|
...
|
...
|
@@ -2,8 +2,9 @@ from userio import *
|
|
2
|
2
|
import requests
|
|
3
|
3
|
import re
|
|
4
|
4
|
import newsParser
|
|
|
5
|
+from requests_html import HTML
|
|
|
6
|
+from requests_html import HTMLSession
|
|
5
|
7
|
|
|
6
|
|
-
|
|
7
|
8
|
def article(url):
|
|
8
|
9
|
say("Article: "+url)
|
|
9
|
10
|
if not "/amphtml" in url:
|
|
...
|
...
|
@@ -12,6 +13,62 @@ def article(url):
|
|
12
|
13
|
url = url.replace("buzzfeed.com/","buzzfeed.com/amphtml/")
|
|
13
|
14
|
url.replace("?origin=web-hf","")
|
|
14
|
15
|
|
|
|
16
|
+ session = HTMLSession()
|
|
|
17
|
+ response = session.get(url,timeout=20,headers={'Accept-Encoding': 'deflate', 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.212 Safari/537.36'})
|
|
|
18
|
+ pageContent=""
|
|
|
19
|
+ article_only=""
|
|
|
20
|
+ with response as r:
|
|
|
21
|
+ #articleStrTitle = r.html.xpath('//meta[@property="og:title"]/@content')[0]
|
|
|
22
|
+ #articleStrDescription = r.html.xpath('//meta[@property="og:description"]/@content')[0]
|
|
|
23
|
+ #articleStrImageUrl = r.html.xpath('//meta[@property="og:image"]/@content')[0]
|
|
|
24
|
+ #articleStrAuthor = r.html.xpath('//div[@class="author_wrapper"]/@content')
|
|
|
25
|
+ #print(articleStrAuthor)
|
|
|
26
|
+ article=r.html.find("main")[0]
|
|
|
27
|
+ #article=r.html.find("body")[0]
|
|
|
28
|
+ article_only+=article.html
|
|
|
29
|
+ lenBefore=len(article_only)
|
|
|
30
|
+ say("LengthBefore: "+str(lenBefore))
|
|
|
31
|
+ pageContent += "<meta property=\"og:type\" content=\"article\" />\n"
|
|
|
32
|
+ #pageContent += "<meta property=\"og:title\" content=\""+articleStrTitle+"\" />\n"
|
|
|
33
|
+ #pageContent += "<meta property=\"og:description\" content=\""+articleStrDescription+"\" />\n"
|
|
|
34
|
+ pageContent += "<meta property=\"og:url\" content=\""+url+"\" />\n"
|
|
|
35
|
+ #pageContent += "<meta property=\"og:image\" content=\""+articleStrImageUrl+"\" />\n"
|
|
|
36
|
+ pageContent += "<meta property=\"og:image:type\" content=\"image/jpeg\" />\n"
|
|
|
37
|
+ #pageContent += "<meta name=\"author\" content=\""+articleStrAuthor+"\" />\n"
|
|
|
38
|
+
|
|
|
39
|
+ article_only = re.sub(r"<amp-img", '<img', article_only)
|
|
|
40
|
+ article_only = re.sub(r"</amp-img>", '', article_only)
|
|
|
41
|
+ article_only = re.sub(r"<h2", '<h3', article_only)
|
|
|
42
|
+ article_only = re.sub(r"</h2>", '</h3>', article_only)
|
|
|
43
|
+ article_only = re.sub(r"<h1", '<h2', article_only)
|
|
|
44
|
+ article_only = re.sub(r"</h1>", '</h2>', article_only)
|
|
|
45
|
+ article_only = re.sub(r'<nav class="newsblock-trending-tags-bar__nav"(.+?)</nav>','',article_only,flags=re.M|re.S)
|
|
|
46
|
+ article_only = re.sub(r'<div class="newsblock-trending-tags-bar__title-wrapper"(.+?)</div>','',article_only,flags=re.M|re.S)
|
|
|
47
|
+ article_only = re.sub(r'<amp-ad type(.+?)</amp-ad>','',article_only,flags=re.M|re.S)
|
|
|
48
|
+ article_only = re.sub(r'<amp-social-share(.+?)</amp-social-share>','',article_only,flags=re.M|re.S)
|
|
|
49
|
+ article_only = re.sub(r'<p class="xs-pb1 xs-pt1 xs-text-center caps xs-text-6 text-gray-lightest ad__disclosure">(.+?)</p>','',article_only,flags=re.M|re.S)
|
|
|
50
|
+ #article_only = re.sub(r'','',article_only)
|
|
|
51
|
+ #article_only = re.sub(r"href=\"/",'href="https://bfmtv.com/',article_only)
|
|
|
52
|
+ #article_only = re.sub(r"src=\"/",'src="https://bfmtv.com/',article_only)
|
|
|
53
|
+ article_only = re.sub(r"^$",'',article_only)
|
|
|
54
|
+ article_only = re.sub(r'^\s*$', '',article_only,flags=re.M|re.S)
|
|
|
55
|
+ article_only = re.sub(r"><",'>\n<',article_only)
|
|
|
56
|
+
|
|
|
57
|
+ pageContent += "<article>\n"+article_only+"\n</article>\n"
|
|
|
58
|
+ lenAfter=len(article_only)
|
|
|
59
|
+ lenGain=float(10000-int(float(100*lenAfter/lenBefore)*100))/100
|
|
|
60
|
+ say("LengthAfter : "+str(lenAfter))
|
|
|
61
|
+ say("Gain : "+str(lenGain)+"%")
|
|
|
62
|
+ return pageContent
|
|
|
63
|
+
|
|
|
64
|
+def articleOld(url):
|
|
|
65
|
+ say("Article: "+url)
|
|
|
66
|
+ if not "/amphtml" in url:
|
|
|
67
|
+ say("Trying AMP")
|
|
|
68
|
+ url = url.replace("buzzfeednews.com/article","buzzfeednews.com/amphtml")
|
|
|
69
|
+ url = url.replace("buzzfeed.com/","buzzfeed.com/amphtml/")
|
|
|
70
|
+ url.replace("?origin=web-hf","")
|
|
|
71
|
+
|
|
15
|
72
|
r = requests.get(url, allow_redirects=True)
|
|
16
|
73
|
content = r.text
|
|
17
|
74
|
pageContent = ""
|