@@ -35,7 +35,6 @@ from .newsParser import newsTheStarMy

 from .newsParser import newsNSTMy

 from .newsParser import newsLaDepeche

 from .newsParser import newsTheGuardian

-from .newsParser import newsBloomberg

 from .newsParser import newsFranceTVInfo

 from .newsParser import newsTheVerge

 from .newsParser import newsBondyBlog

@@ -64,9 +63,9 @@ def articleElement(typeElement,content):

   element=""

   if "\"mainEntityOfPage\": \"https://www.buzzfeed" in content:

     #print("=================== Buzzfeed")

-    if typeElement is "title":

+    if typeElement == "title":

       articleElementBegin ="\"headline\": \""

-    elif typeElement is "description":

+    elif typeElement == "description":

       articleElementBegin ="\"description\": \""

     articleElementEnd   ="\","

     indexElementBegin = content.index(articleElementBegin)

@@ -76,12 +75,12 @@ def articleElement(typeElement,content):

     #print("=================== Lemonde")

     articleElementBegin=""

     articleElementEnd   ="\">"

-    if typeElement is "image":

+    if typeElement == "image":

       articleElementBegin ="<meta property=\"og:image\" content=\"http"

       indexElementBegin = content.index(articleElementBegin)

       indexElementEnd   = content.index(articleElementEnd,indexElementBegin)

       element = "http"+content[indexElementBegin+len(articleElementBegin):indexElementEnd]

-    elif typeElement is "title":

+    elif typeElement == "title":

       articleElementBegin ="<meta property=\"og:title\" content=\""

       indexElementBegin = content.index(articleElementBegin)

       indexElementEnd   = content.index(articleElementEnd,indexElementBegin)

@@ -193,8 +192,6 @@ def getArticle(url):

       data_page += newsParser.newsLaDepeche.article(url)

     elif "guardian.com" in url or "guardian.co.uk" in url:

       data_page += newsParser.newsTheGuardian.article(url)

-    elif "bloomberg.com" in url:

-      data_page += newsParser.newsBloomberg.article(url)

     elif "francetvinfo.fr" in url:

       data_page += newsParser.newsFranceTVInfo.article(url)

     elif "theverge.com" in url:

@@ -1,53 +0,0 @@

-from userio import *

-import requests

-import re

-import newsParser

-

-def article(url):

-  say("Article: "+url)

-  r = requests.get(url, allow_redirects=True, 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'})

-  content = r.text

-  articleCstBegin = "<div class=\"article-content\">"

-  articleCstBegin2 = "<time class=\"article-timestamp\""

-  articleCstEnd   = "<div class=\"bottom-left-rail-touts-spacer\">"

-  try:

-    indexBegin = content.index(articleCstBegin)

-  except:

-    try:

-      indexBegin = content.index(articleCstBegin2)

-    except:

-      indexBegin = 0

-  try:

-    indexEnd   = content.index(articleCstEnd)

-  except:

-    indexEnd   = 0

-  articleStrImageUrl = newsParser.articleImage(content)

-  articleStrTitle = newsParser.articleTitle(content)

-  articleStrDescription = newsParser.articleDescription(content)

-  

-  pageContent = ""

-  pageContent += "<meta property=\"og:type\" content=\"article\">\n"

-  pageContent += "<meta property=\"og:title\" content=\""+articleStrTitle+"\">\n"

-  pageContent += "<meta property=\"og:description\" content=\""+articleStrDescription+"\">\n"

-  pageContent += "<meta property=\"og:url\" content=\""+url+"\">\n"

-  pageContent += "<meta property=\"og:image\" content=\""+articleStrImageUrl+"\">\n"

-  pageContent += "<meta property=\"og:image:type\" content=\"image/jpeg\">"

-  

-  article_only = ""

-  article_only += "<h2>"+articleStrTitle+"</h2>\n"

-  article_only += "<em>"+articleStrDescription+"</em>\n"

-  article_only += "<img src=\""+articleStrImageUrl+"\">\n"

-  article_only += content[indexBegin:indexEnd]

-  article_only = re.sub(r"<div class=\"ac-w-ph__dsc\">Advertisement</div>", '', article_only)

-  article_only = re.sub(r"<h2", '<h3', article_only)

-  article_only = re.sub(r"</h2>", '</h3>', article_only)

-  article_only = re.sub(r"<h1", '<h2', article_only)

-  article_only = re.sub(r"</h1>", '</h2>', article_only)

-  article_only = re.sub(r"<p>Advertisement</p>", '', article_only)

-  article_only = re.sub(r"<picture><source media=\"(.*?)\" srcSet=\"(.*?)\?(.*?)</picture>", "<img src=\"\g<2>\">", article_only)

-  article_only = re.sub(r"<a href=\"#after-(.*?)\" style=\"position:absolute;width:1px;height:1px;margin:-1px;padding:0;border:0;clip:rect\(0 0 0 0\);overflow:hidden\">Continue reading the main story</a>", '', article_only)

-  article_only = article_only.replace("><", ">\n<")

-  

-  article_only = re.sub(r"href=\"\/", 'href=\"//www.nytimes.com/', article_only)

-  pageContent += "<article>"+article_only+"</article>"

-  return pageContent