diff --git a/recipes/adventure_zone_pl.recipe b/recipes/adventure_zone_pl.recipe
index bb311606ac..485a2e0c5b 100644
--- a/recipes/adventure_zone_pl.recipe
+++ b/recipes/adventure_zone_pl.recipe
@@ -3,7 +3,7 @@ import re
class Adventure_zone(BasicNewsRecipe):
title = u'Adventure Zone'
__author__ = 'fenuks'
- description = 'Adventure zone - adventure games from A to Z'
+ description = u'Adventure zone - adventure games from A to Z'
category = 'games'
language = 'pl'
no_stylesheets = True
@@ -11,7 +11,9 @@ class Adventure_zone(BasicNewsRecipe):
max_articles_per_feed = 100
index='http://www.adventure-zone.info/fusion/'
use_embedded_content=False
- preprocess_regexps = [(re.compile(r"| Komentarze | ", re.IGNORECASE), lambda m: '')]
+ preprocess_regexps = [(re.compile(r"Komentarze | ", re.IGNORECASE), lambda m: ''),
+ (re.compile(r'\'), lambda match: ''),
+ (re.compile(r'\'), lambda match: '')]
remove_tags_before= dict(name='td', attrs={'class':'main-bg'})
remove_tags= [dict(name='img', attrs={'alt':'Drukuj'})]
remove_tags_after= dict(id='comments')
@@ -52,6 +54,11 @@ class Adventure_zone(BasicNewsRecipe):
def preprocess_html(self, soup):
footer=soup.find(attrs={'class':'news-footer middle-border'})
+ r = soup.find(name='td', attrs={'class':'capmain'})
+ if r:
+ r.name='h1'
+ for item in soup.findAll(name=['tr', 'td']):
+ item.name='div'
if footer and len(footer('a'))>=2:
footer('a')[1].extract()
for item in soup.findAll(style=True):
diff --git a/recipes/benchmark_pl.recipe b/recipes/benchmark_pl.recipe
index 9544abdfcf..66d4f35e73 100644
--- a/recipes/benchmark_pl.recipe
+++ b/recipes/benchmark_pl.recipe
@@ -12,9 +12,9 @@ class BenchmarkPl(BasicNewsRecipe):
max_articles_per_feed = 100
no_stylesheets=True
preprocess_regexps = [(re.compile(ur'
', re.DOTALL|re.IGNORECASE), lambda match: ''), (re.compile(ur'Więcej o .*?', re.DOTALL|re.IGNORECASE), lambda match: '')]
- keep_only_tags=[dict(name='div', attrs={'class':['m_zwykly', 'gallery']})]
+ keep_only_tags=[dict(name='div', attrs={'class':['m_zwykly', 'gallery']}), dict(id='article')]
remove_tags_after=dict(name='div', attrs={'class':'body'})
- remove_tags=[dict(name='div', attrs={'class':['kategoria', 'socialize', 'thumb', 'panelOcenaObserwowane', 'categoryNextToSocializeGallery', 'breadcrumb']}), dict(name='table', attrs={'background':'http://www.benchmark.pl/uploads/backend_img/a/fotki_newsy/opinie_dnia/bg.png'}), dict(name='table', attrs={'width':'210', 'cellspacing':'1', 'cellpadding':'4', 'border':'0', 'align':'right'})]
+ remove_tags=[dict(name='div', attrs={'class':['kategoria', 'socialize', 'thumb', 'panelOcenaObserwowane', 'categoryNextToSocializeGallery', 'breadcrumb', 'footer', 'moreTopics']}), dict(name='table', attrs={'background':'http://www.benchmark.pl/uploads/backend_img/a/fotki_newsy/opinie_dnia/bg.png'}), dict(name='table', attrs={'width':'210', 'cellspacing':'1', 'cellpadding':'4', 'border':'0', 'align':'right'})]
INDEX= 'http://www.benchmark.pl'
feeds = [(u'Aktualności', u'http://www.benchmark.pl/rss/aktualnosci-pliki.xml'),
(u'Testy i recenzje', u'http://www.benchmark.pl/rss/testy-recenzje-minirecenzje.xml')]
diff --git a/recipes/biolog_pl.recipe b/recipes/biolog_pl.recipe
index b10bf0d925..c339447faf 100644
--- a/recipes/biolog_pl.recipe
+++ b/recipes/biolog_pl.recipe
@@ -13,6 +13,7 @@ class Biolog_pl(BasicNewsRecipe):
masthead_url= 'http://www.biolog.pl/naukowy,portal,biolog.png'
cover_url='http://www.biolog.pl/naukowy,portal,biolog.png'
no_stylesheets = True
+ ignore_duplicate_articles = {'title', 'url'}
#keeps_only_tags=[dict(id='main')]
remove_tags_before=dict(id='main')
remove_tags_after=dict(name='a', attrs={'name':'komentarze'})
diff --git a/recipes/cgm_pl.recipe b/recipes/cgm_pl.recipe
index 4ab4402c3a..8b0e4c084f 100644
--- a/recipes/cgm_pl.recipe
+++ b/recipes/cgm_pl.recipe
@@ -13,11 +13,11 @@ class CGM(BasicNewsRecipe):
use_embedded_content = False
remove_empty_feeds= True
max_articles_per_feed = 100
- no_stylesheers=True
+ no_stylesheets = True
extra_css = 'div {color:black;} strong {color:black;} span {color:black;} p {color:black;} h2 {color:black;}'
remove_tags_before=dict(id='mainContent')
remove_tags_after=dict(name='div', attrs={'class':'fbContainer'})
- remove_tags=[dict(name='div', attrs={'class':'fbContainer'}),
+ remove_tags=[dict(name='div', attrs={'class':['fbContainer', 'socials']}),
dict(name='p', attrs={'class':['tagCloud', 'galleryAuthor']}),
dict(id=['movieShare', 'container'])]
feeds = [(u'Informacje', u'http://www.cgm.pl/rss.xml'), (u'Polecamy', u'http://www.cgm.pl/rss,4,news.xml'),
diff --git a/recipes/dobreprogamy.recipe b/recipes/dobreprogamy.recipe
index 0614cf98ee..5254694d24 100644
--- a/recipes/dobreprogamy.recipe
+++ b/recipes/dobreprogamy.recipe
@@ -19,7 +19,7 @@ class Dobreprogramy_pl(BasicNewsRecipe):
max_articles_per_feed = 100
preprocess_regexps = [(re.compile(ur'