Fix incorrect soup usage in various recipes

Also make SoupStrainer available in calibre.ebooks.BeautifulSoup

recipes/calcalist.recipe

@@ -1,5 +1,5 @@
 from calibre.web.feeds.news import BasicNewsRecipe
-from calibre.ebooks.BeautifulSoup import re
+import re
 
 
 class AdvancedUserRecipe1283848012(BasicNewsRecipe):

recipes/globes_co_il.recipe

@@ -1,5 +1,5 @@
 from calibre.web.feeds.news import BasicNewsRecipe
-from calibre.ebooks.BeautifulSoup import re
+import re
 
 
 class AdvancedUserRecipe1283848012(BasicNewsRecipe):

recipes/metro_news_nl.recipe

@@ -3,7 +3,6 @@
 from calibre.web.feeds.news import BasicNewsRecipe
 import re
 from calibre.utils.magick import Image
-from calibre.ebooks.BeautifulSoup import BeautifulSoup
 
 ''' Version 1.2, updated cover image to match the changed website.
  added info date on title
@@ -163,7 +162,7 @@ def safeRemovePart(self, killingSoup, soupIsArray):
         return killingSoup
 
 
-class MerryProcess(BeautifulSoup):
+class MerryProcess(object):
     myKiller = MerryExtract()
     myPrepare = MerryPreProcess()
 

recipes/roger_ebert.recipe

@@ -1,7 +1,6 @@
 import re
 import urllib2
 from calibre.web.feeds.news import BasicNewsRecipe
-from calibre.ebooks.BeautifulSoup import BeautifulSoup, SoupStrainer
 
 
 class Ebert(BasicNewsRecipe):
@@ -78,8 +77,8 @@ def parse_index(self):
                     description = match.group(2)
 
                 self.log(thislink)
-
-                for link in BeautifulSoup(thislink, parseOnlyThese=SoupStrainer('a')):
+                soup = self.index_to_soup(thislink)
+                for link in soup.findAll('a', href=True):
                     thisurl = self.PREFIX + link['href']
                     thislinktext = self.tag_to_string(link)
 
@@ -91,7 +90,7 @@ def parse_index(self):
                     if thistitle == '':
                         thistitle = 'Ebert Journal Post'
 
-                    """
+                    r"""
                     pattern2 = r'AID=\/(.*?)\/'
                     reg2 = re.compile(pattern2, re.IGNORECASE|re.DOTALL)
                     match2 = reg2.search(thisurl)

recipes/roger_ebert_blog.recipe

@@ -2,7 +2,6 @@
 import urllib2
 import time
 from calibre.web.feeds.news import BasicNewsRecipe
-from calibre.ebooks.BeautifulSoup import BeautifulSoup, SoupStrainer
 from calibre import strftime
 
 '''
@@ -94,8 +93,9 @@ def parse_index(self):
                     description = match.group(2)
 
                 self.log(thislink)
+                soup = self.index_to_soup(thislink)
 
-                for link in BeautifulSoup(thislink, parseOnlyThese=SoupStrainer('a')):
+                for link in soup.findAll('a', href=True):
                     thisurl = self.PREFIX + link['href']
                     thislinktext = self.tag_to_string(link)
 

src/calibre/ebooks/BeautifulSoup.py

@@ -6,8 +6,8 @@
 
 import bs4
 from bs4 import (  # noqa
-    CData, Comment, Declaration, NavigableString, ProcessingInstruction, Tag,
-    __version__
+    CData, Comment, Declaration, NavigableString, ProcessingInstruction,
+    SoupStrainer, Tag, __version__
 )
 
 from polyglot.builtins import unicode_type