diff --git a/manual/news.rst b/manual/news.rst
index 1ea813f20a..a0c80defdf 100644
--- a/manual/news.rst
+++ b/manual/news.rst
@@ -217,7 +217,7 @@ A reasonably complex real life example that exposes more of the :term:`API` of `
description = self.tag_to_string(summary, use_alt=False)
feed = key if key is not None else 'Uncategorized'
- if not articles.has_key(feed):
+ if feed not in articles:
articles[feed] = []
if not 'podcasts' in url:
articles[feed].append(
@@ -225,7 +225,7 @@ A reasonably complex real life example that exposes more of the :term:`API` of `
description=description,
content=''))
ans = self.sort_index_by(ans, {'The Front Page':-1, 'Dining In, Dining Out':1, 'Obituaries':2})
- ans = [(key, articles[key]) for key in ans if articles.has_key(key)]
+ ans = [(key, articles[key]) for key in ans if key in articles]
return ans
def preprocess_html(self, soup):
diff --git a/recipes/20minutos.recipe b/recipes/20minutos.recipe
index 725278c045..e40fc174fa 100644
--- a/recipes/20minutos.recipe
+++ b/recipes/20minutos.recipe
@@ -60,7 +60,6 @@ class t20Minutos(BasicNewsRecipe):
else:
str = self.tag_to_string(item)
item.replaceWith(str)
- for item in soup.findAll('img'):
- if not item.has_key('alt'): # noqa
- item['alt'] = 'image'
+ for item in soup.findAll('img', alt=False):
+ item['alt'] = 'image'
return soup
diff --git a/recipes/ajc.recipe b/recipes/ajc.recipe
index f27a2fc8e1..0b884373b7 100644
--- a/recipes/ajc.recipe
+++ b/recipes/ajc.recipe
@@ -112,7 +112,7 @@ class AdvancedUserRecipe1282101454(BasicNewsRecipe):
for div in soup.findAll('div', attrs={'class': re.compile(self.author_reg_exp, re.IGNORECASE)}):
div.extract()
for auth in div.findAll('a'):
- if (auth.has_key('class') and auth['class'] == 'cm-source-image'): # noqa
+ if auth.get('class') == 'cm-source-image':
continue
names = names + comma + auth.contents[0]
comma = ', '
diff --git a/recipes/animal_politico.recipe b/recipes/animal_politico.recipe
index adbd6d7b3a..61674548c6 100644
--- a/recipes/animal_politico.recipe
+++ b/recipes/animal_politico.recipe
@@ -25,7 +25,7 @@ class AdvancedUserRecipe1290663986(BasicNewsRecipe):
def generic_parse(self, soup):
articles = []
# soup.findAll('li', 'hentry'):
- for entry in soup.findAll(lambda tag: tag.name == 'li' and tag.has_key('class') and tag['class'].find('hentry') != -1): # noqa
+ for entry in soup.findAll('li', attrs={'class': lambda x: x and 'hentry' in x}):
article_url = entry.a['href'] + '?print=yes'
article_title = entry.find('h3', 'entry-title')
article_title = self.tag_to_string(article_title)
@@ -48,7 +48,7 @@ class AdvancedUserRecipe1290663986(BasicNewsRecipe):
def plumaje_parse(self, soup):
articles = []
- blogs_soup = soup.find(lambda tag: tag.name == 'ul' and tag.has_key('class') and tag['class'].find('bloglist-fecha') != -1) # noqa
+ blogs_soup = soup.find('ul', attrs={'class': lambda x: x and 'bloglist-fecha' in x})
for entry in blogs_soup.findAll('li'):
article_title = entry.p
article_url = article_title.a['href'] + '?print=yes'
@@ -69,7 +69,7 @@ class AdvancedUserRecipe1290663986(BasicNewsRecipe):
def boca_parse(self, soup):
articles = []
# soup.findAll('li', 'hentry'):
- for entry in soup.findAll(lambda tag: tag.name == 'div' and tag.has_key('class') and tag['class'].find('hentry') != -1): # noqa
+ for entry in soup.findAll('div', attrs={'class': lambda x: x and 'hentry' in x}):
article_title = entry.find('h2', 'entry-title')
article_url = article_title.a['href'] + '?print=yes'
article_title = self.tag_to_string(article_title)
diff --git a/recipes/ba_herald.recipe b/recipes/ba_herald.recipe
index f8e2272d80..91cac54aa8 100644
--- a/recipes/ba_herald.recipe
+++ b/recipes/ba_herald.recipe
@@ -62,8 +62,8 @@ class BuenosAiresHerald(BasicNewsRecipe):
soup = self.index_to_soup(feedurl)
for item in soup.findAll('div', attrs={'class': 'nota_texto_seccion'}):
description = self.tag_to_string(item.h2)
- atag = item.h2.find('a')
- if atag and atag.has_key('href'): # noqa
+ atag = item.h2.find('a', href=True)
+ if atag is not None:
url = self.INDEX + atag['href']
title = description
date = strftime(self.timefmt)
diff --git a/recipes/benchmark_pl.recipe b/recipes/benchmark_pl.recipe
index 6433742978..83b1b465c9 100644
--- a/recipes/benchmark_pl.recipe
+++ b/recipes/benchmark_pl.recipe
@@ -50,8 +50,8 @@ class BenchmarkPl(BasicNewsRecipe):
def preprocess_html(self, soup):
self.append_page(soup, soup.body)
- for a in soup('a'):
- if a.has_key('href') and not a['href'].startswith('http'): # noqa
+ for a in soup.findAll('a', href=True):
+ if not a['href'].startswith('http'):
a['href'] = self.INDEX + a['href']
for r in soup.findAll(attrs={'class': ['comments', 'body']}):
r.extract()
diff --git a/recipes/bighollywood.recipe b/recipes/bighollywood.recipe
index 43d30795b5..0f0c06760d 100644
--- a/recipes/bighollywood.recipe
+++ b/recipes/bighollywood.recipe
@@ -55,7 +55,6 @@ class BigHollywood(BasicNewsRecipe):
else:
str = self.tag_to_string(item)
item.replaceWith(str)
- for item in soup.findAll('img'):
- if not item.has_key('alt'): # noqa
- item['alt'] = 'image'
+ for item in soup.findAll('img', alt=False):
+ item['alt'] = 'image'
return soup
diff --git a/recipes/business_insider.recipe b/recipes/business_insider.recipe
index 0720600496..d04913ea17 100644
--- a/recipes/business_insider.recipe
+++ b/recipes/business_insider.recipe
@@ -59,7 +59,6 @@ class Business_insider(BasicNewsRecipe):
if item.string is not None:
tstr = item.string
item.replaceWith(tstr)
- for item in soup.findAll('img'):
- if not item.has_key('alt'): # noqa
- item['alt'] = 'image'
+ for item in soup.findAll('img', alt=False):
+ item['alt'] = 'image'
return soup
diff --git a/recipes/calgary_herald.recipe b/recipes/calgary_herald.recipe
index 02bd202987..d3c4e9d554 100644
--- a/recipes/calgary_herald.recipe
+++ b/recipes/calgary_herald.recipe
@@ -286,7 +286,7 @@ class CanWestPaper(BasicNewsRecipe):
else:
description = self.tag_to_string(dtag, False)
print("DESCRIPTION: " + description)
- if not articles.has_key(key): # noqa
+ if key not in articles:
articles[key] = []
articles[key].append(dict(
title=title, url=url, date='', description=description, author='', content=''))
@@ -310,5 +310,5 @@ class CanWestPaper(BasicNewsRecipe):
for (k, url) in self.postmedia_index_pages:
parse_web_index(k, url)
- ans = [(key, articles[key]) for key in ans if articles.has_key(key)] # noqa
+ ans = [(key, articles[key]) for key in ans if key in articles]
return ans
diff --git a/recipes/cd_action.recipe b/recipes/cd_action.recipe
index fd1e7862c2..4d132a8830 100644
--- a/recipes/cd_action.recipe
+++ b/recipes/cd_action.recipe
@@ -22,7 +22,7 @@ class CD_Action(BasicNewsRecipe):
return getattr(self, 'cover_url', self.cover_url)
def preprocess_html(self, soup):
- for a in soup('a'):
- if a.has_key('href') and 'http://' not in a['href'] and 'https://' not in a['href']: # noqa
+ for a in soup.findAll('a', href=True):
+ if 'http://' not in a['href'] and 'https://' not in a['href']:
a['href'] = self.index + a['href']
return soup
diff --git a/recipes/chr_mon.recipe b/recipes/chr_mon.recipe
index d2c4519e9f..3ffa429b9a 100644
--- a/recipes/chr_mon.recipe
+++ b/recipes/chr_mon.recipe
@@ -101,10 +101,7 @@ class CSMonitor(BasicNewsRecipe):
else:
str = self.tag_to_string(item)
item.replaceWith(str)
- for item in soup.findAll('img'):
+ for item in soup.findAll('img', src=True):
if 'scorecardresearch' in item['src']:
item.extract()
- else:
- if not item.has_key('alt'): # noqa
- item['alt'] = 'image'
return soup
diff --git a/recipes/cinebel_be.recipe b/recipes/cinebel_be.recipe
index 74d5ac1a47..56f8b4d8f0 100644
--- a/recipes/cinebel_be.recipe
+++ b/recipes/cinebel_be.recipe
@@ -36,10 +36,9 @@ class Cinebel(BasicNewsRecipe):
]
def preprocess_html(self, soup):
- for alink in soup.findAll('a'):
- if alink.has_key('href'): # noqa
- tstr = "Site officiel: " + alink['href']
- alink.replaceWith(tstr)
+ for alink in soup.findAll('a', href=True):
+ tstr = "Site officiel: " + alink['href']
+ alink.replaceWith(tstr)
return soup
def get_cover_url(self):
diff --git a/recipes/cio_magazine.recipe b/recipes/cio_magazine.recipe
index 5e8c9b39b2..e2c04f7e0c 100644
--- a/recipes/cio_magazine.recipe
+++ b/recipes/cio_magazine.recipe
@@ -131,12 +131,12 @@ class CIO_Magazine(BasicNewsRecipe):
# Esto esta copiado del NY times
feed = key if key is not None else 'Uncategorized'
- if not articles.has_key(feed): # noqa
+ if feed not in articles:
articles[feed] = []
if 'podcasts' not in url:
articles[feed].append(
dict(title=title, url=url, date=pubdate,
description=description,
content=''))
- feeds = [(k, articles[k]) for k in feeds if articles.has_key(k)] # noqa
+ feeds = [(k, articles[k]) for k in feeds if k in articles]
return feeds
diff --git a/recipes/cnd.recipe b/recipes/cnd.recipe
index 0f8e70ca35..320f355e01 100644
--- a/recipes/cnd.recipe
+++ b/recipes/cnd.recipe
@@ -54,7 +54,7 @@ class TheCND(BasicNewsRecipe):
if re.search('cm', date):
continue
if (date is not None) and len(date) > 2:
- if not articles.has_key(date): # noqa
+ if date not in articles:
articles[date] = []
articles[date].append(
{'title': title, 'url': url, 'description': '', 'date': ''})
diff --git a/recipes/cnd_weekly.recipe b/recipes/cnd_weekly.recipe
index ae748c2e76..7566ec9548 100644
--- a/recipes/cnd_weekly.recipe
+++ b/recipes/cnd_weekly.recipe
@@ -54,7 +54,7 @@ class TheCND(BasicNewsRecipe):
continue
self.log('\tFound article: ', title, 'at', url, '@', date)
if (date is not None) and len(date) > 2:
- if not articles.has_key(date): # noqa
+ if date not in articles:
articles[date] = []
articles[date].append(
{'title': title, 'url': url, 'description': '', 'date': ''})
diff --git a/recipes/cosmopolitan.recipe b/recipes/cosmopolitan.recipe
index 9b84088764..ab31ab88bb 100644
--- a/recipes/cosmopolitan.recipe
+++ b/recipes/cosmopolitan.recipe
@@ -53,8 +53,8 @@ class General(BasicNewsRecipe):
for item in soup.body.findAll(name=['table', 'td', 'tr', 'th', 'caption', 'thead', 'tfoot', 'tbody', 'colgroup', 'col']):
item.name = 'div'
for attrib in attribs:
- if item.has_key(attrib): # noqa
- del item[attrib]
+ item[attrib] = ''
+ del item[attrib]
return soup
def get_cover_url(self):
diff --git a/recipes/cubadebate.recipe b/recipes/cubadebate.recipe
index 2ab9c79c8b..ea87b6688c 100644
--- a/recipes/cubadebate.recipe
+++ b/recipes/cubadebate.recipe
@@ -46,7 +46,6 @@ class CubaDebate(BasicNewsRecipe):
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
- for item in soup.findAll('img'):
- if not item.has_key('alt'): # noqa
- item['alt'] = 'image'
+ for item in soup.findAll('img', alt=False):
+ item['alt'] = 'image'
return soup
diff --git a/recipes/dailytportal.recipe b/recipes/dailytportal.recipe
index 37b749f8fa..00deb4c1db 100644
--- a/recipes/dailytportal.recipe
+++ b/recipes/dailytportal.recipe
@@ -57,7 +57,6 @@ class Pagina12(BasicNewsRecipe):
else:
str = self.tag_to_string(item)
item.replaceWith(str)
- for item in soup.findAll('img'):
- if not item.has_key('alt'): # noqa
- item['alt'] = 'image'
+ for item in soup.findAll('img', alt=False):
+ item['alt'] = 'image'
return soup
diff --git a/recipes/degentenaar.recipe b/recipes/degentenaar.recipe
index 6b6c52bef0..2c08ee7859 100644
--- a/recipes/degentenaar.recipe
+++ b/recipes/degentenaar.recipe
@@ -64,7 +64,7 @@ class DeGentenaarOnline(BasicNewsRecipe):
del item['style']
for item in soup.findAll('span'):
item.name = 'div'
- if item.has_key('id') and item['id'] == 'lblArticleTitle': # noqa
+ if item.get('id') == 'lblArticleTitle':
item.name = 'h3'
soup.html['lang'] = self.lang
diff --git a/recipes/deutsche_welle_bs.recipe b/recipes/deutsche_welle_bs.recipe
index 72a3761219..0b852c94c8 100644
--- a/recipes/deutsche_welle_bs.recipe
+++ b/recipes/deutsche_welle_bs.recipe
@@ -65,8 +65,8 @@ class DeutscheWelle_bs(BasicNewsRecipe):
if limg:
item.name = 'div'
del item['href']
- if item.has_key('target'): # noqa
- del item['target']
+ item['target'] = ''
+ del item['target']
else:
str = self.tag_to_string(item)
item.replaceWith(str)
diff --git a/recipes/deutsche_welle_hr.recipe b/recipes/deutsche_welle_hr.recipe
index 1c1427a8e4..906e4a1d39 100644
--- a/recipes/deutsche_welle_hr.recipe
+++ b/recipes/deutsche_welle_hr.recipe
@@ -63,8 +63,8 @@ class DeutscheWelle_hr(BasicNewsRecipe):
if limg:
item.name = 'div'
del item['href']
- if item.has_key('target'): # noqa
- del item['target']
+ item['target'] = ''
+ del item['target']
else:
str = self.tag_to_string(item)
item.replaceWith(str)
diff --git a/recipes/deutsche_welle_pt.recipe b/recipes/deutsche_welle_pt.recipe
index 1fca72963b..4b9a9ea9dc 100644
--- a/recipes/deutsche_welle_pt.recipe
+++ b/recipes/deutsche_welle_pt.recipe
@@ -54,8 +54,8 @@ class DeutscheWelle_pt(BasicNewsRecipe):
if limg:
item.name = 'div'
del item['href']
- if item.has_key('target'): # noqa
- del item['target']
+ item['target'] = ''
+ del item['target']
else:
str = self.tag_to_string(item)
item.replaceWith(str)
diff --git a/recipes/deutsche_welle_sr.recipe b/recipes/deutsche_welle_sr.recipe
index 3ea1a2a10f..b9c67e4976 100644
--- a/recipes/deutsche_welle_sr.recipe
+++ b/recipes/deutsche_welle_sr.recipe
@@ -68,8 +68,8 @@ class DeutscheWelle_sr(BasicNewsRecipe):
if limg:
item.name = 'div'
del item['href']
- if item.has_key('target'): # noqa
- del item['target']
+ item['target'] = ''
+ del item['target']
else:
str = self.tag_to_string(item)
item.replaceWith(str)
diff --git a/recipes/dnevnik_cro.recipe b/recipes/dnevnik_cro.recipe
index 9060a9185c..02f4a3bcd8 100644
--- a/recipes/dnevnik_cro.recipe
+++ b/recipes/dnevnik_cro.recipe
@@ -55,8 +55,8 @@ class DnevnikCro(BasicNewsRecipe):
for item in soup.body.findAll(name=['table', 'td', 'tr', 'th', 'caption', 'thead', 'tfoot', 'tbody', 'colgroup', 'col']):
item.name = 'div'
for attrib in attribs:
- if item.has_key(attrib): # noqa
- del item[attrib]
+ item[attrib] = ''
+ del item[attrib]
mlang = Tag(soup, 'meta', [
("http-equiv", "Content-Language"), ("content", self.lang)])
diff --git a/recipes/dobanevinosti.recipe b/recipes/dobanevinosti.recipe
index 242edabf46..90cbc5866c 100644
--- a/recipes/dobanevinosti.recipe
+++ b/recipes/dobanevinosti.recipe
@@ -37,7 +37,6 @@ class DobaNevinosti(BasicNewsRecipe):
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
- for item in soup.findAll('img'):
- if not item.has_key('alt'): # noqa
- item['alt'] = 'image'
+ for item in soup.findAll('img', alt=False):
+ item['alt'] = 'image'
return soup
diff --git a/recipes/dobreprogamy.recipe b/recipes/dobreprogamy.recipe
index 878ceb57c3..c97d9c0e8f 100644
--- a/recipes/dobreprogamy.recipe
+++ b/recipes/dobreprogamy.recipe
@@ -28,8 +28,8 @@ class Dobreprogramy_pl(BasicNewsRecipe):
('Blogi', 'http://feeds.feedburner.com/dobreprogramy/BlogCzytelnikow')]
def preprocess_html(self, soup):
- for a in soup('a'):
- if a.has_key('href') and 'http://' not in a['href'] and 'https://' not in a['href']: # noqa
+ for a in soup('a', href=True):
+ if 'http://' not in a['href'] and 'https://' not in a['href']:
a['href'] = self.index + a['href']
for r in soup.findAll('iframe'):
r.parent.extract()
diff --git a/recipes/dzieje_pl.recipe b/recipes/dzieje_pl.recipe
index 7a2e9284a6..57d243bd74 100644
--- a/recipes/dzieje_pl.recipe
+++ b/recipes/dzieje_pl.recipe
@@ -81,8 +81,8 @@ class Dzieje(BasicNewsRecipe):
return feeds
def preprocess_html(self, soup):
- for a in soup('a'):
- if a.has_key('href') and not a['href'].startswith('http'): # noqa
+ for a in soup('a', href=True):
+ if not a['href'].startswith('http'):
a['href'] = self.index + a['href']
self.append_page(soup, soup.body)
return soup
diff --git a/recipes/edmonton_journal.recipe b/recipes/edmonton_journal.recipe
index e8e6ad5a87..9e7ae425bf 100644
--- a/recipes/edmonton_journal.recipe
+++ b/recipes/edmonton_journal.recipe
@@ -286,7 +286,7 @@ class CanWestPaper(BasicNewsRecipe):
else:
description = self.tag_to_string(dtag, False)
print("DESCRIPTION: " + description)
- if not articles.has_key(key): # noqa
+ if key not in articles:
articles[key] = []
articles[key].append(dict(
title=title, url=url, date='', description=description, author='', content=''))
@@ -310,5 +310,5 @@ class CanWestPaper(BasicNewsRecipe):
for (k, url) in self.postmedia_index_pages:
parse_web_index(k, url)
- ans = [(key, articles[key]) for key in ans if articles.has_key(key)] # noqa
+ ans = [(key, articles[key]) for key in ans if key in articles]
return ans
diff --git a/recipes/el_diplo.recipe b/recipes/el_diplo.recipe
index 119e010eb9..d9fbe755a8 100644
--- a/recipes/el_diplo.recipe
+++ b/recipes/el_diplo.recipe
@@ -113,11 +113,11 @@ class ElDiplo_Recipe(BasicNewsRecipe):
if aut:
auth = self.tag_to_string(aut, use_alt=False).strip()
- if not articles.has_key(section): # noqa
+ if section not in articles: # noqa
articles[section] = []
articles[section].append(dict(
title=title, author=auth, url=url, date=None, description=description, content=''))
- ans = [(s, articles[s]) for s in ans if articles.has_key(s)] # noqa
+ ans = [(s, articles[s]) for s in ans if s in articles]
return ans
diff --git a/recipes/elclubdelebook.recipe b/recipes/elclubdelebook.recipe
index 47a7043b3a..f186140210 100644
--- a/recipes/elclubdelebook.recipe
+++ b/recipes/elclubdelebook.recipe
@@ -53,7 +53,6 @@ class ElClubDelEbook(BasicNewsRecipe):
else:
str = self.tag_to_string(item)
item.replaceWith(str)
- for item in soup.findAll('img'):
- if not item.has_key('alt'): # noqa
- item['alt'] = 'image'
+ for item in soup.findAll('img', alt=False):
+ item['alt'] = 'image'
return soup
diff --git a/recipes/elpais_semanal.recipe b/recipes/elpais_semanal.recipe
index 1a607b4858..69a0a0fb42 100644
--- a/recipes/elpais_semanal.recipe
+++ b/recipes/elpais_semanal.recipe
@@ -35,17 +35,16 @@ class ElPaisSemanal(BasicNewsRecipe):
def parse_index(self):
articles = []
soup = self.index_to_soup(self.index)
- for item in soup.findAll('a', attrs={'class': ['g19i003', 'g17r003', 'g17i003']}):
+ for item in soup.findAll('a', attrs={'class': ['g19i003', 'g17r003', 'g17i003']}, href=True):
description = ''
title_prefix = ''
feed_link = item
- if item.has_key('href'): # noqa
- url = 'http://www.elpais.com' + item['href'].rpartition('/')[0]
- title = title_prefix + self.tag_to_string(feed_link)
- date = strftime(self.timefmt)
- articles.append({
- 'title': title, 'date': date, 'url': url, 'description': description
- })
+ url = 'http://www.elpais.com' + item['href'].rpartition('/')[0]
+ title = title_prefix + self.tag_to_string(feed_link)
+ date = strftime(self.timefmt)
+ articles.append({
+ 'title': title, 'date': date, 'url': url, 'description': description
+ })
return [(soup.head.title.string, articles)]
def print_version(self, url):
diff --git a/recipes/eluniversalimpresa.recipe b/recipes/eluniversalimpresa.recipe
index e0cf058494..331da13a86 100644
--- a/recipes/eluniversalimpresa.recipe
+++ b/recipes/eluniversalimpresa.recipe
@@ -31,7 +31,7 @@ class ElUniversalImpresaRecipe(BasicNewsRecipe):
table = soup.find('table', attrs={'width': '500'})
articles = []
- for td in table.findAll(lambda tag: tag.name == 'td' and tag.has_key('class') and tag['class'] == 'arnegro12'): # noqa
+ for td in table.findAll('td', attrs={'class': 'arnegro12'}):
a = td.a
a.extract()
title = self.tag_to_string(a)
@@ -79,8 +79,8 @@ class ElUniversalImpresaRecipe(BasicNewsRecipe):
tag = soup.find('font', attrs={'color': '#0F046A'})
if tag:
for attr in ['color', 'face', 'helvetica,', 'sans-serif', 'size']:
- if tag.has_key(attr): # noqa
- del tag[attr]
+ tag[attr] = ''
+ del tag[attr]
tag.name = 'h1'
return soup
diff --git a/recipes/espn.recipe b/recipes/espn.recipe
index 8c4ce332fa..e29a88b9cb 100644
--- a/recipes/espn.recipe
+++ b/recipes/espn.recipe
@@ -62,8 +62,8 @@ class ESPN(BasicNewsRecipe):
]
def preprocess_html(self, soup):
- for div in soup.findAll('div'):
- if div.has_key('style') and 'px' in div['style']: # noqa
+ for div in soup.findAll('div', style=True):
+ if 'px' in div['style']:
div['style'] = ''
return soup
diff --git a/recipes/estadao.recipe b/recipes/estadao.recipe
index cbb06247fe..b2f8215528 100644
--- a/recipes/estadao.recipe
+++ b/recipes/estadao.recipe
@@ -88,7 +88,7 @@ class Estadao(BasicNewsRecipe):
def postprocess_html(self, soup, first):
# process all the images. assumes that the new html has the correct
# path
- for tag in soup.findAll(lambda tag: tag.name.lower() == 'img' and tag.has_key('src')): # noqa
+ for tag in soup.findAll('img', src=True):
iurl = tag['src']
img = Image()
img.open(iurl)
diff --git a/recipes/financialsense.recipe b/recipes/financialsense.recipe
index 9fcfa17413..fdf45c45b8 100644
--- a/recipes/financialsense.recipe
+++ b/recipes/financialsense.recipe
@@ -57,7 +57,6 @@ class FinancialSense(BasicNewsRecipe):
else:
str = self.tag_to_string(item)
item.replaceWith(str)
- for item in soup.findAll('img'):
- if not item.has_key('alt'): # noqa
- item['alt'] = 'image'
+ for item in soup.findAll('img', alt=False):
+ item['alt'] = 'image'
return soup
diff --git a/recipes/freeway.recipe b/recipes/freeway.recipe
index 3662fac972..9e91929371 100644
--- a/recipes/freeway.recipe
+++ b/recipes/freeway.recipe
@@ -84,8 +84,8 @@ class General(BasicNewsRecipe):
for item in soup.body.findAll(name=['table', 'td', 'tr', 'th', 'caption', 'thead', 'tfoot', 'tbody', 'colgroup', 'col']):
item.name = 'div'
for attrib in attribs:
- if item.has_key(attrib): # noqa
- del item[attrib]
+ item[attrib] = ''
+ del item[attrib]
return soup
def get_cover_url(self):
diff --git a/recipes/gameplay_pl.recipe b/recipes/gameplay_pl.recipe
index 10f71c1fad..351cce20e8 100644
--- a/recipes/gameplay_pl.recipe
+++ b/recipes/gameplay_pl.recipe
@@ -27,7 +27,7 @@ class Gameplay_pl(BasicNewsRecipe):
return url
def preprocess_html(self, soup):
- for a in soup('a'):
- if a.has_key('href') and '../' in a['href']: # noqa
+ for a in soup('a', href=True):
+ if '../' in a['href']:
a['href'] = self.index + a['href'][2:]
return soup
diff --git a/recipes/geek_poke.recipe b/recipes/geek_poke.recipe
index e4e1092940..22193d8bbf 100644
--- a/recipes/geek_poke.recipe
+++ b/recipes/geek_poke.recipe
@@ -56,7 +56,7 @@ class AdvancedUserRecipe1307556816(BasicNewsRecipe):
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')): # noqa
+ for tag in soup.findAll('img', src=True):
iurl = tag['src']
img = Image()
img.open(iurl)
diff --git a/recipes/gildia_pl.recipe b/recipes/gildia_pl.recipe
index 0cc92013ca..4cdf03ad28 100644
--- a/recipes/gildia_pl.recipe
+++ b/recipes/gildia_pl.recipe
@@ -58,8 +58,8 @@ class Gildia(BasicNewsRecipe):
def preprocess_html(self, soup):
title = soup.title.renderContents().lower()
- for a in soup('a'):
- if a.has_key('href') and not a['href'].startswith('http'): # noqa
+ for a in soup('a', href=True):
+ if not a['href'].startswith('http'):
if '/gry/' in a['href']:
a['href'] = 'http://www.gry.gildia.pl' + a['href']
elif u'książk' in title or u'komiks' in title:
diff --git a/recipes/gram_pl.recipe b/recipes/gram_pl.recipe
index b66ac1e241..77267d93ed 100644
--- a/recipes/gram_pl.recipe
+++ b/recipes/gram_pl.recipe
@@ -43,8 +43,8 @@ class Gram_pl(BasicNewsRecipe):
tag.p.img.extract()
tag.p.insert(len(tag.p.contents) - 2,
BeautifulSoup('Ocena: {0}
'.format(rate)).h2)
- for a in soup('a'):
- if a.has_key('href') and 'http://' not in a['href'] and 'https://' not in a['href']: # noqa
+ for a in soup.findAll('a', href=True):
+ if 'http://' not in a['href'] and 'https://' not in a['href']: # noqa
a['href'] = self.index + a['href']
tag = soup.find(name='span', attrs={'class': 'platforma'})
if tag:
diff --git a/recipes/in4_pl.recipe b/recipes/in4_pl.recipe
index ab4bffd50c..46c9e930c0 100644
--- a/recipes/in4_pl.recipe
+++ b/recipes/in4_pl.recipe
@@ -47,7 +47,7 @@ class in4(BasicNewsRecipe):
def preprocess_html(self, soup):
self.append_page(soup, soup.body)
- for a in soup('a'):
- if a.has_key('href') and 'http://' not in a['href'] and 'https://' not in a['href']: # noqa
+ for a in soup.findAll('a', href=True):
+ if 'http://' not in a['href'] and 'https://' not in a['href']:
a['href'] = self.index + a['href']
return soup
diff --git a/recipes/infra_pl.recipe b/recipes/infra_pl.recipe
index b036f04eb9..e705539191 100644
--- a/recipes/infra_pl.recipe
+++ b/recipes/infra_pl.recipe
@@ -21,7 +21,7 @@ class INFRA(BasicNewsRecipe):
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
- for a in soup('a'):
- if a.has_key('href') and 'http://' not in a['href'] and 'https://' not in a['href']: # noqa
+ for a in soup.findAll('a', href=True):
+ if 'http://' not in a['href'] and 'https://' not in a['href']:
a['href'] = self.index + a['href']
return soup
diff --git a/recipes/jutarnji.recipe b/recipes/jutarnji.recipe
index ff3867d6f7..9397cb3067 100644
--- a/recipes/jutarnji.recipe
+++ b/recipes/jutarnji.recipe
@@ -65,8 +65,8 @@ class Jutarnji(BasicNewsRecipe):
for item in soup.body.findAll(name=['table', 'td', 'tr', 'th', 'caption', 'thead', 'tfoot', 'tbody', 'colgroup', 'col']):
item.name = 'div'
for attrib in attribs:
- if item.has_key(attrib): # noqa
- del item[attrib]
+ item[attrib] = ''
+ del item[attrib]
mlang = Tag(soup, 'meta', [
("http-equiv", "Content-Language"), ("content", self.lang)])
diff --git a/recipes/klip_me.recipe b/recipes/klip_me.recipe
index 20d73ac23c..2d504ce3ab 100644
--- a/recipes/klip_me.recipe
+++ b/recipes/klip_me.recipe
@@ -47,7 +47,7 @@ class AdvancedUserRecipe1299694372(BasicNewsRecipe):
soup = self.index_to_soup(feedurl)
for item in soup.findAll('table', attrs={'class': ['item', 'item new']}):
atag = item.a
- if atag and atag.has_key('href'): # noqa
+ if atag and atag.get('href') is not None:
url = atag['href']
articles.append({
'url': url
diff --git a/recipes/lemonde_dip.recipe b/recipes/lemonde_dip.recipe
index d03c8b6ba8..716daecc79 100644
--- a/recipes/lemonde_dip.recipe
+++ b/recipes/lemonde_dip.recipe
@@ -61,17 +61,18 @@ class LeMondeDiplomatiqueEn(BasicNewsRecipe):
cnt = soup.find('div', attrs={'class': 'som_num'})
for item in cnt.findAll('li'):
description = ''
- feed_link = item.find('a')
+ feed_link = item.find('a', href=True)
+ if feed_link is None:
+ continue
desc = item.find('div', attrs={'class': 'chapo'})
if desc:
description = desc.string
- if feed_link and feed_link.has_key('href'): # noqa
- url = self.PREFIX + feed_link['href'].partition('/../')[2]
- title = self.tag_to_string(feed_link)
- date = strftime(self.timefmt)
- articles.append({
- 'title': title, 'date': date, 'url': url, 'description': description
- })
+ url = self.PREFIX + feed_link['href'].partition('/../')[2]
+ title = self.tag_to_string(feed_link)
+ date = strftime(self.timefmt)
+ articles.append({
+ 'title': title, 'date': date, 'url': url, 'description': description
+ })
return [(self.title, articles)]
def get_cover_url(self):
diff --git a/recipes/lenta_ru.recipe b/recipes/lenta_ru.recipe
index 1e633b2c17..583954ea75 100644
--- a/recipes/lenta_ru.recipe
+++ b/recipes/lenta_ru.recipe
@@ -60,14 +60,9 @@ class LentaRURecipe(BasicNewsRecipe):
if not feedData:
raise NotImplementedError
self.log("parse_index: Feed loaded successfully.")
- if feedData.feed.has_key('title'): # noqa
- self.title = feedData.feed.title
- self.log("parse_index: Title updated to: ", self.title)
- if feedData.feed.has_key('image'): # noqa
- self.log("HAS IMAGE!!!!")
def get_virtual_feed_articles(feed):
- if feeds.has_key(feed): # noqa
+ if feed in feeds:
return feeds[feed][1]
self.log("Adding new feed: ", feed)
articles = []
@@ -84,7 +79,7 @@ class LentaRURecipe(BasicNewsRecipe):
continue
article = {'title': title, 'url': link, 'description': item.get(
'description', ''), 'date': item.get('date', ''), 'content': ''}
- if not item.has_key('tags'): # noqa
+ if not item.get('tags'):
get_virtual_feed_articles('_default').append(article)
continue
for tag in item.tags:
@@ -101,7 +96,7 @@ class LentaRURecipe(BasicNewsRecipe):
# Select sorted feeds first of all
result = []
for feedName in self.sortOrder:
- if (not feeds.has_key(feedName)): # noqa
+ if (not feeds.get(feedName)):
continue
result.append(feeds[feedName])
del feeds[feedName]
diff --git a/recipes/lrb_payed.recipe b/recipes/lrb_payed.recipe
index c99a3b8216..8d6e0055a2 100644
--- a/recipes/lrb_payed.recipe
+++ b/recipes/lrb_payed.recipe
@@ -45,7 +45,7 @@ class LondonReviewOfBooksPayed(BasicNewsRecipe):
soup = self.index_to_soup(self.INDEX)
cover_item = soup.find('p', attrs={'class': 'cover'})
dates = str(soup.find('span', attrs={'class': 'coverdate'}))
- newdates = re.sub('\<.*\>', '', re.split('
', dates)[1])
+ newdates = re.sub(r'\<.*\>', '', re.split('
', dates)[1])
self.timefmt = ' [%s]' % newdates
lrbtitle = self.title
if cover_item:
@@ -58,13 +58,13 @@ class LondonReviewOfBooksPayed(BasicNewsRecipe):
description = u''
title_prefix = u''
feed_link = item
- if feed_link.has_key('href'): # noqa
+ if feed_link.get('href'):
url = self.INDEX + feed_link['href']
title_link = re.split('
', str(feed_link))
if len(title_link) > 1:
title = title_prefix + \
re.sub(
- '\<.*\>', '', title_link[0]) + ' - ' + re.sub('\<.*\>', '', title_link[1])
+ r'\<.*\>', '', title_link[0]) + ' - ' + re.sub(r'\<.*\>', '', title_link[1])
else:
title = title_prefix + self.tag_to_string(feed_link)
desc = item.findNext('li')
diff --git a/recipes/metro_news_nl.recipe b/recipes/metro_news_nl.recipe
index 205f71c596..fa5c4fdd7a 100644
--- a/recipes/metro_news_nl.recipe
+++ b/recipes/metro_news_nl.recipe
@@ -133,7 +133,7 @@ class AdvancedUserRecipe1306097511(BasicNewsRecipe):
class MerryPreProcess():
def optimizePicture(self, soup):
- for tag in soup.findAll(lambda tag: tag.name.lower() == 'img' and tag.has_key('src')): # noqa
+ for tag in soup.findAll('img', src=True):
try:
iurl = tag['src']
img = Image()
diff --git a/recipes/moneycontrol.recipe b/recipes/moneycontrol.recipe
index 7d9d440c3e..8cc0cfdeac 100644
--- a/recipes/moneycontrol.recipe
+++ b/recipes/moneycontrol.recipe
@@ -42,11 +42,10 @@ class MoneyControlRecipe(BasicNewsRecipe):
h1.append(self.tag_to_string(headline))
freshSoup.body.append(h1)
- for p in soup.findAll('p'):
- if p.has_key('class'):
- if p['class'] == 'MsoNormal':
- # We have some weird pagebreak marker here; it will not find all of them however
- continue
+ for p in soup.findAll('p', attrs={'class': true}):
+ if p['class'] == 'MsoNormal':
+ # We have some weird pagebreak marker here; it will not find all of them however
+ continue
para = Tag(freshSoup, 'p')
# Convert to string; this will loose all formatting but also all illegal markup
diff --git a/recipes/montreal_gazette.recipe b/recipes/montreal_gazette.recipe
index a0ab8aa8b0..d1366c4c07 100644
--- a/recipes/montreal_gazette.recipe
+++ b/recipes/montreal_gazette.recipe
@@ -286,7 +286,7 @@ class CanWestPaper(BasicNewsRecipe):
else:
description = self.tag_to_string(dtag, False)
print("DESCRIPTION: " + description)
- if not articles.has_key(key): # noqa
+ if key not in articles:
articles[key] = []
articles[key].append(dict(
title=title, url=url, date='', description=description, author='', content=''))
@@ -310,5 +310,5 @@ class CanWestPaper(BasicNewsRecipe):
for (k, url) in self.postmedia_index_pages:
parse_web_index(k, url)
- ans = [(key, articles[key]) for key in ans if articles.has_key(key)] # noqa
+ ans = [(key, articles[key]) for key in ans if key in articles]
return ans
diff --git a/recipes/naszdziennik.recipe b/recipes/naszdziennik.recipe
index 50b5aaec4f..b3427b94e1 100644
--- a/recipes/naszdziennik.recipe
+++ b/recipes/naszdziennik.recipe
@@ -38,7 +38,7 @@ class naszdziennik(BasicNewsRecipe):
section = self.tag_to_string(section)
# sprawdzamy czy w słowniku artykułów istnieje klucz dotyczący sekcji
# jeśli nie istnieje to :
- if not articles.has_key(section): # noqa
+ if section not in articles:
# do listy sekcji dodajemy nową sekcje
sections.append(section)
# deklarujemy nową sekcje w słowniku artykułów przypisując jej
diff --git a/recipes/ncrnext.recipe b/recipes/ncrnext.recipe
index 92d0ca0e2d..96d3337703 100644
--- a/recipes/ncrnext.recipe
+++ b/recipes/ncrnext.recipe
@@ -77,7 +77,7 @@ class NrcNextRecipe(BasicNewsRecipe):
# Add the article to a temporary list
article = {'title': completeTitle, 'date': u'',
'url': href, 'description': '
'}
- if not articles.has_key(index): # noqa
+ if index not in articles:
articles[index] = []
articles[index].append(article)
@@ -90,7 +90,7 @@ class NrcNextRecipe(BasicNewsRecipe):
indices, {u'columnisten': 1, u'koken': 3, u'geld & werk': 2, u'vandaag': 0})
# Apply this sort order to the actual list of feeds and articles
answer = [(key, articles[key])
- for key in indices if articles.has_key(key)] # noqa
+ for key in indices if key in articles]
return answer
diff --git a/recipes/newsweek_polska.recipe b/recipes/newsweek_polska.recipe
index a834b2150e..eda4146c4d 100644
--- a/recipes/newsweek_polska.recipe
+++ b/recipes/newsweek_polska.recipe
@@ -201,8 +201,7 @@ class Newsweek(BasicNewsRecipe):
self.DATE = matches.group(0)
# cover
- img = main_section.find(lambda tag: tag.name == 'img' and tag.has_key( # noqa
- 'alt') and tag.has_key('title'))
+ img = main_section.find('img', src=True, alt=True, title=True)
self.cover_url = img['src']
feeds = []
articles = {}
@@ -233,7 +232,7 @@ class Newsweek(BasicNewsRecipe):
if article is None:
continue
- if articles.has_key(section): # noqa
+ if section in articles:
articles[section].append(article)
else:
articles[section] = [article]
diff --git a/recipes/novosti.recipe b/recipes/novosti.recipe
index 23383aad75..fee0c4d1b0 100644
--- a/recipes/novosti.recipe
+++ b/recipes/novosti.recipe
@@ -82,7 +82,6 @@ class Novosti(BasicNewsRecipe):
else:
str = self.tag_to_string(item)
item.replaceWith(str)
- for item in soup.findAll('img'):
- if not item.has_key('alt'): # noqa
- item['alt'] = 'image'
+ for item in soup.findAll('img', alt=False):
+ item['alt'] = 'image'
return soup
diff --git a/recipes/nsfw_corp.recipe b/recipes/nsfw_corp.recipe
index 05e832a80d..3681daad63 100644
--- a/recipes/nsfw_corp.recipe
+++ b/recipes/nsfw_corp.recipe
@@ -55,8 +55,8 @@ class NotSafeForWork(BasicNewsRecipe):
def get_feeds(self):
self.feeds = []
soup = self.index_to_soup(self.SETTINGS)
- for item in soup.findAll('input', attrs={'type': 'text'}):
- if item.has_key('value') and item['value'].startswith('https://www.nsfwcorp.com/feed/'): # noqa
+ for item in soup.findAll('input', value=True, attrs={'type': 'text'}):
+ if item['value'].startswith('https://www.nsfwcorp.com/feed/'):
self.feeds.append(item['value'])
return self.feeds
return self.feeds
diff --git a/recipes/nspm.recipe b/recipes/nspm.recipe
index f34e823d20..f2e41e9d1d 100644
--- a/recipes/nspm.recipe
+++ b/recipes/nspm.recipe
@@ -109,7 +109,6 @@ class Nspm(BasicNewsRecipe):
else:
str = self.tag_to_string(item)
item.replaceWith(str)
- for item in soup.findAll('img'):
- if not item.has_key('alt'): # noqa
- item['alt'] = 'image'
+ for item in soup.findAll('img', alt=False):
+ item['alt'] = 'image'
return soup
diff --git a/recipes/ottawa_citizen.recipe b/recipes/ottawa_citizen.recipe
index f72b49a78a..a5f16c5bef 100644
--- a/recipes/ottawa_citizen.recipe
+++ b/recipes/ottawa_citizen.recipe
@@ -286,7 +286,7 @@ class CanWestPaper(BasicNewsRecipe):
else:
description = self.tag_to_string(dtag, False)
print("DESCRIPTION: " + description)
- if not articles.has_key(key): # noqa
+ if key not in articles:
articles[key] = []
articles[key].append(dict(
title=title, url=url, date='', description=description, author='', content=''))
@@ -310,5 +310,5 @@ class CanWestPaper(BasicNewsRecipe):
for (k, url) in self.postmedia_index_pages:
parse_web_index(k, url)
- ans = [(key, articles[key]) for key in ans if articles.has_key(key)] # noqa
+ ans = [(key, articles[key]) for key in ans if key in articles]
return ans
diff --git a/recipes/pobjeda.recipe b/recipes/pobjeda.recipe
index 9f52941f88..5671bf30dc 100644
--- a/recipes/pobjeda.recipe
+++ b/recipes/pobjeda.recipe
@@ -86,8 +86,8 @@ class Pobjeda(BasicNewsRecipe):
soup = self.index_to_soup(feedurl)
for item in soup.findAll('div', attrs={'class': 'vijest'}):
description = self.tag_to_string(item.h2)
- atag = item.h1.find('a')
- if atag and atag.has_key('href'): # noqa
+ atag = item.h1.find('a', href=True)
+ if atag is not None:
url = self.INDEX + '/' + atag['href']
title = self.tag_to_string(atag)
date = strftime(self.timefmt)
diff --git a/recipes/politika.recipe b/recipes/politika.recipe
index 48e5359ec9..f46c664fe3 100644
--- a/recipes/politika.recipe
+++ b/recipes/politika.recipe
@@ -58,10 +58,9 @@ class Politika(BasicNewsRecipe):
del item['style']
for item in soup.findAll('a', attrs={'class': 'category'}):
item.name = 'span'
- if item.has_key('href'): # noqa
- del item['href']
- if item.has_key('title'): # noqa
- del item['title']
+ item['href'] = item['title'] = ''
+ del item['href']
+ del item['title']
return soup
def get_cover_url(self):
diff --git a/recipes/polityka.recipe b/recipes/polityka.recipe
index 33e73c7c2f..8deb4f98f5 100644
--- a/recipes/polityka.recipe
+++ b/recipes/polityka.recipe
@@ -51,7 +51,7 @@ class Polityka(BasicNewsRecipe):
'http://archiwum.polityka.pl' + div.a['href'],)
section = self.tag_to_string(article_page.find(
'h2', attrs={'class': 'box_nag'})).split('/')[0].lstrip().rstrip()
- if not articles.has_key(section): # noqa
+ if section not in articles:
articles[section] = []
articles[section].append({
'title': self.tag_to_string(div.a),
diff --git a/recipes/regina_leader_post.recipe b/recipes/regina_leader_post.recipe
index ad56dde0fc..1b928de984 100644
--- a/recipes/regina_leader_post.recipe
+++ b/recipes/regina_leader_post.recipe
@@ -190,7 +190,7 @@ class CanWestPaper(BasicNewsRecipe):
# Find each instance of class="sectiontitle", class="featurecontent"
for divtag in soup.findAll('div', attrs={'class': ["section_title02", "featurecontent"]}):
if divtag['class'].startswith('section_title'):
- # div contains section title
+ # div contains section title
if not divtag.h3:
continue
key = self.tag_to_string(divtag.h3, False)
@@ -215,11 +215,11 @@ class CanWestPaper(BasicNewsRecipe):
autag = divtag.find('h4')
if autag:
author = self.tag_to_string(autag, False)
- if not articles.has_key(key): # noqa
+ if key not in articles:
articles[key] = []
articles[key].append(dict(title=title, url=url, date=pubdate,
description=description, author=author, content=''))
ans = [(keyl, articles[keyl])
- for keyl in ans if articles.has_key(keyl)] # noqa
+ for keyl in ans if keyl in articles]
return ans
diff --git a/recipes/republika.recipe b/recipes/republika.recipe
index 836c6d028c..02daafbe71 100644
--- a/recipes/republika.recipe
+++ b/recipes/republika.recipe
@@ -46,8 +46,8 @@ class Republika(BasicNewsRecipe):
for item in soup.body.findAll(name=['table', 'td', 'tr', 'th', 'caption', 'thead', 'tfoot', 'tbody', 'colgroup', 'col']):
item.name = 'div'
for attrib in attribs:
- if item.has_key(attrib): # noqa
- del item[attrib]
+ item[attrib] = ''
+ del item[attrib]
return soup
def parse_index(self):
diff --git a/recipes/saskatoon_star_phoenix.recipe b/recipes/saskatoon_star_phoenix.recipe
index 1bac2a795b..c78fef6160 100644
--- a/recipes/saskatoon_star_phoenix.recipe
+++ b/recipes/saskatoon_star_phoenix.recipe
@@ -190,7 +190,7 @@ class CanWestPaper(BasicNewsRecipe):
# Find each instance of class="sectiontitle", class="featurecontent"
for divtag in soup.findAll('div', attrs={'class': ["section_title02", "featurecontent"]}):
if divtag['class'].startswith('section_title'):
- # div contains section title
+ # div contains section title
if not divtag.h3:
continue
key = self.tag_to_string(divtag.h3, False)
@@ -215,10 +215,10 @@ class CanWestPaper(BasicNewsRecipe):
autag = divtag.find('h4')
if autag:
author = self.tag_to_string(autag, False)
- if not articles.has_key(key): # noqa
+ if key not in articles:
articles[key] = []
articles[key].append(dict(title=title, url=url, date=pubdate,
description=description, author=author, content=''))
- ans = [(k, articles[k]) for k in ans if articles.has_key(k)] # noqa
+ ans = [(k, articles[k]) for k in ans if k in articles]
return ans
diff --git a/recipes/scprint.recipe b/recipes/scprint.recipe
index 954b2ba011..e4a2edc3b2 100644
--- a/recipes/scprint.recipe
+++ b/recipes/scprint.recipe
@@ -45,11 +45,11 @@ class SCPrintMagazine(BasicNewsRecipe):
if arttitlet is not None:
mylink = arttitlet.find('a')
if mylink is not None:
- if mylink.has_key('title'): # noqa
+ if mylink.get('title'):
arttitle = mylink['title']
else:
arttitle = 'unknown'
- if mylink.has_key('href'): # noqa
+ if mylink.get('href'):
artlink = mylink['href']
artlink = artlink.replace(
"/article", "/printarticle")
diff --git a/recipes/sueddeutsche_mobil.recipe b/recipes/sueddeutsche_mobil.recipe
index ccaf22512e..2b4d8415f9 100644
--- a/recipes/sueddeutsche_mobil.recipe
+++ b/recipes/sueddeutsche_mobil.recipe
@@ -81,7 +81,7 @@ class SZmobil(BasicNewsRecipe):
if itt['href'].startswith('article.php?id='):
article_url = itt['href']
article_id = int(
- re.search("id=(\d*)&etag=", itt['href']).group(1))
+ re.search(r"id=(\d*)&etag=", itt['href']).group(1))
# first check if link is a special article in section
# "Meinungsseite"
@@ -104,7 +104,7 @@ class SZmobil(BasicNewsRecipe):
# just another link ("mehr") to an article
continue
- if itt.has_key('id'): # noqa
+ if itt.get('id') is not None:
shorttitles[article_id] = article_name
else:
articles.append(
@@ -118,7 +118,7 @@ class SZmobil(BasicNewsRecipe):
# pubdate = strftime('')
pubdate = strftime('[%a, %d %b]')
description = ''
- if shorttitles.has_key(article_id): # noqa
+ if shorttitles.get(article_id) is not None:
description = shorttitles[article_id]
# we do not want the flag ("Impressum")
if "HERAUSGEGEBEN VOM" in description:
diff --git a/recipes/techcrunch.recipe b/recipes/techcrunch.recipe
index 6d130e787a..cfdda7f233 100644
--- a/recipes/techcrunch.recipe
+++ b/recipes/techcrunch.recipe
@@ -55,7 +55,6 @@ class TechCrunch(BasicNewsRecipe):
else:
str = self.tag_to_string(item)
item.replaceWith(str)
- for item in soup.findAll('img'):
- if not item.has_key('alt'): # noqa
- item['alt'] = 'image'
+ for item in soup.findAll('img', alt=False):
+ item['alt'] = 'image'
return soup
diff --git a/recipes/the_age.recipe b/recipes/the_age.recipe
index aad60d29b8..3728fd4d1a 100644
--- a/recipes/the_age.recipe
+++ b/recipes/the_age.recipe
@@ -45,7 +45,7 @@ class TheAge(BasicNewsRecipe):
# Make sure to skip: TheAge
- elif section and tag.has_key('href') and len(tag['href'].strip()) > 1: # noqa
+ elif section and tag.get('href'):
url = tag['href'].strip()
if url.startswith('/'):
url = 'http://www.theage.com.au' + url
@@ -105,7 +105,7 @@ class TheAge(BasicNewsRecipe):
# Filter out what's left of the text-mode navigation stuff
- if re.match('((\s)|(\ \;))*\[[\|\s*]*\]((\s)|(\ \;))*$', contents):
+ if re.match(r'((\s)|(\ \;))*\[[\|\s*]*\]((\s)|(\ \;))*$', contents):
p.extract()
continue
diff --git a/recipes/thedgesingapore.recipe b/recipes/thedgesingapore.recipe
index 57462b3465..9277cc297a 100644
--- a/recipes/thedgesingapore.recipe
+++ b/recipes/thedgesingapore.recipe
@@ -47,6 +47,6 @@ class Edgesingapore(BasicNewsRecipe):
for item in soup.body.findAll(name=['table', 'td', 'tr', 'th', 'caption', 'thead', 'tfoot', 'tbody', 'colgroup', 'col']):
item.name = 'div'
for attrib in attribs:
- if item.has_key(attrib): # noqa
- del item[attrib]
+ item[attrib] = ''
+ del item[attrib]
return self.adeify_images(soup)
diff --git a/recipes/theonion.recipe b/recipes/theonion.recipe
index dc5ba8a317..af97c0169a 100644
--- a/recipes/theonion.recipe
+++ b/recipes/theonion.recipe
@@ -78,12 +78,12 @@ class TheOnion(BasicNewsRecipe):
if limg:
item.name = 'div'
item.attrs = []
- if not limg.has_key('alt'): # noqa
+ if not limg.get('alt'):
limg['alt'] = 'image'
else:
str = self.tag_to_string(item)
item.replaceWith(str)
for item in soup.findAll('img'):
- if item.has_key('data-src'): # noqa
+ if item.get('data-src'):
item['src'] = item['data-src']
return soup
diff --git a/recipes/tomshardware.recipe b/recipes/tomshardware.recipe
index 8473fb34a3..27b33d8988 100644
--- a/recipes/tomshardware.recipe
+++ b/recipes/tomshardware.recipe
@@ -57,8 +57,8 @@ class Tomshardware(BasicNewsRecipe):
def cleanup_image_tags(self, soup):
for item in soup.findAll('img'):
for attrib in ['height', 'width', 'border', 'align']:
- if item.has_key(attrib): # noqa
- del item[attrib]
+ item[attrib] = ''
+ del item[attrib]
return soup
def preprocess_html(self, soup):
diff --git a/recipes/twitchfilms.recipe b/recipes/twitchfilms.recipe
index 27144c3d14..3279b6c24c 100644
--- a/recipes/twitchfilms.recipe
+++ b/recipes/twitchfilms.recipe
@@ -45,7 +45,6 @@ class Twitchfilm(BasicNewsRecipe):
else:
str = self.tag_to_string(item)
item.replaceWith(str)
- for item in soup.findAll('img'):
- if not item.has_key('alt'): # noqa
- item['alt'] = 'image'
+ for item in soup.findAll('img', alt=False):
+ item['alt'] = 'image'
return soup
diff --git a/recipes/vancouver_province.recipe b/recipes/vancouver_province.recipe
index a97c53750e..588133290d 100644
--- a/recipes/vancouver_province.recipe
+++ b/recipes/vancouver_province.recipe
@@ -299,7 +299,7 @@ class CanWestPaper(BasicNewsRecipe):
else:
description = self.tag_to_string(dtag, False)
print("DESCRIPTION: " + description)
- if not articles.has_key(key): # noqa
+ if key not in articles:
articles[key] = []
articles[key].append(dict(
title=title, url=url, date='', description=description, author='', content=''))
@@ -323,5 +323,5 @@ class CanWestPaper(BasicNewsRecipe):
for (k, url) in self.postmedia_index_pages:
parse_web_index(k, url)
- ans = [(key, articles[key]) for key in ans if articles.has_key(key)] # noqa
+ ans = [(key, articles[key]) for key in ans if key in articles]
return ans
diff --git a/recipes/vancouver_sun.recipe b/recipes/vancouver_sun.recipe
index 899c8fbca9..e0c9e4fdce 100644
--- a/recipes/vancouver_sun.recipe
+++ b/recipes/vancouver_sun.recipe
@@ -287,7 +287,7 @@ class CanWestPaper(BasicNewsRecipe):
else:
description = self.tag_to_string(dtag, False)
print("DESCRIPTION: " + description)
- if not articles.has_key(key): # noqa
+ if key not in articles:
articles[key] = []
articles[key].append(dict(
title=title, url=url, date='', description=description, author='', content=''))
@@ -311,5 +311,5 @@ class CanWestPaper(BasicNewsRecipe):
for (k, url) in self.postmedia_index_pages:
parse_web_index(k, url)
- ans = [(key, articles[key]) for key in ans if articles.has_key(key)] # noqa
+ ans = [(key, articles[key]) for key in ans if key in articles] # noqa
return ans
diff --git a/recipes/variety.recipe b/recipes/variety.recipe
index f54b732d13..2aa61b3c3f 100644
--- a/recipes/variety.recipe
+++ b/recipes/variety.recipe
@@ -62,7 +62,6 @@ class Variety(BasicNewsRecipe):
else:
str = self.tag_to_string(item)
item.replaceWith(str)
- for item in soup.findAll('img'):
- if not item.has_key('alt'): # noqa
- item['alt'] = 'image'
+ for item in soup.findAll('img', alt=False):
+ item['alt'] = 'image'
return soup
diff --git a/recipes/vedomosti.recipe b/recipes/vedomosti.recipe
index 8133588a1e..f3e67fef11 100644
--- a/recipes/vedomosti.recipe
+++ b/recipes/vedomosti.recipe
@@ -62,16 +62,22 @@ class VedomostiRecipe(BasicNewsRecipe):
if not feedData:
raise NotImplementedError
self.log("parse_index: Feed loaded successfully.")
- if feedData.feed.has_key('title'): # noqa
- self.title = feedData.feed.title
- self.log("parse_index: Title updated to: ", self.title)
- if feedData.feed.has_key('description'): # noqa
- self.description = feedData.feed.description
- self.log("parse_index: Description updated to: ",
- self.description)
+ try:
+ if feedData.feed.title:
+ self.title = feedData.feed.title
+ self.log("parse_index: Title updated to: ", self.title)
+ except Exception:
+ pass
+ try:
+ if feedData.feed.description:
+ self.description = feedData.feed.description
+ self.log("parse_index: Description updated to: ",
+ self.description)
+ except Exception:
+ pass
def get_virtual_feed_articles(feed):
- if feeds.has_key(feed): # noqa
+ if feed in feeds:
return feeds[feed][1]
self.log("Adding new feed: ", feed)
articles = []
@@ -88,7 +94,7 @@ class VedomostiRecipe(BasicNewsRecipe):
continue
article = {'title': title, 'url': link, 'description': item.get(
'description', ''), 'date': item.get('date', ''), 'content': ''}
- if not item.has_key('tags'): # noqa
+ if not item.get('tags'): # noqa
get_virtual_feed_articles('_default').append(article)
continue
for tag in item.tags:
@@ -105,7 +111,7 @@ class VedomostiRecipe(BasicNewsRecipe):
# Select sorted feeds first of all
result = []
for feedName in self.sortOrder:
- if (not feeds.has_key(feedName)): # noqa
+ if (not feeds.get(feedName)):
continue
result.append(feeds[feedName])
del feeds[feedName]
@@ -142,9 +148,9 @@ class VedomostiRecipe(BasicNewsRecipe):
imgDiv = Tag(soup, 'div')
imgDiv['class'] = 'article_img'
- if img.has_key('width'): # noqa
+ if img.get('width'):
del(img['width'])
- if img.has_key('height'): # noqa
+ if img.get('height'):
del(img['height'])
# find description
@@ -180,11 +186,9 @@ class VedomostiRecipe(BasicNewsRecipe):
contents.insert(len(contents.contents), authorsP)
# Fix urls that use relative path
- urls = contents.findAll('a')
+ urls = contents.findAll('a', href=True)
if urls:
for url in urls:
- if not url.has_key('href'): # noqa
- continue
if '/' == url['href'][0]:
url['href'] = self.base_url + url['href']
diff --git a/recipes/wapo_cartoons.recipe b/recipes/wapo_cartoons.recipe
index 4fe51a5903..d4097910ac 100644
--- a/recipes/wapo_cartoons.recipe
+++ b/recipes/wapo_cartoons.recipe
@@ -94,8 +94,8 @@ class WaPoCartoonsRecipe(BasicNewsRecipe):
img = soup.find('img', attrs={'class': 'pic_big'})
if img:
td = img.parent
- if td.has_key('style'): # noqa
- del td['style']
+ td['style'] = ''
+ del td['style']
td.name = 'div'
td['id'] = 'comic_full'
freshSoup.body.append(td)
@@ -134,11 +134,8 @@ class WaPoCartoonsRecipe(BasicNewsRecipe):
'June': '06', 'July': '07', 'August': '08', 'September': '09', 'October': '10',
'November': '11', 'December': '12'}
- opts = select.findAll('option')
+ opts = select.findAll('option', selected=False)
for i in range(1, len(opts)):
- if opts[i].has_key('selected'): # noqa
- continue
-
dateString = self.tag_to_string(opts[i])
rest, sep, year = dateString.rpartition(', ')
parts = rest.split(' ')
diff --git a/recipes/wenxuecity-znjy.recipe b/recipes/wenxuecity-znjy.recipe
index 97a0a2f98f..031175812e 100644
--- a/recipes/wenxuecity-znjy.recipe
+++ b/recipes/wenxuecity-znjy.recipe
@@ -42,11 +42,11 @@ class TheCND(BasicNewsRecipe):
url = 'http://bbs.wenxuecity.com' + url
title = self.tag_to_string(a)
self.log('\tFound article: ', title, ' at:', url)
- dateReg = re.search('(\d\d?)/(\d\d?)/(\d\d)',
+ dateReg = re.search(r'(\d\d?)/(\d\d?)/(\d\d)',
self.tag_to_string(a.parent))
date = '%(y)s/%(m)02d/%(d)02d' % {'y': dateReg.group(3),
'm': int(dateReg.group(1)), 'd': int(dateReg.group(2))}
- if not articles.has_key(date): # noqa
+ if date not in articles: # noqa
articles[date] = []
articles[date].append(
{'title': title, 'url': url, 'description': '', 'date': ''})
diff --git a/recipes/windows_star.recipe b/recipes/windows_star.recipe
index ec97b1223e..d66e4cd9c1 100644
--- a/recipes/windows_star.recipe
+++ b/recipes/windows_star.recipe
@@ -96,10 +96,10 @@ class CanWestPaper(BasicNewsRecipe):
autag = divtag.find('h4')
if autag:
author = self.tag_to_string(autag, False)
- if not articles.has_key(key): # noqa
+ if key not in articles:
articles[key] = []
articles[key].append(dict(title=title, url=url, date=pubdate,
description=description, author=author, content=''))
- ans = [(keyl, articles[key]) for keyl in ans if articles.has_key(keyl)] # noqa
+ ans = [(keyl, articles[key]) for keyl in ans if keyl in articles]
return ans
diff --git a/recipes/windsor_star.recipe b/recipes/windsor_star.recipe
index 5c20cecb8f..b1837120e5 100644
--- a/recipes/windsor_star.recipe
+++ b/recipes/windsor_star.recipe
@@ -189,9 +189,9 @@ class CanWestPaper(BasicNewsRecipe):
# Find each instance of class="sectiontitle", class="featurecontent"
for divtag in soup.findAll('div', attrs={'class': ["section_title02", "featurecontent"]}):
- # self.log(" div class = %s" % divtag['class'])
+ # self.log(" div class = %s" % divtag['class'])
if divtag['class'].startswith('section_title'):
- # div contains section title
+ # div contains section title
if not divtag.h3:
continue
key = self.tag_to_string(divtag.h3, False)
@@ -221,11 +221,11 @@ class CanWestPaper(BasicNewsRecipe):
if autag:
author = self.tag_to_string(autag, False)
# self.log("author %s" % author)
- if not articles.has_key(key): # noqa
+ if key not in articles:
articles[key] = []
articles[key].append(dict(title=title, url=url, date=pubdate,
description=description, author=author, content=''))
ans = [(keyl, articles[keyl])
- for keyl in ans if articles.has_key(keyl)] # noqa
+ for keyl in ans if keyl in articles]
return ans
diff --git a/recipes/zaobao.recipe b/recipes/zaobao.recipe
index 48e24a53c0..4d674c4aaf 100644
--- a/recipes/zaobao.recipe
+++ b/recipes/zaobao.recipe
@@ -83,11 +83,10 @@ class ZAOBAO(BasicNewsRecipe):
]
def preprocess_html(self, soup):
- for tag in soup.findAll(name='a'):
- if tag.has_key('href'): # noqa
- tag_url = tag['href']
- if tag_url.find('http://') != -1 and tag_url.find('zaobao.com') == -1:
- del tag['href']
+ for tag in soup.findAll(name='a', href=True):
+ tag_url = tag['href']
+ if tag_url.find('http://') != -1 and tag_url.find('zaobao.com') == -1:
+ del tag['href']
return soup
def postprocess_html(self, soup, first):
@@ -107,8 +106,8 @@ class ZAOBAO(BasicNewsRecipe):
for i, item in enumerate(soup.findAll('li')):
if i >= self.MAX_ITEMS_IN_INDEX:
break
- a = item.find('a')
- if a and a.has_key('href'): # noqa
+ a = item.find('a', href=True)
+ if a is not None:
a_url = a['href']
a_title = self.tag_to_string(a)
date = ''