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
|
from unbiasedObjects import *
import os
import random
import time
#take in a url and delimiters, return twitter card
def buildArticle(url, sourceName):#, titleDelStart, titleDelEnd, imgDelStart, imgDelEnd):
'''#PRINT DEBUGGING
print(sourceName)
print(url)
print()
'''
#download url
os.system('wget -q -O scratch/temp_article.html --no-check-certificate '+url)
#read the file in
f=open('scratch/temp_article.html', 'r', encoding="utf8")
content=f.read()
f.close()
try:
#because the quote separator could be ' or ", trim to just before it then lop it off
img=content.split('og:image" content=')[1][1:].split('>')[0]
if img[-1]=='/':
img=img[:-1].strip()
img=img[:-1]
title=content.split('og:title" content=')[1][1:].split('>')[0]
if title[-1]=='/':
title=title[:-1].strip()
title=title[:-1]
author=''
if sourceName!='The Blaze':
authorTags=['article:author', 'dc.creator']
for tag in authorTags:
if tag in content:
author=content.split(tag+'" content=')[1][1:].split('>')[0]
author=author[:-1]
break
#handle The Blaze
else:
if 'class="article-author">' in content:
author=content.split('class="article-author">')[1].split('<')[0]
elif 'class="article-author" href="' in content:
author=content.split('class="article-author" href="')[1]
author=author.split('>')[1].split('<')[0].strip()
description=content.split('og:description" content=')[1][1:].split('>')[0]
if description[-1]=='/':
description=description[:-1].strip()
description=description[:-1]
#strip out self-references
description=description.replace(sourceName, 'our')
a=Article(title, url, img, description, sourceName, author)
return a
except:
print("Article parsing error in buildArticle() for URL: "+url+" in source "+sourceName+'\n')
return None
def buildOutput(newsSourceArr):
#read in the template html file
f=open('html_template/template.html', 'r')
template=f.read()
f.close()
#set the random order for sources
h1RandomSources=random.sample(range(len(newsSourceArr)), 4)
#For h2s and h3s, select N random sources (can repeat), then
#a non-repetitive random article from within
h2RandomPairs=[]
while len(h2RandomPairs) < 6:
x=random.sample(range(len(newsSourceArr)), 1)[0]
y=random.sample(range(len(newsSourceArr[x].h2Arr)), 1)[0]
pair=[x,y]
if not pair in h2RandomPairs:
h2RandomPairs.append(pair)
h3RandomPairs=[]
while len(h3RandomPairs) < 12:
x=random.sample(range(len(newsSourceArr)), 1)[0]
y=random.sample(range(len(newsSourceArr[x].h3Arr)), 1)[0]
pair=[x,y]
if not pair in h3RandomPairs:
h3RandomPairs.append(pair)
#replace html template locations with data from newsSourceArr
for i in range(len(h1RandomSources)):
source=newsSourceArr[h1RandomSources[i]]
randomArticle=random.sample(range(len(source.h1Arr)), 1)[0]
article=source.h1Arr[randomArticle]
template=template.replace('xxURL1-'+str(i+1)+'xx', article.url)
template=template.replace('xxTitle1-'+str(i+1)+'xx', article.title)
template=template.replace('xxImg1-'+str(i+1)+'xx', article.img)
desc=article.description
if len(desc)>144:
desc=desc[:141]
desc=desc.split()[:-1]
desc=' '.join(desc)+' ...'
template=template.replace('xxDesc1-'+str(i+1)+'xx', desc)
for i in range(len(h2RandomPairs)):
pair=h2RandomPairs[i]
article=newsSourceArr[pair[0]].h2Arr[pair[1]]
template=template.replace('xxURL2-'+str(i+1)+'xx', article.url)
template=template.replace('xxTitle2-'+str(i+1)+'xx', article.title)
template=template.replace('xxImg2-'+str(i+1)+'xx', article.img)
for i in range(len(h3RandomPairs)):
pair=h3RandomPairs[i]
article=newsSourceArr[pair[0]].h3Arr[pair[1]]
template=template.replace('xxURL3-'+str(i+1)+'xx', article.url)
template=template.replace('xxTitle3-'+str(i+1)+'xx', article.title)
template=template.replace('xxImg3-'+str(i+1)+'xx', article.img)
sourcesStr=''
for i in range(len(newsSourceArr)-1):
sourcesStr+=newsSourceArr[i].name+', '
sourcesStr+=newsSourceArr[-1].name
print('Successfully parsed: '+sourcesStr)
template=template.replace('xxSourcesxx', sourcesStr)
#return updated text
return template
def printOutputHTML(outputHTML, outFile):
timestamp=time.strftime("%a, %b %-d, %-I:%M%P %Z", time.localtime())
outputHTML=outputHTML.replace('xxTimexx', timestamp)
f=open(outFile, 'w')
f.write(outputHTML)
f.close()
def buildNewsSourceArr(sourceList):
#build the data structure
i=0
listLen=len(sourceList)
while i < listLen:
source=sourceList[i]
if type(source) is NewsSource2:
i+=1
continue
url=source.url
#download file
os.system('wget -q -O scratch/temp'+str(i)+'.html --no-check-certificate '+url)
#read file
f=open('scratch/temp'+str(i)+'.html', 'r', encoding="utf8")
content=f.read()
f.close()
#delete file MAYBE DON'T DO THIS? CAUSES OS ERRORS
#os.remove('scratch/temp'+str(i)+'.html')
#add stories etc to the NewsSource object
h1s, h2s, h3s=extractURLs(content, source)
#build the Article objects and add to newsSource's appropriate list
if h1s!=None and h2s!=None:
for url in h1s:
article=buildArticle(url, source.name)
if article!=None: source.addArticle(article, 1) #sourceList[i].h1Arr.append(article)
for url in h2s:
article=buildArticle(url, source.name)
if article!=None: sourceList[i].h2Arr.append(article)
for url in h3s:
article=buildArticle(url, source.name)
if article!=None: sourceList[i].h3Arr.append(article)
i+=1
else:
sourceList.remove(source)
listLen-=1
#return the original sourceList,
#since everything should have been modified in place
return sourceList
|
