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
|
#!/usr/bin/env python3
from unbiasedObjects import *
from unbiasedFunctions import *
import time
def main():
while True:
print('-----------------------')
run()
print('-----------------------')
time.sleep(120)
def run():
sourceList=[]
sourceList.append(NewsSource('New York Times',
'http://nytimes.com',
['<a href="'],#'<h1 class="story-heading"><a href="'],#['"b-column column', 'h2 class="story-heading"><a href="'],
['article class="story theme-summary', 'h2 class="story-heading"><a href="'],
['<hr class="single-rule"', 'article class="story theme-summary', 'h2 class="story-heading"><a href="'],
'<div class="b-column column">', '<!-- close photo-spot-region -->',
'section id="top-news" class="top-news"', '</div><!-- close a-column -->',
'class="second-column-region region"', 'html.geo-dma-501 .nythpNYRegionPromo'))
sourceList.append(NewsSource('Fox News',
'http://foxnews.com',
['<h1><a href="'],
['<li data-vr-contentbox=""><a href="'],
[],
None, None,
'<div class="top-stories">', '<section id="latest"',
None, None))
sourceList.append(NewsSource('NBC News',
'http://nbcnews.com',
['top-stories-section', 'panel_hero', '<a href="'],
['panel panel_default', '<a href="'],
[],
None, None,
'row_no-clear ad-container ad-container_default ad-hide ad-container-mobilebox1', 'js-more-topstories',
None, None))
sourceList.append(NewsSource('CBS News',
'http://cbsnews.com',
['<h1 class="title"><a href="'],
['<li data-tb-region-item>', '<a href="'],
[],
None, None,
'Big News Area Side Assets', '</ul></div>',
None, None))
#scrape all urls and build data structure
newsSourceArr=buildNewsSourceArr(sourceList)
#build the output file HTML
outputHTML=buildOutput(newsSourceArr)
#print the output file HTML
printOutputHTML(outputHTML, '/var/www/html/index.html')#'unbiased.html')
if __name__=="__main__":
main()
|
