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
|
#!/usr/bin/python -tt
# -*- coding: utf-8 -*-
from __future__ import print_function
import codecs
import os
import sys
import feedparser
import re
import sys
feedparser._HTMLSanitizer.unacceptable_elements_with_end_tag.add('<div>')
defenc = "utf-8" if sys.getdefaultencoding() == "ascii" else sys.getdefaultencoding()
FedMag = ['http://fedoraplanet.org/rss20.xml']
if len(sys.argv) > 2:
print ('Alone script or only one argument is allowed.')
sys.exit(1)
HTML = u"""
"""
for feed in map(feedparser.parse, FedMag):
# We will parse last ten items
HTML += u"""
<div class="container" id="blog-headlines">
<div class="container">
<div class="row">
<div class="col-sm-12">
<h2><span>Fedora Planet</span></h2>
</div>
</div>
<div class="row">
"""
cnt = 0
# Getting at least 4 items in case of some python exceptions.
for item in feed["items"][:6]:
if int(cnt) % 2 == 0:
HTML += u"""
<div class="col-sm-6 blog-headlines">
"""
item.title = item.title.replace("&", "&")
author, title = item.title.split(':', 1)
link = item.links[0]['href']
# Remove image tag from beginning
try:
article_desc = '\n'.join(item.description.split('\n')[1:])
# remove html tags from description
article_desc = re.sub('<[^<]+?>', '', article_desc)
article_desc = re.sub('<', '<', article_desc)
article_desc = re.sub('>', '>', article_desc)
if len(article_desc) > 140:
article_desc = ' '.join(article_desc.split()[0:25]) + '...'
if not article_desc.startswith('<p>'):
article_desc = '<p>%s</p>' % article_desc
except AttributeError:
print ('AttributeError. Going to next item')
continue
# we got
# Tue, 20 Oct 2015 03:28:42 +0000
# But we expect
# Tue, 20 Oct 2015
article_date = ' '.join(item.updated.split()[:4])
HTML += u"""
<article>
<h3><a href="{article_url}">{article_title}</a></h3>
{article_desc}
<p><a href="{article_url}">Read more</a></p>
<p class="byline">by <span class="author">{author}</span> <span class="date">{article_date}</span></p>
</article>
""".format(article_url=link,
article_title=title,
article_desc=article_desc,
article_date=article_date,
author=author)
cnt += 1
if int(cnt) % 2 == 0:
HTML += u"""
</div>
"""
# Condition if items were collected properly
if int(cnt) > 3:
break
HTML += u"""
</div>
</div>
</div>
"""
if len(sys.argv) == 1:
INDEX_FILE = os.path.join('.', '_site', 'index.html')
else:
INDEX_FILE = sys.argv[1]
with codecs.open(INDEX_FILE, 'r', 'utf8') as f:
contents = [line for line in f.readlines()]
if contents:
with codecs.open(INDEX_FILE, 'w', 'utf8') as f:
found_start = False
for line in contents:
if not found_start:
f.write(line)
if '<!-- BLOG_HEADLINES_START -->' in line:
f.write(HTML)
found_start = True
continue
if '<!-- BLOG_HEADLINES_END -->' in line:
found_start = False
f.write(line)
continue
#regexp = r'.*(<!-- BLOG_HEADLINES_START -->)(.*)(<!-- BLOG_HEADLINES_END -->).*'
#print (re.search(regexp, contents, re.MULTILINE | re.DOTALL))
#contents = re.sub(regexp, r'\1 MYREPLACE \3', contents, re.DOTALL | re.MULTILINE)
|
