diff --git a/recipes/geek_poke.recipe b/recipes/geek_poke.recipe index 7f5117b586..7a241db407 100644 --- a/recipes/geek_poke.recipe +++ b/recipes/geek_poke.recipe @@ -1,6 +1,6 @@ from calibre.web.feeds.news import BasicNewsRecipe import re -from calibre.utils.magick import Image +from calibre.utils.magick import Image, create_canvas class AdvancedUserRecipe1307556816(BasicNewsRecipe): title = u'Geek and Poke' @@ -11,7 +11,7 @@ class AdvancedUserRecipe1307556816(BasicNewsRecipe): oldest_article = 31 max_articles_per_feed = 100 language = u'en' - simultaneous_downloads = 5 + simultaneous_downloads = 1 #delay = 1 timefmt = ' [%a, %d %B, %Y]' summary_length = -1 @@ -22,6 +22,7 @@ class AdvancedUserRecipe1307556816(BasicNewsRecipe): remove_javascript = True remove_empty_feeds = True publication_type = 'blog' + masthead_url = None conversion_options = { 'comments' : '' ,'tags' : category @@ -44,28 +45,38 @@ class AdvancedUserRecipe1307556816(BasicNewsRecipe): (r'yimg\.com'), (r'scorecardresearch\.com')] - preprocess_regexps = [(re.compile(r'(

( |\s)*

|]*>Tweet|]*>|)', re.DOTALL|re.IGNORECASE),lambda match: ''), + preprocess_regexps = [(re.compile(r'(

( |\s)*

|]*>Tweet|]*>|||]*>[^<]*[^<]*)', re.DOTALL|re.IGNORECASE),lambda match: ''), (re.compile(r'( |\s\s)+\s*', re.DOTALL|re.IGNORECASE),lambda match: ' '), - (re.compile(r']*>([^<]*)[^>]*(]*>)', re.DOTALL|re.IGNORECASE), lambda match: match.group(2) + '
' + match.group(1) + '
'), (re.compile(r'(]*>)]>((?!', re.DOTALL|re.IGNORECASE),lambda match: match.group(1) + match.group(2) + ''), - (re.compile(r'(]*alt="([^"]*)"[^>]*>)', re.DOTALL|re.IGNORECASE),lambda match: match.group(1) + '
' + match.group(2) + ''), + (re.compile(r'(]*alt="([^"]*)"[^>]*>)', re.DOTALL|re.IGNORECASE),lambda match: '
' + match.group(2) + '
' + match.group(1) + '
'), (re.compile(r'()+', re.DOTALL|re.IGNORECASE),lambda match: '
'), - (re.compile(r'', re.DOTALL), lambda m: '') ] - extra_css = 'body, h3, p, #MERRYdate, h1, div, span{margin:0px; padding:0px} h3.entry-header{font-size: 0.8em} div.entry-body{font-size: 0.7em} #MERRYdate {font-size: 0.5em}' + extra_css = 'body, h3, p, div, span{margin:0px; padding:0px} h3.entry-header{font-size: 0.8em} div.entry-body{font-size: 0.7em}' def postprocess_html(self, soup, first): for tag in soup.findAll(lambda tag: tag.name.lower()=='img' and tag.has_key('src')): iurl = tag['src'] img = Image() img.open(iurl) - width, height = img.size - #print 'img is: ', iurl, 'width is: ', width, 'height is: ', height + #width, height = img.size + #print '***img is: ', iurl, '\n****width is: ', width, 'height is: ', height img.trim(0) - img.save(iurl) + #width, height = img.size + #print '***TRIMMED img width is: ', width, 'height is: ', height + left=0 + top=0 + border_color='#ffffff' width, height = img.size - #print 'img is: ', iurl, 'width is: ', width, 'height is: ', height + #print '***retrieved img width is: ', width, 'height is: ', height + height_correction = 1.17 + canvas = create_canvas(width, height*height_correction,border_color) + canvas.compose(img, left, top) + #img = canvas + #img.save(iurl) + canvas.save(iurl) + #width, height = canvas.size + #print '***NEW img width is: ', width, 'height is: ', height return soup feeds = ['http://feeds.feedburner.com/GeekAndPoke?format=xml']