Thread: maya recipe
View Single Post
Old 10-18-2010, 05:01 AM   #25
marbs
Zealot
marbs began at the beginning.
 
Posts: 122
Karma: 10
Join Date: Jul 2010
Device: nook
i still need a bit more help on this one.

so i have changed what i what form my recipe. i will try to write the full version in pure python later, but now i want to do this as a recipe.

if you take a look here you will see a list links on the page. i want the article title to be "the 1st link text" - "the 2nd link text"
right now it is just "the 2nd link next". the id of the 1st link is "CompNmHref" i just dont know how to do it with the for loop and soup. is there a "tag before" command in soup? because we are talikng about the tag befor the "item" in my code...


Spoiler:
Code:
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import BeautifulSoup, re
class AlisonB(BasicNewsRecipe):
    title      ='Maya'
    __author__ = 'marbs'
    description = 'blah'
    language = 'en'
    no_stylesheets = True
    publisher           = 'marbs'
#    simultaneous_downloads = 1
#    delay                  = 25   
    category            = 'column'
    extra_css='body{direction: rtl;} .article_description{direction: rtl; } a.article{direction: rtl; } .calibre_feed_description{direction: rtl; }'
#    no_stylesheets = True
    use_embedded_content= False
    remove_attributes = ['width','height']
    no_stylesheets      = True
    oldest_article      = 24
    remove_javascript   = True
    remove_empty_feeds  = True
    
    max_articles_per_feed = 5000
    INDEX = 'http://maya.tase.co.il/'
    

    def parse_index(self):
        feeds = []
        for title, url in [
                            #(u"Feed", u"http://maya.tase.co.il/bursa/index.asp?view=search&company_group=3000&arg_comp=&srh_comp_lb=1007&srh_from=2010-01-01&srh_until=2010-09-28&srh_anaf=-1&srh_event=9999&is_urgent=0&srh_company_press="),
                            (u"הודעות מאתמול", u"http://maya.tase.co.il/bursa/index.asp?view=yesterday"),                            
                            
                             ]:
            articles = self.make_links(url)
            if articles:
                feeds.append((title, articles))
        return feeds
        
    def make_links(self, url):
        title = 'Temp'
        current_articles = []
        soup = self.index_to_soup(url)
        print 'url is', url

#        print 'The soup is: ', soup
        for item in soup.findAll('a',attrs={'class':'A3'}):
            print 'item is: ',item
            #link = item.find('a')
            #titlecheck = self.tag_to_string(link)
            #url_test = re.search('javascript', item['href'])
           
            if not re.search('javascript', item['href']):
              temp2= self.INDEX + 'bursa/' + item['href']
        #      temp2=[temp3]
              print 'url1 is', temp2
              soup1 = self.index_to_soup(temp2)
  #            print 'the new soup is', soup1
              print '6714' 
              for item1 in soup1.findAll('iframe'):
                 print 'item1 is:' , item1
                 txt= item1['src']
                 print 'FOUND GOOD URL'
                 re1='.*?'	# Non-greedy match on filler
                 re2='(mayafiles)'	# Variable Name 1
                 re3='(.)'	# Any Single Character 1
                 re4='.*?'	# Non-greedy match on filler
                 re5='htm'	# Uninteresting: word
                 re6='.*?'	# Non-greedy match on filler
                 re7='(htm)'	# Word 1
                 
                 rg = re.compile(re1+re2+re3+re4+re5+re6+re7,re.IGNORECASE|re.DOTALL)
                 m = rg.search(txt)
                 if m:
                     var1=m.group(1)
                     c1=m.group(2)
                     word1=m.group(3)
                     print "("+var1+")"+"("+c1+")"+"("+word1+")"+"\n"
                     url = item1['src']
                 else:
                     url = 'http://www.pdfdownload.org/pdf2html/pdf2html.php?url=' + item1['src'] + '&images=yes'

                 print 'url is: ', url
                 title       = self.tag_to_string(item)
                 print 'title is: ', title
                 current_articles.append({'title': title, 'url': url, 'description':'', 'date':''}) # append all this
            
           
        return current_articles
marbs is offline   Reply With Quote