Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-08-11 09:13:57 -04:00
Code Issues Packages Projects Releases Wiki Activity

...

Browse Source
This commit is contained in:
Kovid Goyal 2011-12-08 09:06:43 +05:30
parent a9b701d685
commit 5cbbc9b998
1 changed files with 10 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
recipes/la_republica.recipe
View File

@ -25,12 +25,12 @@ class LaRepubblica(BasicNewsRecipe):
use_embedded_content = False use_embedded_content = False
no_stylesheets = True no_stylesheets = True
publication_type = 'newspaper' publication_type = 'newspaper'
articles_are_obfuscated = True articles_are_obfuscated = True
temp_files = [] temp_files = []
extra_css = """ extra_css = """
img{display: block} img{display: block}
""" """
remove_attributes = ['width','height','lang','xmlns:og','xmlns:fb'] remove_attributes = ['width','height','lang','xmlns:og','xmlns:fb']
preprocess_regexps = [ preprocess_regexps = [
@ -38,14 +38,14 @@ class LaRepubblica(BasicNewsRecipe):
(re.compile(r'<head>.*?<title>', re.DOTALL|re.IGNORECASE), lambda match: '<head><title>'), (re.compile(r'<head>.*?<title>', re.DOTALL|re.IGNORECASE), lambda match: '<head><title>'),
(re.compile(r'</title>.*?</head>', re.DOTALL|re.IGNORECASE), lambda match: '</title></head>') (re.compile(r'</title>.*?</head>', re.DOTALL|re.IGNORECASE), lambda match: '</title></head>')
] ]
def get_article_url(self, article): def get_article_url(self, article):
link = BasicNewsRecipe.get_article_url(self, article) link = BasicNewsRecipe.get_article_url(self, article)
if link and not '.repubblica.it/' in link: if link and not '.repubblica.it/' in link:
link2 = article.get('id', article.get('guid', None)) link2 = article.get('id', article.get('guid', None))
if link2: if link2:
link = link2 link = link2
return link.rpartition('?')[0] return link.rpartition('?')[0]
def get_obfuscated_article(self, url): def get_obfuscated_article(self, url):
count = 0 count = 0
@ -56,12 +56,12 @@ class LaRepubblica(BasicNewsRecipe):
count = 10 count = 10
except: except:
print "Retrying download..." print "Retrying download..."
count += 1 count += 1
self.temp_files.append(PersistentTemporaryFile('_fa.html')) self.temp_files.append(PersistentTemporaryFile('_fa.html'))
self.temp_files[-1].write(html) self.temp_files[-1].write(html)
self.temp_files[-1].close() self.temp_files[-1].close()
return self.temp_files[-1].name return self.temp_files[-1].name
keep_only_tags = [ keep_only_tags = [
dict(attrs={'class':'articolo'}), dict(attrs={'class':'articolo'}),
dict(attrs={'class':'body-text'}), dict(attrs={'class':'body-text'}),
@ -105,8 +105,8 @@ class LaRepubblica(BasicNewsRecipe):
def preprocess_html(self, soup): def preprocess_html(self, soup):
for item in soup.findAll(['hgroup','deresponsabilizzazione','per']): for item in soup.findAll(['hgroup','deresponsabilizzazione','per']):
item.name = 'div' item.name = 'div'
item.attrs = [] item.attrs = []
for item in soup.findAll(style=True): for item in soup.findAll(style=True):
del item['style'] del item['style']
return soup return soup