dateutil>=2.9
|
|
17
|
+
Description-Content-Type: text/markdown
|
|
18
|
+
|
|
19
|
+
# rssfeed
|
|
20
|
+
|
|
21
|
+
A simple rss/atom/opml parser
|
|
22
|
+
|
|
23
|
+
## Installation
|
|
24
|
+
|
|
25
|
+
`pip install rssfeed`
|
|
26
|
+
|
|
27
|
+
|
|
28
|
+
## Get Started
|
|
29
|
+
|
|
30
|
+
### rss parse
|
|
31
|
+
|
|
32
|
+
``` python
|
|
33
|
+
import requests
|
|
34
|
+
import rssfeed
|
|
35
|
+
|
|
36
|
+
text = requests.get("https://lobste.rs/rss").text
|
|
37
|
+
rssfeed.parse(text)
|
|
38
|
+
```
|
|
39
|
+
|
|
40
|
+
``` json
|
|
41
|
+
{
|
|
42
|
+
"name": "Lobsters",
|
|
43
|
+
"lastupdate": 1739824193,
|
|
44
|
+
"items": [
|
|
45
|
+
{
|
|
46
|
+
"title": "Why I'm Writing a Scheme Implementation in 2025 (The Answer is Async Rust)",
|
|
47
|
+
"author": "maplant.com by mplant",
|
|
48
|
+
"timestamp": 1739824193,
|
|
49
|
+
"url": "https://maplant.com/2025-02-17-Why-I'm-Writing-a-Scheme-Implementation-in-2025-(The-Answer-is-Async-Rust).html",
|
|
50
|
+
"content": "<p><a href=\"https://lobste.rs/s/zm1g8r/why_i_m_writing_scheme_implementation\">Comments</a></p>"
|
|
51
|
+
},
|
|
52
|
+
{
|
|
53
|
+
"title": "14 years of systemd",
|
|
54
|
+
"author": "lwn.net via calvin",
|
|
55
|
+
"timestamp": 1739814564,
|
|
56
|
+
"url": "https://lwn.net/SubscriberLink/1008721/7c31808d76480012/",
|
|
57
|
+
"content": "<p><a href=\"https://lobste.rs/s/c6rk0l/14_years_systemd\">Comments</a></p>"
|
|
58
|
+
},
|
|
59
|
+
{
|
|
60
|
+
"title": "Making the Web More Readable With Stylus",
|
|
61
|
+
"author": "wezm.net by wezm",
|
|
62
|
+
"timestamp": 1739757928,
|
|
63
|
+
"url": "https://www.wezm.net/v2/posts/2025/stylus/",
|
|
64
|
+
"content": "<p><a href=\"https://lobste.rs/s/sag0p3/making_web_more_readable_with_stylus\">Comments</a></p>"
|
|
65
|
+
}
|
|
66
|
+
]
|
|
67
|
+
}
|
|
68
|
+
```
|
|
69
|
+
|
|
70
|
+
> rssfeed **does not** escape HTML tag, 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.
|
|
71
|
+
|
|
72
|
+
|
|
73
|
+
### opml parse
|
|
74
|
+
|
|
75
|
+
``` python
|
|
76
|
+
import rssfeed
|
|
77
|
+
opml = """
|
|
78
|
+
<?xml version="1.0" encoding="UTF-8"?>
|
|
79
|
+
<opml version="1.0">
|
|
80
|
+
<head>
|
|
81
|
+
<title>demo feeds</title>
|
|
82
|
+
</head>
|
|
83
|
+
<body>
|
|
84
|
+
<outline text="news">
|
|
85
|
+
<outline text="奇客Solidot" xmlUrl="https://www.solidot.org/index.rss" type="rss" />
|
|
86
|
+
<outline text="news-submenu">
|
|
87
|
+
<outline text="Lobsters" xmlUrl="https://lobste.rs/rss" type="rss" />
|
|
88
|
+
</outline>
|
|
89
|
+
</outline>
|
|
90
|
+
<outline text="阮一峰的网络日志" xmlUrl="https://feeds.feedburner.com/ruanyifeng" type="rss" />
|
|
91
|
+
</body>
|
|
92
|
+
</opml>
|
|
93
|
+
"""
|
|
94
|
+
rssfeed.opmlParse(opml)
|
|
95
|
+
````
|
|
96
|
+
|
|
97
|
+
``` json
|
|
98
|
+
{
|
|
99
|
+
"default": [
|
|
100
|
+
{
|
|
101
|
+
"name": "阮一峰的网络日志",
|
|
102
|
+
"url": "https://feeds.feedburner.com/ruanyifeng"
|
|
103
|
+
}
|
|
104
|
+
],
|
|
105
|
+
"news": [
|
|
106
|
+
{
|
|
107
|
+
"name": "奇客Solidot",
|
|
108
|
+
"url": "https://www.solidot.org/index.rss"
|
|
109
|
+
},
|
|
110
|
+
{
|
|
111
|
+
"name": "Lobsters",
|
|
112
|
+
"url": "https://lobste.rs/rss"
|
|
113
|
+
}
|
|
114
|
+
]
|
|
115
|
+
}
|
|
116
|
+
```
|
|
117
|
+
|
|
118
|
+
as you can see, a two-layer structure will always be generated regardless of the original structure. If the original file includes multiple levels, only the outermost menu is retained. If a feed on the root it will be place in `default` menu.
|
|
119
|
+
|
rssfeed-0.4.1/README.md
ADDED
|
@@ -0,0 +1,101 @@
|
|
|
1
|
+
# rssfeed
|
|
2
|
+
|
|
3
|
+
A simple rss/atom/opml parser
|
|
4
|
+
|
|
5
|
+
## Installation
|
|
6
|
+
|
|
7
|
+
`pip install rssfeed`
|
|
8
|
+
|
|
9
|
+
|
|
10
|
+
## Get Started
|
|
11
|
+
|
|
12
|
+
### rss parse
|
|
13
|
+
|
|
14
|
+
``` python
|
|
15
|
+
import requests
|
|
16
|
+
import rssfeed
|
|
17
|
+
|
|
18
|
+
text = requests.get("https://lobste.rs/rss").text
|
|
19
|
+
rssfeed.parse(text)
|
|
20
|
+
```
|
|
21
|
+
|
|
22
|
+
``` json
|
|
23
|
+
{
|
|
24
|
+
"name": "Lobsters",
|
|
25
|
+
"lastupdate": 1739824193,
|
|
26
|
+
"items": [
|
|
27
|
+
{
|
|
28
|
+
"title": "Why I'm Writing a Scheme Implementation in 2025 (The Answer is Async Rust)",
|
|
29
|
+
"author": "maplant.com by mplant",
|
|
30
|
+
"timestamp": 1739824193,
|
|
31
|
+
"url": "https://maplant.com/2025-02-17-Why-I'm-Writing-a-Scheme-Implementation-in-2025-(The-Answer-is-Async-Rust).html",
|
|
32
|
+
"content": "<p><a href=\"https://lobste.rs/s/zm1g8r/why_i_m_writing_scheme_implementation\">Comments</a></p>"
|
|
33
|
+
},
|
|
34
|
+
{
|
|
35
|
+
"title": "14 years of systemd",
|
|
36
|
+
"author": "lwn.net via calvin",
|
|
37
|
+
"timestamp": 1739814564,
|
|
38
|
+
"url": "https://lwn.net/SubscriberLink/1008721/7c31808d76480012/",
|
|
39
|
+
"content": "<p><a href=\"https://lobste.rs/s/c6rk0l/14_years_systemd\">Comments</a></p>"
|
|
40
|
+
},
|
|
41
|
+
{
|
|
42
|
+
"title": "Making the Web More Readable With Stylus",
|
|
43
|
+
"author": "wezm.net by wezm",
|
|
44
|
+
"timestamp": 1739757928,
|
|
45
|
+
"url": "https://www.wezm.net/v2/posts/2025/stylus/",
|
|
46
|
+
"content": "<p><a href=\"https://lobste.rs/s/sag0p3/making_web_more_readable_with_stylus\">Comments</a></p>"
|
|
47
|
+
}
|
|
48
|
+
]
|
|
49
|
+
}
|
|
50
|
+
```
|
|
51
|
+
|
|
52
|
+
> rssfeed **does not** escape HTML tag, 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.
|
|
53
|
+
|
|
54
|
+
|
|
55
|
+
### opml parse
|
|
56
|
+
|
|
57
|
+
``` python
|
|
58
|
+
import rssfeed
|
|
59
|
+
opml = """
|
|
60
|
+
<?xml version="1.0" encoding="UTF-8"?>
|
|
61
|
+
<opml version="1.0">
|
|
62
|
+
<head>
|
|
63
|
+
<title>demo feeds</title>
|
|
64
|
+
</head>
|
|
65
|
+
<body>
|
|
66
|
+
<outline text="news">
|
|
67
|
+
<outline text="奇客Solidot" xmlUrl="https://www.solidot.org/index.rss" type="rss" />
|
|
68
|
+
<outline text="news-submenu">
|
|
69
|
+
<outline text="Lobsters" xmlUrl="https://lobste.rs/rss" type="rss" />
|
|
70
|
+
</outline>
|
|
71
|
+
</outline>
|
|
72
|
+
<outline text="阮一峰的网络日志" xmlUrl="https://feeds.feedburner.com/ruanyifeng" type="rss" />
|
|
73
|
+
</body>
|
|
74
|
+
</opml>
|
|
75
|
+
"""
|
|
76
|
+
rssfeed.opmlParse(opml)
|
|
77
|
+
````
|
|
78
|
+
|
|
79
|
+
``` json
|
|
80
|
+
{
|
|
81
|
+
"default": [
|
|
82
|
+
{
|
|
83
|
+
"name": "阮一峰的网络日志",
|
|
84
|
+
"url": "https://feeds.feedburner.com/ruanyifeng"
|
|
85
|
+
}
|
|
86
|
+
],
|
|
87
|
+
"news": [
|
|
88
|
+
{
|
|
89
|
+
"name": "奇客Solidot",
|
|
90
|
+
"url": "https://www.solidot.org/index.rss"
|
|
91
|
+
},
|
|
92
|
+
{
|
|
93
|
+
"name": "Lobsters",
|
|
94
|
+
"url": "https://lobste.rs/rss"
|
|
95
|
+
}
|
|
96
|
+
]
|
|
97
|
+
}
|
|
98
|
+
```
|
|
99
|
+
|
|
100
|
+
as you can see, a two-layer structure will always be generated regardless of the original structure. If the original file includes multiple levels, only the outermost menu is retained. If a feed on the root it will be place in `default` menu.
|
|
101
|
+
|
|
@@ -19,15 +19,16 @@ keywords = [
|
|
|
19
19
|
"rss",
|
|
20
20
|
"feed",
|
|
21
21
|
"atom",
|
|
22
|
-
"
|
|
22
|
+
"opml",
|
|
23
23
|
]
|
|
24
24
|
classifiers = [
|
|
25
25
|
"Programming Language :: Python :: 3",
|
|
26
26
|
"Programming Language :: Python :: 3.12",
|
|
27
|
+
"Programming Language :: Python :: 3.13",
|
|
27
28
|
"License :: OSI Approved :: GNU General Public License v3 (GPLv3)",
|
|
28
29
|
"Topic :: Text Processing :: Markup :: XML",
|
|
29
30
|
]
|
|
30
|
-
version = "0.
|
|
31
|
+
version = "0.4.1"
|
|
31
32
|
|
|
32
33
|
[project.license]
|
|
33
34
|
text = "GPLv3"
|
|
@@ -0,0 +1,89 @@
|
|
|
1
|
+
from dateutil.parser import parse as timeParse
|
|
2
|
+
from xml.etree import ElementTree
|
|
3
|
+
|
|
4
|
+
__version__ = "0.4.1"
|
|
5
|
+
|
|
6
|
+
class ParseError(Exception):
|
|
7
|
+
pass
|
|
8
|
+
|
|
9
|
+
def _parse(data):
|
|
10
|
+
if not (data:=data.lstrip()):
|
|
11
|
+
raise ParseError("empty data")
|
|
12
|
+
parser = ElementTree.XMLPullParser(("start", "end"))
|
|
13
|
+
try:
|
|
14
|
+
parser.feed(data)
|
|
15
|
+
parser.close()
|
|
16
|
+
except ElementTree.ParseError as e:
|
|
17
|
+
raise ParseError("xml parse fail") from e
|
|
18
|
+
return parser
|
|
19
|
+
|
|
20
|
+
def parse(data):
|
|
21
|
+
items = list()
|
|
22
|
+
for event, elem in _parse(data).read_events():
|
|
23
|
+
tag = elem.tag.split("}", 1)[1] if elem.tag.startswith("{") else elem.tag
|
|
24
|
+
text = elem.text.strip() if elem.text else str()
|
|
25
|
+
if event == "start":
|
|
26
|
+
if tag in ("channel", "RDF", "feed", "item", "entry"):
|
|
27
|
+
items.append({
|
|
28
|
+
"title": str(),
|
|
29
|
+
"author": str(),
|
|
30
|
+
"timestamp": 0,
|
|
31
|
+
"url": str(),
|
|
32
|
+
"content": str()
|
|
33
|
+
})
|
|
34
|
+
else:
|
|
35
|
+
i = items[-1]
|
|
36
|
+
match tag:
|
|
37
|
+
case "description" | "encoded" | "summary" | "content":
|
|
38
|
+
i["content"] = text
|
|
39
|
+
case "pubDate" | "updated" | "published" | "lastBuildDate":
|
|
40
|
+
if text.isdigit():
|
|
41
|
+
i["timestamp"] = int(text)
|
|
42
|
+
elif text:
|
|
43
|
+
try:
|
|
44
|
+
i["timestamp"] = int(timeParse(text).timestamp())
|
|
45
|
+
except Exception as e:
|
|
46
|
+
raise ParseError("time parse fail") from e
|
|
47
|
+
# if len(items) and items[0]["timestamp"] < i["timestamp"]:
|
|
48
|
+
# items[0]["timestamp"] = i["timestamp"]
|
|
49
|
+
case "link":
|
|
50
|
+
i["url"] = text or elem.get("href")
|
|
51
|
+
case "title" | "author":
|
|
52
|
+
i[tag] = text
|
|
53
|
+
|
|
54
|
+
|
|
55
|
+
if not items:
|
|
56
|
+
raise ParseError("not valid result")
|
|
57
|
+
|
|
58
|
+
feed = {
|
|
59
|
+
"name": items[0]["title"],
|
|
60
|
+
"lastupdate": items[0]["timestamp"],
|
|
61
|
+
"items": items[1:]
|
|
62
|
+
}
|
|
63
|
+
|
|
64
|
+
return feed
|
|
65
|
+
|
|
66
|
+
def opmlParse(data):
|
|
67
|
+
path = list()
|
|
68
|
+
result = dict(default=list())
|
|
69
|
+
for event, elem in _parse(data).read_events():
|
|
70
|
+
if elem.tag != "outline":
|
|
71
|
+
continue
|
|
72
|
+
if event == "start":
|
|
73
|
+
if elem.get("type") == "rss":
|
|
74
|
+
name = path[0] if path else "default"
|
|
75
|
+
result[name].append({
|
|
76
|
+
"name": elem.get("text") or elem.get("title"),
|
|
77
|
+
"url": elem.get("xmlUrl") or elem.get("htmlUrl")
|
|
78
|
+
})
|
|
79
|
+
else:
|
|
80
|
+
path.append(elem.get("text") or elem.get("title"))
|
|
81
|
+
if len(path) == 1: result[path[0]] = list()
|
|
82
|
+
else:
|
|
83
|
+
if elem.get("type") != "rss":
|
|
84
|
+
path.pop()
|
|
85
|
+
|
|
86
|
+
if not result["default"]:
|
|
87
|
+
del result["default"]
|
|
88
|
+
|
|
89
|
+
return result
|
rssfeed-0.3/PKG-INFO
DELETED
|
@@ -1,73 +0,0 @@
|
|
|
1
|
-
Metadata-Version: 2.1
|
|
2
|
-
Name: rssfeed
|
|
3
|
-
Version: 0.3
|
|
4
|
-
Summary: A simple rss/atom feed parser
|
|
5
|
-
Keywords: rssfeed,rss,feed,atom,feedparser
|
|
6
|
-
Author: p7e4
|
|
7
|
-
License: GPLv3
|
|
8
|
-
Classifier: Programming Language :: Python :: 3
|
|
9
|
-
Classifier: Programming Language :: Python :: 3.12
|
|
10
|
-
Classifier: License :: OSI Approved :: GNU General Public License v3 (GPLv3)
|
|
11
|
-
Classifier: Topic :: Text Processing :: Markup :: XML
|
|
12
|
-
Project-URL: Repository, https://github.com/p7e4/rssfeed
|
|
13
|
-
Project-URL: Issues, https://github.com/p7e4/rssfeed/issues
|
|
14
|
-
Requires-Python: >=3.12
|
|
15
|
-
Requires-Dist: python-dateutil>=2.9
|
|
16
|
-
Description-Content-Type: text/markdown
|
|
17
|
-
|
|
18
|
-
# rssfeed
|
|
19
|
-
|
|
20
|
-
A simple rss/atom feed parser
|
|
21
|
-
|
|
22
|
-
## Installation
|
|
23
|
-
|
|
24
|
-
`pip install rssfeed`
|
|
25
|
-
|
|
26
|
-
## Get Started
|
|
27
|
-
|
|
28
|
-
``` python
|
|
29
|
-
import requests
|
|
30
|
-
import rssfeed
|
|
31
|
-
|
|
32
|
-
feed = rssfeed.parse(requests.get("https://www.solidot.org/index.rss").text)
|
|
33
|
-
print(feed)
|
|
34
|
-
```
|
|
35
|
-
```
|
|
36
|
-
{
|
|
37
|
-
"name": "奇客Solidot–传递最新科技情报",
|
|
38
|
-
"lastupdate": 1717423475,
|
|
39
|
-
"items": [
|
|
40
|
-
{
|
|
41
|
-
"title": "中国科学家使用细胞疗法治愈一名患者的糖尿病",
|
|
42
|
-
"author": "",
|
|
43
|
-
"timestamp": 1717410594,
|
|
44
|
-
"url": "https://www.solidot.org/story?sid=78338",
|
|
45
|
-
"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 ..."
|
|
46
|
-
},
|
|
47
|
-
{
|
|
48
|
-
"title": "Steam 平台 Linux 玩家四分之三使用 AMD CPU",
|
|
49
|
-
"author": "",
|
|
50
|
-
"timestamp": 1717404736,
|
|
51
|
-
"url": "https://www.solidot.org/story?sid=78337",
|
|
52
|
-
"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% ..."
|
|
53
|
-
},
|
|
54
|
-
{
|
|
55
|
-
"title": "Hugging Face 称黑客窃取了 Spaces 平台的身份验证令牌",
|
|
56
|
-
"author": "",
|
|
57
|
-
"timestamp": 1717400574,
|
|
58
|
-
"url": "https://www.solidot.org/story?sid=78336",
|
|
59
|
-
"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 ..."
|
|
60
|
-
}
|
|
61
|
-
...
|
|
62
|
-
]
|
|
63
|
-
}
|
|
64
|
-
```
|
|
65
|
-
|
|
66
|
-
## Warning
|
|
67
|
-
|
|
68
|
-
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.
|
|
69
|
-
|
|
70
|
-
## Changelog
|
|
71
|
-
|
|
72
|
-
[Changelog.md](/Changelog.md)
|
|
73
|
-
|
rssfeed-0.3/README.md
DELETED
|
@@ -1,56 +0,0 @@
|
|
|
1
|
-
# rssfeed
|
|
2
|
-
|
|
3
|
-
A simple rss/atom feed parser
|
|
4
|
-
|
|
5
|
-
## Installation
|
|
6
|
-
|
|
7
|
-
`pip install rssfeed`
|
|
8
|
-
|
|
9
|
-
## Get Started
|
|
10
|
-
|
|
11
|
-
``` python
|
|
12
|
-
import requests
|
|
13
|
-
import rssfeed
|
|
14
|
-
|
|
15
|
-
feed = rssfeed.parse(requests.get("https://www.solidot.org/index.rss").text)
|
|
16
|
-
print(feed)
|
|
17
|
-
```
|
|
18
|
-
```
|
|
19
|
-
{
|
|
20
|
-
"name": "奇客Solidot–传递最新科技情报",
|
|
21
|
-
"lastupdate": 1717423475,
|
|
22
|
-
"items": [
|
|
23
|
-
{
|
|
24
|
-
"title": "中国科学家使用细胞疗法治愈一名患者的糖尿病",
|
|
25
|
-
"author": "",
|
|
26
|
-
"timestamp": 1717410594,
|
|
27
|
-
"url": "https://www.solidot.org/story?sid=78338",
|
|
28
|
-
"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 ..."
|
|
29
|
-
},
|
|
30
|
-
{
|
|
31
|
-
"title": "Steam 平台 Linux 玩家四分之三使用 AMD CPU",
|
|
32
|
-
"author": "",
|
|
33
|
-
"timestamp": 1717404736,
|
|
34
|
-
"url": "https://www.solidot.org/story?sid=78337",
|
|
35
|
-
"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% ..."
|
|
36
|
-
},
|
|
37
|
-
{
|
|
38
|
-
"title": "Hugging Face 称黑客窃取了 Spaces 平台的身份验证令牌",
|
|
39
|
-
"author": "",
|
|
40
|
-
"timestamp": 1717400574,
|
|
41
|
-
"url": "https://www.solidot.org/story?sid=78336",
|
|
42
|
-
"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 ..."
|
|
43
|
-
}
|
|
44
|
-
...
|
|
45
|
-
]
|
|
46
|
-
}
|
|
47
|
-
```
|
|
48
|
-
|
|
49
|
-
## Warning
|
|
50
|
-
|
|
51
|
-
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.
|
|
52
|
-
|
|
53
|
-
## Changelog
|
|
54
|
-
|
|
55
|
-
[Changelog.md](/Changelog.md)
|
|
56
|
-
|
rssfeed-0.3/rssfeed/__init__.py
DELETED
|
@@ -1 +0,0 @@
|
|
|
1
|
-
from .lib import parse
|
rssfeed-0.3/rssfeed/lib.py
DELETED
|
@@ -1,74 +0,0 @@
|
|
|
1
|
-
from dateutil.parser import parse as timeParse
|
|
2
|
-
from xml.etree import ElementTree
|
|
3
|
-
|
|
4
|
-
__version__ = "0.3"
|
|
5
|
-
|
|
6
|
-
def parse(data):
|
|
7
|
-
assert type(data) == str, "data argument must be a string"
|
|
8
|
-
if not data or not (data:=data.lstrip()):
|
|
9
|
-
return
|
|
10
|
-
if not any((data.startswith(i) for i in ("<?xml ", "<rss ", "<feed "))):
|
|
11
|
-
return
|
|
12
|
-
parser = ElementTree.XMLPullParser(("start", "end"))
|
|
13
|
-
try:
|
|
14
|
-
parser.feed(data)
|
|
15
|
-
parser.close()
|
|
16
|
-
except ElementTree.ParseError:
|
|
17
|
-
return
|
|
18
|
-
|
|
19
|
-
items = list()
|
|
20
|
-
path = list()
|
|
21
|
-
for event, elem in parser.read_events():
|
|
22
|
-
tag = elem.tag.split("}", 1)[1] if elem.tag.startswith("{") else elem.tag
|
|
23
|
-
text = elem.text.strip() if elem.text else str()
|
|
24
|
-
if event == "start":
|
|
25
|
-
if tag in ("channel", "RDF", "feed", "item", "entry"):
|
|
26
|
-
items.append({
|
|
27
|
-
"title": str(),
|
|
28
|
-
"author": str(),
|
|
29
|
-
"timestamp": 0,
|
|
30
|
-
"url": str(),
|
|
31
|
-
"content": str()
|
|
32
|
-
})
|
|
33
|
-
path.append(tag)
|
|
34
|
-
else:
|
|
35
|
-
match tag:
|
|
36
|
-
case "summary" | "description" | "encoded":
|
|
37
|
-
tag = "content"
|
|
38
|
-
case "updated" | "pubDate" | "published" | "lastBuildDate":
|
|
39
|
-
if text.isdigit():
|
|
40
|
-
items[-1]["timestamp"] = int(text)
|
|
41
|
-
elif text:
|
|
42
|
-
try:
|
|
43
|
-
items[-1]["timestamp"] = int(timeParse(text).timestamp())
|
|
44
|
-
except:
|
|
45
|
-
pass
|
|
46
|
-
continue
|
|
47
|
-
case "link":
|
|
48
|
-
items[-1]["url"] = text or elem.get("href")
|
|
49
|
-
continue
|
|
50
|
-
case "author":
|
|
51
|
-
authorTag = False
|
|
52
|
-
continue
|
|
53
|
-
case "name" if path[-2] == "author":
|
|
54
|
-
tag = "author"
|
|
55
|
-
case "title" | "content":
|
|
56
|
-
pass
|
|
57
|
-
case _:
|
|
58
|
-
continue
|
|
59
|
-
|
|
60
|
-
items[-1][tag] = text
|
|
61
|
-
path.pop()
|
|
62
|
-
|
|
63
|
-
if not items: return
|
|
64
|
-
feed = {
|
|
65
|
-
"name": items[0]["title"],
|
|
66
|
-
"lastupdate": items[0]["timestamp"],
|
|
67
|
-
"items": items[1:]
|
|
68
|
-
}
|
|
69
|
-
# for item in items:
|
|
70
|
-
# if feed["lastupdate"] < item["timestamp"]:
|
|
71
|
-
# feed["lastupdate"] = item["timestamp"]
|
|
72
|
-
|
|
73
|
-
return feed
|
|
74
|
-
|
|
File without changes
|