|
...
|
...
|
@@ -10,15 +10,35 @@ def article(url):
|
|
10
|
10
|
say("Article: "+url)
|
|
11
|
11
|
session = HTMLSession()
|
|
12
|
12
|
response = session.get(url,timeout=20)
|
|
|
13
|
+ say("Return code: "+str(response.status_code))
|
|
13
|
14
|
pageContent=""
|
|
14
|
15
|
article_only=""
|
|
15
|
16
|
with response as r:
|
|
16
|
|
- articleStrTitle = r.html.xpath('//meta[@property="og:title"]/@content')[0]
|
|
17
|
|
- articleStrDescription = r.html.xpath('//meta[@property="og:description"]/@content')[0]
|
|
18
|
|
- articleStrImageUrl = r.html.xpath('//meta[@property="og:image"]/@content')[0]
|
|
19
|
|
- articleStrAuthor = r.html.xpath('//div[@class="author_wrapper"]/@content')
|
|
20
|
|
- article=r.html.find("article")[0]
|
|
21
|
|
- article_only+=article.html
|
|
|
17
|
+ articleStrTitle = ""
|
|
|
18
|
+ articleStrDescription = ""
|
|
|
19
|
+ articleStrImageUrl = ""
|
|
|
20
|
+ articleStrAuthor = ""
|
|
|
21
|
+ try:
|
|
|
22
|
+ articleStrTitle = r.html.xpath('//meta[@property="og:title"]/@content')[0]
|
|
|
23
|
+ articleStrDescription = r.html.xpath('//meta[@property="og:description"]/@content')[0]
|
|
|
24
|
+ articleStrImageUrl = r.html.xpath('//meta[@property="og:image"]/@content')[0]
|
|
|
25
|
+ articleStrAuthor = r.html.xpath('//div[@class="author_wrapper"]/@content')
|
|
|
26
|
+ except:
|
|
|
27
|
+ error("Extracting Metadatas")
|
|
|
28
|
+ article_only+="<p>ERROR: Extracting Metadatas<p>"
|
|
|
29
|
+ try:
|
|
|
30
|
+ article=r.html.find("article")[0]
|
|
|
31
|
+ article_only+=article.html
|
|
|
32
|
+ except:
|
|
|
33
|
+ #article_only+="<p>WARN: Tag not found<p>"
|
|
|
34
|
+ #article_only+="<p><a href=\""+url+"\">"+url+"</a></p>"
|
|
|
35
|
+ article_only+="<h1>"+articleStrTitle+"</h1>\n"
|
|
|
36
|
+ article_only+="<em>"+articleStrDescription+"</em>\n"
|
|
|
37
|
+ article_only+="<img src=\""+articleStrImageUrl+"\">\n"
|
|
|
38
|
+ for div in r.html.find('div'):
|
|
|
39
|
+ if "class" in div.attrs:
|
|
|
40
|
+ if "article-body" in div.attrs['class']:
|
|
|
41
|
+ article_only+=div.html+"\n"
|
|
22
|
42
|
lenBefore=len(article_only)
|
|
23
|
43
|
say("LengthBefore: "+str(lenBefore))
|
|
24
|
44
|
pageContent += "<meta property=\"og:type\" content=\"article\" />\n"
|
|
...
|
...
|
@@ -63,7 +83,9 @@ def article(url):
|
|
63
|
83
|
#pageContent += "\n"+article_only+"\n"
|
|
64
|
84
|
pageContent += "<article>\n"+article_only+"\n</article>\n"
|
|
65
|
85
|
lenAfter=len(article_only)
|
|
66
|
|
- lenGain=float(10000-int(float(100*lenAfter/lenBefore)*100))/100
|
|
|
86
|
+ lenGain=0
|
|
|
87
|
+ if lenBefore != 0:
|
|
|
88
|
+ lenGain=float(10000-int(float(100*lenAfter/lenBefore)*100))/100
|
|
67
|
89
|
say("LengthAfter : "+str(lenAfter))
|
|
68
|
90
|
say("Gain : "+str(lenGain)+"%")
|
|
69
|
91
|
return pageContent
|