Showing 1 changed files with 140 additions and 0 deletions
+140
newsParser/newsParser/newsSlateCom.py
... ...
@@ -0,0 +1,140 @@
1
+from userio import *
2
+import requests
3
+import re
4
+from requests_html import HTML    
5
+from requests_html import HTMLSession
6
+
7
+def articleImage(content):
8
+  articleImgBegin ="<meta property=\"og:image\" content=\""
9
+  articleImgEnd   ="\""
10
+  indexImgBegin = content.index(articleImgBegin)
11
+  indexImgEnd   = content.index(articleImgEnd,indexImgBegin+len(articleImgBegin))
12
+  try:
13
+    image = content[indexImgBegin+len(articleImgBegin):indexImgEnd]
14
+  except:
15
+    image = "favicon.png"
16
+  return image
17
+
18
+def articleDescription(content):
19
+  articleImgBegin ="<meta property=\"og:description\" content=\""
20
+  articleImgEnd   ="\""
21
+  indexImgBegin = content.index(articleImgBegin)
22
+  indexImgEnd   = content.index(articleImgEnd,indexImgBegin+len(articleImgBegin))
23
+  try:
24
+    title = content[indexImgBegin+len(articleImgBegin):indexImgEnd]
25
+  except:
26
+    title = "Description Extraction Failed"
27
+  return title
28
+
29
+def articleTitle(content):
30
+  #articleImgBegin ="<meta property=\"og:title\" content=\""
31
+  articleImgBegin ="\"og:title\" content=\""
32
+  articleImgEnd   ="\""
33
+  indexImgBegin = content.index(articleImgBegin)
34
+  indexImgEnd   = content.index(articleImgEnd,indexImgBegin+len(articleImgBegin))
35
+  try:
36
+    title = content[indexImgBegin+len(articleImgBegin):indexImgEnd]
37
+  except:
38
+    title = "Title Extraction Failed"
39
+  return title
40
+
41
+def article(url):
42
+  say("Article: "+url)
43
+  session = HTMLSession()
44
+  response = session.get(url,timeout=20)
45
+  pageContent=""
46
+  article_only=""
47
+  with response as r:
48
+    #articleStrTitle=r.html.find('title')[0].text
49
+    articleStrTitle = r.html.xpath('//meta[@property="og:title"]/@content')[0]
50
+    articleStrDescription = r.html.xpath('//meta[@property="og:description"]/@content')[0]
51
+    articleStrImageUrl = r.html.xpath('//meta[@property="og:image"]/@content')[0]
52
+    articleStrAuthor = r.html.xpath('//meta[@name="author"]/@content')[0]
53
+    article=r.html.find("article")[0]
54
+    pageContent += "<meta property=\"og:type\" content=\"article\" />\n"
55
+    pageContent += "<meta property=\"og:title\" content=\""+articleStrTitle+"\" />\n"
56
+    pageContent += "<meta property=\"og:description\" content=\""+articleStrDescription+"\" />\n"
57
+    pageContent += "<meta property=\"og:url\" content=\""+url+"\" />\n"
58
+    pageContent += "<meta property=\"og:image\" content=\""+articleStrImageUrl+"\" />\n"
59
+    pageContent += "<meta property=\"og:image:type\" content=\"image/jpeg\" />\n"
60
+    pageContent += "<meta name=\"author\" content=\""+articleStrAuthor+"\" />\n"
61
+    article_only+=article.html
62
+
63
+
64
+  article_only = re.sub(r"<amp-img", '<img', article_only)
65
+  article_only = re.sub(r"</amp-img>", '', article_only)
66
+  article_only = re.sub(r"<h2", '<h3', article_only)
67
+  article_only = re.sub(r"</h2>", '</h3>', article_only)
68
+  article_only = re.sub(r"<h1", '<h2', article_only)
69
+  article_only = re.sub(r"</h1>", '</h2>', article_only)
70
+  article_only = re.sub(r"<div class=\"slate-ad__label\">Advertisement</div>",'',article_only)
71
+  article_only = re.sub(r"<!-- data-uri=(.+?)-->",'',article_only)
72
+  article_only = re.sub(r"<script data-uri=\"(.+?)</script>",'',article_only,flags=re.M|re.S)
73
+  article_only = re.sub(r"<p class=\"slate-paragraph (.+?)\" data-word-count=\"(.+?)\" data-uri=\"(.+?)\">",'<p>',article_only)
74
+  article_only = re.sub(r"<div class=\"slate-ad__creative\"(.+?)</div>",'',article_only,flags=re.M|re.S)
75
+  article_only = re.sub(r"<div class=\"slate-ad (.+?)</div>",'',article_only,flags=re.M|re.S)
76
+  article_only = re.sub(r"<div class=\"article__share-sidebar-xl share-sidebar\">(.+?)</div>",'',article_only,flags=re.M|re.S)
77
+  article_only = re.sub(r"<div class=\"article__share-sidebar share-sidebar\">(.+?)</div>",'',article_only,flags=re.M|re.S)
78
+  article_only = re.sub(r"<div class=\"article__left-rail\">(.+?)</div>",'',article_only,flags=re.M|re.S)
79
+  article_only = re.sub(r"<div class=\"article__podcast-subscribe\"/>(.+?)</div>",'',article_only,flags=re.M|re.S)
80
+  article_only = re.sub(r"<div class=\"social-share\" aria-label=\"social media links\"(.+?)>(.+?)</div>",'',article_only,flags=re.M|re.S)
81
+  article_only = re.sub(r"<img (.+?)src=\"(.+?)\"(.+?)>",r'<img src="\2">',article_only)
82
+  article_only = re.sub(r"data-uri=\"slate.com",'data-uri="https://slate.com',article_only)
83
+  article_only = re.sub(r"<aside(.+)</aside>",'',article_only,flags=re.M|re.S)
84
+  article_only = re.sub(r"<aside(.+)/>",'',article_only,flags=re.M|re.S)
85
+  article_only = re.sub(r"<noscript(.+)</noscript>",'',article_only,flags=re.M|re.S)
86
+  #article_only = re.sub(r"",'',article_only)
87
+  article_only = re.sub(r"href=\"/",'href="https://slate.com/,',article_only)
88
+  article_only = re.sub(r"^$",'',article_only)
89
+  article_only = re.sub(r'^\s*$', '',article_only,flags=re.M|re.S)
90
+
91
+  pageContent += "<article>\n"+article_only+"\n</article>\n"
92
+  say("Length: "+str(len(article_only)))
93
+  return pageContent
94
+
95
+def articleOld(url):
96
+  say("Article: "+url)
97
+  r = requests.get(url, allow_redirects=True)
98
+  content = r.text
99
+  r.html.find('article')
100
+
101
+  articleStrImageUrl = articleImage(content)
102
+  articleStrTitle = articleTitle(content)
103
+  articleStrDescription = articleDescription(content)
104
+  
105
+  pageContent = ""
106
+  pageContent += "<meta property=\"og:type\" content=\"article\">\n"
107
+  pageContent += "<meta property=\"og:title\" content=\""+articleStrTitle+"\">\n"
108
+  pageContent += "<meta property=\"og:description\" content=\""+articleStrDescription+"\">\n"
109
+  pageContent += "<meta property=\"og:url\" content=\""+url+"\">\n"
110
+  pageContent += "<meta property=\"og:image\" content=\""+articleStrImageUrl+"\">\n"
111
+  pageContent += "<meta property=\"og:image:type\" content=\"image/jpeg\">\n"
112
+  
113
+  articleCstBegin = "<article"
114
+  articleCstEnd   = "</article>"
115
+  articleCstBegin2 = "<body"
116
+  articleCstEnd2   = "</body>"
117
+  try:
118
+    indexBegin = content.index(articleCstBegin)
119
+  except:
120
+    try:
121
+      indexBegin = content.index(articleCstBegin2)
122
+    except:
123
+      indexBegin = 0
124
+  try:
125
+    indexEnd   = content.index(articleCstEnd)
126
+  except:
127
+    try:
128
+      indexEnd = content.index(articleCstEnd2)
129
+    except:
130
+      indexEnd = strlen(content)
131
+  article_only = content[indexBegin:indexEnd]
132
+  article_only = re.sub(r"<amp-img", '<img', article_only)
133
+  article_only = re.sub(r"</amp-img>", '', article_only)
134
+  article_only = re.sub(r"<h2", '<h3', article_only)
135
+  article_only = re.sub(r"</h2>", '</h3>', article_only)
136
+  article_only = re.sub(r"<h1", '<h2', article_only)
137
+  article_only = re.sub(r"</h1>", '</h2>', article_only)
138
+  article_only = article_only.replace("><", ">\n<")
139
+  pageContent += "<article>"+article_only+"</article>"
140
+  return pageContent