|
...
|
...
|
@@ -0,0 +1,114 @@
|
|
|
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
|
+ lenBefore=len(article_only)
|
|
|
65
|
+ say("LengthBefore: "+str(lenBefore))
|
|
|
66
|
+ article_only = re.sub(r"<amp-img", '<img', article_only)
|
|
|
67
|
+ article_only = re.sub(r"</amp-img>", '', article_only)
|
|
|
68
|
+ article_only = re.sub(r"<h2", '<h3', article_only)
|
|
|
69
|
+ article_only = re.sub(r"</h2>", '</h3>', article_only)
|
|
|
70
|
+ article_only = re.sub(r"<h1", '<h2', article_only)
|
|
|
71
|
+ article_only = re.sub(r"</h1>", '</h2>', article_only)
|
|
|
72
|
+ #article_only = re.sub(r"<div class=\"slate-ad__label\">Advertisement</div>",'',article_only)
|
|
|
73
|
+ #article_only = re.sub(r"<!-- data-uri=(.+?)-->",'',article_only)
|
|
|
74
|
+ #article_only = re.sub(r"<script data-uri=\"(.+?)</script>",'',article_only,flags=re.M|re.S)
|
|
|
75
|
+ #article_only = re.sub(r"<p class=\"slate-paragraph (.+?)\" data-word-count=\"(.+?)\" data-uri=\"(.+?)\">",'<p>',article_only)
|
|
|
76
|
+ #article_only = re.sub(r"<div class=\"slate-ad__creative\"(.+?)</div>",'',article_only,flags=re.M|re.S)
|
|
|
77
|
+ #article_only = re.sub(r"<div class=\"slate-ad (.+?)</div>",'',article_only,flags=re.M|re.S)
|
|
|
78
|
+ #article_only = re.sub(r"<div class=\"article__share-sidebar-xl share-sidebar\">(.+?)</div>",'',article_only,flags=re.M|re.S)
|
|
|
79
|
+ #article_only = re.sub(r"<div class=\"article__share-sidebar share-sidebar\">(.+?)</div>",'',article_only,flags=re.M|re.S)
|
|
|
80
|
+ #article_only = re.sub(r"<div class=\"article__left-rail\">(.+?)</div>",'',article_only,flags=re.M|re.S)
|
|
|
81
|
+ #article_only = re.sub(r"<div class=\"article__podcast-subscribe\"/>(.+?)</div>",'',article_only,flags=re.M|re.S)
|
|
|
82
|
+ #article_only = re.sub(r"<div class=\"social-share\" aria-label=\"social media links\"(.+?)>(.+?)</div>",'',article_only,flags=re.M|re.S)
|
|
|
83
|
+ #article_only = re.sub(r"<img (.+?)src=\"(.+?)\"(.+?)>",r'<img src="\2">',article_only)
|
|
|
84
|
+ #article_only = re.sub(r"data-uri=\"slate.com",'data-uri="https://slate.com',article_only)
|
|
|
85
|
+ #article_only = re.sub(r"<aside(.+)</aside>",'',article_only,flags=re.M|re.S)
|
|
|
86
|
+ #article_only = re.sub(r"<aside(.+)/>",'',article_only,flags=re.M|re.S)
|
|
|
87
|
+ article_only = re.sub(r"<script(.+)</script>",'',article_only,flags=re.M|re.S)
|
|
|
88
|
+ article_only = re.sub(r"<nav class=\"footer__socials\">(.+)</nav>",'',article_only,flags=re.M|re.S)
|
|
|
89
|
+
|
|
|
90
|
+ article_only = re.sub(r"<form method=\"post\" target=\"_blank\">(.+?)</form>",'',article_only,flags=re.M|re.S)
|
|
|
91
|
+ article_only = re.sub(r"<div class=\"article-header(.+?)\">",'<div>',article_only)
|
|
|
92
|
+ article_only = re.sub(r"<button class=\"sharing-btn(.+?)</button>",'',article_only)
|
|
|
93
|
+ article_only = re.sub(r"<div class=\"article-content(.+?)\">",'<div>',article_only)
|
|
|
94
|
+ article_only = re.sub(r" class=\"article-header__title\"",'',article_only)
|
|
|
95
|
+ article_only = re.sub(r" class=\"article-header__chapo\"",'',article_only)
|
|
|
96
|
+ article_only = re.sub(r"<div class=\"row\">",'<div>',article_only)
|
|
|
97
|
+ article_only = re.sub(r"<div (.+?)/>",'',article_only)
|
|
|
98
|
+ #article_only = re.sub(r"",'',article_only)
|
|
|
99
|
+ article_only = re.sub(r"href=\"/",'href="https://slate.fr/',article_only)
|
|
|
100
|
+ article_only = re.sub(r"src=\"/",'src="https://slate.fr/',article_only)
|
|
|
101
|
+ article_only = re.sub(r"<img class=\"image image--full lazyload\" data-full-src=\"",'<img src="',article_only)
|
|
|
102
|
+ article_only = re.sub(r"<div class=\"sharing-tools(.+?)>(.+?)</div>",'',article_only,flags=re.M|re.S)
|
|
|
103
|
+ article_only = re.sub(r"<div class=\"ad(.+?)>(.+?)</div>",'',article_only,flags=re.M|re.S)
|
|
|
104
|
+ article_only = re.sub(r"^$",'',article_only)
|
|
|
105
|
+ article_only = re.sub(r'^\s*$', '',article_only,flags=re.M|re.S)
|
|
|
106
|
+
|
|
|
107
|
+ #pageContent += "<article>\n"+article_only+"\n</article>\n"
|
|
|
108
|
+ pageContent += article_only+"\n"
|
|
|
109
|
+ lenAfter=len(article_only)
|
|
|
110
|
+ lenGain=float(10000-int(float(100*lenAfter/lenBefore)*100))/100
|
|
|
111
|
+ say("LengthAfter : "+str(lenAfter))
|
|
|
112
|
+ say("Gain : "+str(lenGain)+"%")
|
|
|
113
|
+ return pageContent
|
|
|
114
|
+
|