1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
|
#!/usr/bin/env python3
import lxml.etree as ET
class RssFeed(object):
"""Class for storing an RSS 2.0 feed.
https://validator.w3.org/feed/docs/rss2.html.
"""
# pylint: disable=too-many-instance-attributes
REQUIRED_ELEMENTS = ["title", "link", "description"]
OPTIONAL_ELEMENTS = ["language", "copyright", "managingEditor", "webMaster",
"pubDate", "lastBuildDate", "category", "generator",
"docs", "cloud", "ttl", "image", "textInput",
"skipHours", "skipDays"]
def __init__(self):
"""Define available attributes."""
self.rssurl = None # the URL of the rss feed
self.atomlink = None
for element in self.REQUIRED_ELEMENTS:
setattr(self, element, None)
for element in self.OPTIONAL_ELEMENTS:
setattr(self, element, None)
self.docs = ET.Element("docs")
self.docs.text = "https://validator.w3.org/feed/docs/rss2.html"
self.author_text = None
self.update_timestamp = None
self.items = []
self.rss = None
self.channel = None
def assemble_rss(self, FEED_MAX_ENTRIES):
"""Assemble RSS 2.0 feed."""
self.rss = ET.Element("rss", version="2.0", nsmap={"atom": "http://www.w3.org/2005/Atom"})
self.channel = ET.SubElement(self.rss, "channel")
# https://validator.w3.org/feed/docs/warning/MissingAtomSelfLink.html
self.atomlink = ET.SubElement(self.channel, "{http://www.w3.org/2005/Atom}link",
href=self.rssurl, rel="self", type="application/rss+xml")
for element in self.REQUIRED_ELEMENTS:
self.channel.append(getattr(self, element))
for element in self.OPTIONAL_ELEMENTS:
attr = getattr(self, element)
if attr is not None:
self.channel.append(attr)
# include at most FEED_MAX_ENTRIES items in the RSS feed
for item in self.items[:FEED_MAX_ENTRIES]:
self.channel.append(item.item)
def dump_rss(self, FEED_MAX_ENTRIES):
"""Dump RSS feed XML."""
if self.rss is None:
self.assemble_rss(FEED_MAX_ENTRIES)
return ET.tostring(self.rss).decode("utf-8")
|
