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
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
|
from datetime import datetime
from io import BytesIO
from typing import Optional, List
from xml.etree.ElementTree import Element
import attr
from .utils import (
parse_xml, get_child, get_text, get_int, get_datetime, FeedParseError
)
@attr.s
class RSSImage:
url: str = attr.ib()
title: Optional[str] = attr.ib()
link: str = attr.ib()
width: int = attr.ib()
height: int = attr.ib()
description: Optional[str] = attr.ib()
@attr.s
class RSSEnclosure:
url: str = attr.ib()
length: Optional[int] = attr.ib()
type: Optional[str] = attr.ib()
@attr.s
class RSSSource:
title: str = attr.ib()
url: Optional[str] = attr.ib()
@attr.s
class RSSItem:
title: Optional[str] = attr.ib()
link: Optional[str] = attr.ib()
description: Optional[str] = attr.ib()
author: Optional[str] = attr.ib()
categories: List[str] = attr.ib()
comments: Optional[str] = attr.ib()
enclosures: List[RSSEnclosure] = attr.ib()
guid: Optional[str] = attr.ib()
pub_date: Optional[datetime] = attr.ib()
source: Optional[RSSSource] = attr.ib()
# Extension
content_encoded: Optional[str] = attr.ib()
@attr.s
class RSSChannel:
title: Optional[str] = attr.ib()
link: Optional[str] = attr.ib()
description: Optional[str] = attr.ib()
language: Optional[str] = attr.ib()
copyright: Optional[str] = attr.ib()
managing_editor: Optional[str] = attr.ib()
web_master: Optional[str] = attr.ib()
pub_date: Optional[datetime] = attr.ib()
last_build_date: Optional[datetime] = attr.ib()
categories: List[str] = attr.ib()
generator: Optional[str] = attr.ib()
docs: Optional[str] = attr.ib()
ttl: Optional[int] = attr.ib()
image: Optional[RSSImage] = attr.ib()
items: List[RSSItem] = attr.ib()
# Extension
content_encoded: Optional[str] = attr.ib()
def _get_image(element: Element, name,
optional: bool=True) -> Optional[RSSImage]:
child = get_child(element, name, optional)
if child is None:
return None
return RSSImage(
get_text(child, 'url', optional=False),
get_text(child, 'title'),
get_text(child, 'link', optional=False),
get_int(child, 'width') or 88,
get_int(child, 'height') or 31,
get_text(child, 'description')
)
def _get_source(element: Element, name,
optional: bool=True) -> Optional[RSSSource]:
child = get_child(element, name, optional)
if child is None:
return None
return RSSSource(
child.text.strip(),
child.attrib.get('url'),
)
def _get_enclosure(element: Element) -> RSSEnclosure:
length = element.attrib.get('length')
try:
length = int(length)
except (TypeError, ValueError):
length = None
return RSSEnclosure(
element.attrib['url'],
length,
element.attrib.get('type'),
)
def _get_link(element: Element) -> Optional[str]:
"""Attempt to retrieve item link.
Use the GUID as a fallback if it is a permalink.
"""
link = get_text(element, 'link')
if link is not None:
return link
guid = get_child(element, 'guid')
if guid is not None and guid.attrib.get('isPermaLink') == 'true':
return get_text(element, 'guid')
return None
def _get_item(element: Element) -> RSSItem:
root = element
title = get_text(root, 'title')
link = _get_link(root)
description = get_text(root, 'description')
author = get_text(root, 'author')
categories = [e.text for e in root.findall('category')]
comments = get_text(root, 'comments')
enclosure = [_get_enclosure(e) for e in root.findall('enclosure')]
guid = get_text(root, 'guid')
pub_date = get_datetime(root, 'pubDate')
source = _get_source(root, 'source')
content_encoded = get_text(root, 'content:encoded')
return RSSItem(
title,
link,
description,
author,
categories,
comments,
enclosure,
guid,
pub_date,
source,
content_encoded
)
def _parse_rss(root: Element) -> RSSChannel:
rss_version = root.get('version')
if rss_version != '2.0':
raise FeedParseError('Cannot process RSS feed version "{}"'
.format(rss_version))
root = root.find('channel')
title = get_text(root, 'title')
link = get_text(root, 'link')
description = get_text(root, 'description')
language = get_text(root, 'language')
copyright = get_text(root, 'copyright')
managing_editor = get_text(root, 'managingEditor')
web_master = get_text(root, 'webMaster')
pub_date = get_datetime(root, 'pubDate')
last_build_date = get_datetime(root, 'lastBuildDate')
categories = [e.text for e in root.findall('category')]
generator = get_text(root, 'generator')
docs = get_text(root, 'docs')
ttl = get_int(root, 'ttl')
image = _get_image(root, 'image')
items = [_get_item(e) for e in root.findall('item')]
content_encoded = get_text(root, 'content:encoded')
return RSSChannel(
title,
link,
description,
language,
copyright,
managing_editor,
web_master,
pub_date,
last_build_date,
categories,
generator,
docs,
ttl,
image,
items,
content_encoded
)
def parse_rss_file(filename: str) -> RSSChannel:
"""Parse an RSS feed from a local XML file."""
root = parse_xml(filename).getroot()
return _parse_rss(root)
def parse_rss_bytes(data: bytes) -> RSSChannel:
"""Parse an RSS feed from a byte-string containing XML data."""
root = parse_xml(BytesIO(data)).getroot()
return _parse_rss(root)
|
