summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorsstvinc2 <sstvinc2@gmail.com>2017-02-18 17:10:13 -0600
committersstvinc2 <sstvinc2@gmail.com>2017-02-18 17:10:13 -0600
commitf19dd7a3291e2d61d4d76eef5300df522193fa1e (patch)
treec2f37c5d2b19b65e47ca33f2575726da073472af
parentf03c0b7c0eb7f607fe271d1e36ec869ee8caca57 (diff)
Fixed NPR parsing; put NYT back in; Mobile CSS
Diffstat
-rw-r--r--html_template/template.html1
-rw-r--r--html_template/unbiased.css55
-rw-r--r--main.py12
-rw-r--r--parser.py46
-rw-r--r--unbiasedFunctions.py1
5 files changed, 94 insertions, 21 deletions
diff --git a/html_template/template.html b/html_template/template.html
index 1c2e858..c0e0711 100644
--- a/html_template/template.html
+++ b/html_template/template.html
@@ -1,6 +1,7 @@
<!DOCTYPE html>
<html>
<head>
+ <meta name="viewport" content="width=device-width; initial-scale=1.0; maximum-scale=1.0; user-scalable=0;" />
<meta charset="utf-8">
<link rel="stylesheet" href="unbiased.css">
<title>UnBiased</title>
diff --git a/html_template/unbiased.css b/html_template/unbiased.css
index 52f1b66..126e194 100644
--- a/html_template/unbiased.css
+++ b/html_template/unbiased.css
@@ -19,8 +19,8 @@ a:link, a:visited, a:hover, a:active {
text-align:center;
padding:.5em 0 1em;
margin-bottom:1em;
- border-bottom:3px solid #f00;
- background:#44a;
+ border-bottom:3px solid #BB133E;
+ background:#002147;
}
.title{
@@ -53,6 +53,12 @@ a:link, a:visited, a:hover, a:active {
margin-right:auto;
}
+@media only screen and (max-width:900px){
+ #page-container{
+ width:100%
+ }
+}
+
#top-stories{
width:95%;
display:block;
@@ -61,7 +67,7 @@ a:link, a:visited, a:hover, a:active {
margin-left:auto;
margin-right:auto;
text-align:center;
- border-bottom: 3px solid #f00;
+ border-bottom: 3px solid #BB133E;
margin-bottom: 10px;
}
@@ -78,6 +84,14 @@ a:link, a:visited, a:hover, a:active {
border:2px solid #ccc;
}
+@media only screen and (max-width:500px){
+ .top-story{
+ display:block;
+ width:auto;
+ height:auto;
+ }
+}
+
.top-stories-img{
width:350px;
height:200px;
@@ -87,6 +101,13 @@ a:link, a:visited, a:hover, a:active {
margin:0 auto;
}
+@media only screen and (max-width:500px){
+ .top-stories-img{
+ width:auto;
+ }
+}
+
+
.top-stories-hed{
font-weight:bold;
font-size:1.35em;
@@ -109,6 +130,13 @@ a:link, a:visited, a:hover, a:active {
float:left;
}
+@media only screen and (max-width:500px){
+ #middle-stories{
+ width:100%;
+ float:none;
+ }
+}
+
.middle-story{
margin:5px 10px;
padding:10px;
@@ -118,6 +146,12 @@ a:link, a:visited, a:hover, a:active {
float:left;
}
+@media only screen and (max-width:500px){
+ .middle-story{
+ width:auto;
+ }
+}
+
.middle-stories-img{
width:150px;
height:100px;
@@ -125,6 +159,7 @@ a:link, a:visited, a:hover, a:active {
background-size: cover;
background-position: center center;
float:left;
+ max-width:35%;
}
.middle-stories-hed{
@@ -134,6 +169,12 @@ a:link, a:visited, a:hover, a:active {
margin-left:10px;
}
+@media only screen and (max-width:500px){
+ .middle-stories-hed{
+ max-width:60%;
+ }
+}
+
#bottom-stories{
margin:0 10px;
padding:10px;
@@ -144,6 +185,14 @@ a:link, a:visited, a:hover, a:active {
border:5px solid #ddd;
}
+@media only screen and (max-width:900px){
+ #bottom-stories{
+ width:auto;
+ border-width:3px;
+ float:none;
+ }
+}
+
.bottom-story{
padding:15px 0;
}
diff --git a/main.py b/main.py
index 5025fdc..8318da0 100644
--- a/main.py
+++ b/main.py
@@ -15,9 +15,17 @@ def main():
def run():
sourceList=[]
+ '''
- #nyt=buildNYT()
- #sourceList.append(nyt)
+ SOURCES TO ADD NEXT:
+ -ABC
+ -REUTERS
+ -THE HILL
+
+ '''
+
+ nyt=buildNYT()
+ sourceList.append(nyt)
npr=buildNPR()
sourceList.append(npr)
diff --git a/parser.py b/parser.py
index 40532f7..5cb1c51 100644
--- a/parser.py
+++ b/parser.py
@@ -100,7 +100,7 @@ def removeDuplicates(h1s, h2s, h3s):
-def removeBadStories(source, badTitleArr, badDescArr, badAuthorArr, badImgArr):
+def removeBadStories(source, badTitleArr, badDescArr, badAuthorArr, badImgArr, badURLArr=None):
arr=[source.h1Arr, source.h2Arr, source.h3Arr]
@@ -159,6 +159,19 @@ def removeBadStories(source, badTitleArr, badDescArr, badAuthorArr, badImgArr):
arr[1].remove(arr[1][0])
print('Removed:\n'+source.name+'\n'+hed.title+' from '+source.name+'\nReason: Image ('+item+')\n')
+ if badURLArr!=None:
+ for i in range(len(arr)):
+ for hed in arr[i]:
+ for item in badURLArr:
+ if item in hed.url:
+ arr[i].remove(hed)
+ #if it's in the h1 slot, bump up the
+ # first h2 into the h1 slot
+ if i==0:
+ arr[0].append(arr[1][0])
+ arr[1].remove(arr[1][0])
+ print('Removed:\n'+source.name+'\n'+hed.title+' from '+source.name+'\nReason: URL ('+item+')\n')
+
return source
@@ -508,7 +521,7 @@ def buildWeeklyStandard():
badTitleArr=None
## if flagged again, remove Micah Mattix
badDescArr=['Matt Labash']
- badAuthorArr=['MATT LABASH', 'TWS PODCAST', 'ERIC FELTEN', 'Steven J. Lenzner']
+ badAuthorArr=['MATT LABASH', 'TWS PODCAST', 'ERIC FELTEN', 'Steven J. Lenzner', 'MARK HEMINGWAY']
badImgArr=['http://www.weeklystandard.com/s3/tws15/images/twitter/tws-twitter_1024x512.png']
wkl=removeBadStories(wkl, badTitleArr, badDescArr, badAuthorArr, badImgArr)
@@ -518,7 +531,7 @@ def buildWeeklyStandard():
def buildNPR():
- url='http://npr.com'
+ url='http://www.npr.org/sections/news/'
name='NPR'
#DOWNLOAD HOMEPAGE CONTENT
@@ -526,7 +539,7 @@ def buildNPR():
#get main headline
h1=content
- h1=h1.split('<div id="contentWrap">', 1)[1]
+ h1=h1.split('<a id="mainContent">', 1)[1]
h1=h1.split('<a href="', 1)[1]
h1=h1.split('"', 1)[0]
h1s=[h1]
@@ -534,10 +547,11 @@ def buildNPR():
#GET SECONDARY HEADLINES
h2=content
h2s=[]
- h2=h2.split('<article class="hp-item attachment volume-low">', 1)[1]
- h2=h2.split('</section>', 1)[0]
- while 'href="' in h2:
- h2=h2.split('href="', 1)[1]
+ h2=h2.split('<article class="item has-image">', 1)[1]
+ h2=h2.split('<!-- END CLASS=\'FEATURED-3-UP\' -->', 1)[0]
+ while '<article class="item has-image">' in h2:
+ h2=h2.split('<article class="item has-image">', 1)[1]
+ h2=h2.split('<a href="', 1)[1]
x=h2.split('"', 1)[0]
if h1 not in x:
h2s.append(x)
@@ -545,15 +559,16 @@ def buildNPR():
#GET TERTIARY HEADLINES
h3=content
h3s=[]
- h3=h3.split('<ul id="nib-list">', 1)[1]
- h3=h3.split('</ul>', 1)[0]
- while 'href=\'' in h3:
- h3=h3.split('href=\'', 1)[1]
- x=h3.split('\'', 1)[0]
+ h3=h3.split('<div id="overflow" class="list-overflow"', 1)[1]
+ h3=h3.split('<!-- END ID="OVERFLOW" CLASS="LIST-OVERFLOW"', 1)[0]
+ while '<h2 class="title"><a href="' in h3:
+ h3=h3.split('<h2 class="title"><a href="', 1)[1]
+ x=h3.split('"', 1)[0]
if h1 not in x:
h3s.append(x)
h1s, h2s, h3s = removeDuplicates(h1s, h2s, h3s)
+
npr=buildNewsSource2(name, url, h1s, h2s, h3s)
#REMOVE BAD STORIES
@@ -611,7 +626,8 @@ def buildFoxNews():
badDescArr=None
badAuthorArr=['Bill O\'Reilly', 'Sean Hannity']
badImgArr=['http://www.foxnews.com/content/dam/fox-news/logo/og-fn-foxnews.jpg']
- fox=removeBadStories(fox, badTitleArr, badDescArr, badAuthorArr, badImgArr)
+ badURLArr=['http://www.foxnews.com/opinion']
+ fox=removeBadStories(fox, badTitleArr, badDescArr, badAuthorArr, badImgArr, badURLArr)
return fox
@@ -673,8 +689,6 @@ def buildNYT():
if (h1 not in x) and (x not in h2s):
h2s.append(x)
- print(h2s)
-
#GET TERTIARY HEADLINES
h3=content
h3s=[]
diff --git a/unbiasedFunctions.py b/unbiasedFunctions.py
index 748aed7..ef0265f 100644
--- a/unbiasedFunctions.py
+++ b/unbiasedFunctions.py
@@ -103,6 +103,7 @@ def buildOutput(newsSourceArr):
h3RandomPairs=[]
while len(h3RandomPairs) < 12:
x=random.sample(range(len(newsSourceArr)), 1)[0]
+ print(newsSourceArr[x].name)
y=random.sample(range(len(newsSourceArr[x].h3Arr)), 1)[0]
pair=[x,y]
if not pair in h3RandomPairs:
generated by cgit v1.2.3 (git 2.39.1) at 2024-11-22 05:21:53 +0000