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
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
|
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(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()
#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]#[:-1]
if img[-1]=='/':
img=img[:-1].strip()
img=img[:-1]
title=content.split('og:title" content=')[1][1:].split('>')[0]#[1].split('"')[0]
if title[-1]=='/':
title=title[:-1].strip()
title=title[:-1]
a=Article(title, url, img, sourceName)
return a
#do the hardcore HTML parsing
def splitHTML(content, sectionDividerStart, sectionDividerEnd, delStart, delEnd):
retArr=[]
if sectionDividerStart!=None:
content=content.split(sectionDividerStart)[1]
if sectionDividerEnd!=None:
content=content.split(sectionDividerEnd)[0]
if delStart!=[]:
while True:
x=content
for delim in delStart:
if delim in content:
x=content.split(delim)[1]
x=x.split(delEnd)[0]
if x not in retArr:
retArr.append(x)
content=content.split(delStart[0], 1)
if(len(content)==1):
break
else:
content=content[1:][0]
return retArr
'''
**********************8
Need to fix this function to use splitHTML() and actually loop through
all of the links instead of just using the first one.
************************
'''
#take in a read main source file (e.g. from nytimes.com) and return lists of the urls for stories
def extractURLs(content, source):
h1s=[]
h2s=[]
h3s=[]
h1=content
if source.h1SectionDividerStart!=None:
h1=h1.split(source.h1SectionDividerStart)[1]
if source.h1SectionDividerEnd!=None:
h1=h1.split(source.h1SectionDividerEnd)[0]
for delim in source.h1DelStart:
h1=h1.split(delim)[1]
h1=h1.split(source.h1DelEnd)[0]
if '.com' not in h1:
h1=source.url+h1
h1s.append(h1)
h2=content
if source.h2SectionDividerStart!=None:
h2=h2.split(source.h2SectionDividerStart, 1)[1]
if source.h2SectionDividerEnd!=None:
h2=h2.split(source.h2SectionDividerEnd, 1)[0]
while source.h2DelStart[0] in h2:
x=h2
for delim in source.h2DelStart:
x=x.split(delim)[1]
h2=h2.split(delim, 1)[1]
x=x.split(source.h2DelEnd)[0]
h2=h2.split(source.h2DelEnd, 1)[1]
if '.com' not in x:
x=source.url+x
h2s.append(x)
'''
h2=content.split(source.h2SectionDividerStart, 1)[1]
h2=h2.split(source.h2SectionDividerEnd, 1)[0]
if source.h2DelStart!=[]:
while True:
x=h2
for delim in source.h2DelStart:
if delim in h2:
x=h2.split(delim)[1]
x=x.split(source.h2DelEnd)[0]
if '.com' not in x:
x=source.url+x
if x not in h2s:
h2s.append(x)
print(x)
h2=h2.split(source.h2DelStart[0], 1)
if(len(h2)==1):
break
else:
h2=h2[1]#:][0]
h2s=splitHTML(content,
source.h2SectionDividerStart,
source.h2SectionDividerEnd,
source.h2DelStart,
source.h2DelEnd)
if source.h2SectionDividerStart!=None:
h2=h2.split(source.h2SectionDividerStart)[1]
if source.h2SectionDividerEnd!=None:
h2=h2.split(source.h2SectionDividerEnd)[0]
delim0=source.h2DelStart[0]
while delim0 in h2:
for delim in source.h2DelStart:
url=h2.split(delim)[1]
h2=''.join(h2.split(delim)[1:])
url=h2.split(source.h2DelEnd)[0]
h2=h2.split(source.h2DelEnd)[1]
if '.com' not in url:
url=source.url+url
h2s.append(url)
print(len(h2s))
h3s=splitHTML(content,
source.h3SectionDividerStart,
source.h3SectionDividerEnd,
source.h3DelStart,
source.h3DelEnd)
'''
return h1s, h2s, h3s
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)
h2RandomSources=random.sample(range(len(newsSourceArr)), 4)
'''
print(h3RandomSources)
h2RandomSources=random.sample(range(len(newsSourceArr)), 1)
print(h3RandomSources)
'''
#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)
for i in range(len(h2RandomSources)):
source=newsSourceArr[h2RandomSources[i]]
randomArticle=random.sample(range(len(source.h2Arr)), 1)[0]
article=source.h2Arr[randomArticle]
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)
#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
for i in range(len(sourceList)):
source=sourceList[i]
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
for url in h1s:
article=buildArticle(url, source.name)
source.addArticle(article, 1) #sourceList[i].h1Arr.append(article)
for url in h2s:
article=buildArticle(url, source.name)
sourceList[i].h2Arr.append(article)
for url in h3s:
article=buildArticle(url, source.name)
sourceList[i].h3Arr.append(article)
#return the original sourceList,
#since everything should have been modified in place
return sourceList
|
