Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-08 10:44:09 -04:00
Code Issues Packages Projects Releases Wiki Activity

Fix Big Oven

Browse Source
This commit is contained in:
Kovid Goyal 2011-04-15 15:55:07 -06:00
parent 7736144410
commit 96ab5a8c12
1 changed files with 30 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

43
recipes/big_oven.recipe
View File

@ -36,29 +36,38 @@ class BigOven(BasicNewsRecipe):
remove_attributes = ['style', 'font']
remove_tags = [dict(name='div', attrs={'class':['ppy-caption']})
,dict(name='div', attrs={'id':['float_corner']})
def get_article_url(self, article):
url = article.get('feedburner_origlink',article.get('link', None))
front, middle, end = url.partition('comhttp//www.bigoven.com')
url = front + 'com' + end
return url
keep_only_tags = [dict(name='div', attrs={'id':['nosidebar_main']})]
remove_tags_after = [dict(name='div', attrs={'class':['display-field']})]
remove_tags = [dict(name='ul', attrs={'class':['tabs']})]
preprocess_regexps = [
(re.compile(r'Want detailed nutrition information?', re.DOTALL), lambda match: ''),
(re.compile('\(You could win \$100 in our ', re.DOTALL), lambda match: ''),
]
def preprocess_html(self, soup):
for tag in soup.findAll(name='a', attrs={'class':['deflink']}):
tag.replaceWith(tag.string)
for tag in soup.findAll(name='a', text=re.compile(r'.*View Metric.*', re.DOTALL)):
tag.parent.parent.extract()
for tag in soup.findAll(name='a', text=re.compile(r'.*Add my own photo.*', re.DOTALL)):
tag.parent.parent.extract()
for tag in soup.findAll(name='div', attrs={'class':['container']}):
if tag.find(name='h1'):
continue
if tag.find(name='h2', text=re.compile(r'.*Ingredients.*', re.DOTALL)):
print 'tag found Ingred h2'
continue
if tag.find(name='h2', text=re.compile(r'Preparation.*', re.DOTALL)):
print 'tag found Prep h2'
continue
for tag in soup.findAll(text=re.compile(r'.*Try BigOven Pro for Free.*', re.DOTALL)):
tag.extract()
for tag in soup.findAll(text=re.compile(r'.*Add my photo of this recipe.*', re.DOTALL)):
tag.parent.extract()
for tag in soup.findAll(name='a', text=re.compile(r'.*photo contest.*', re.DOTALL)):
tag.parent.extract()
for tag in soup.findAll(name='a', text='Remove ads'):
tag.parent.parent.extract()
for tag in soup.findAll(name='ol', attrs={'class':['recipe-tags']}):
tag.parent.extract()
return soup
feeds = [(u'4 & 5 Star Rated Recipes', u'http://feeds.feedburner.com/Bigovencom-RecipeRaves?format=xml')]
feeds = [(u'Recent Raves', u'http://www.bigoven.com/rss/recentraves'),
(u'Recipe Of The Day', u'http://feeds.feedburner.com/bigovencom-RecipeOfTheDay')]