Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-08 02:34:06 -04:00
Code Issues Packages Projects Releases Wiki Activity

Fix #6478 (Updated Recipe: Big Oven)

Browse Source
This commit is contained in:
Kovid Goyal 2010-08-11 17:51:59 -06:00
parent de3908cb2f
commit a49c938e7b
1 changed files with 25 additions and 25 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

50
resources/recipes/big_oven.recipe
View File

@ -1,4 +1,5 @@
from calibre.web.feeds.news import BasicNewsRecipe
import re
class BigOven(BasicNewsRecipe):
title = 'BigOven'
@ -22,43 +23,42 @@ class BigOven(BasicNewsRecipe):
, 'publisher' : publisher
, 'language' : language
}
def get_browser(self):
br = BasicNewsRecipe.get_browser()
if self.username is not None and self.password is not None:
br.open('http://www.bigoven.com/')
br.select_form(name='form1')
br['TopMenu_bo1$email'] = self.username
br['TopMenu_bo1$password'] = self.password
br.open('http://www.bigoven.com/account/login?ReturnUrl=/')
br.select_form(nr=1)
br['Email'] = self.username
br['Password'] = self.password
br.submit()
return br
remove_attributes = ['style', 'font']
keep_only_tags = [dict(name='h1')
,dict(name='div', attrs={'class':'img'})
,dict(name='div', attrs={'id':'intro'})
]
remove_tags = [dict(name='div', attrs={'style':["overflow: visible;"]})
,dict(name='div', attrs={'class':['ctas']})
#,dict(name='a', attrs={'class':['edit']})
,dict(name='p', attrs={'class':['byline']})
]
feeds = [(u'4 & 5 Star Rated Recipes', u'http://feeds.feedburner.com/Bigovencom-RecipeRaves?format=xml')]
remove_tags = [dict(name='div', attrs={'class':['ppy-caption']})
,dict(name='div', attrs={'id':['float_corner']})
]
def preprocess_html(self, soup):
for tag in soup.findAll(name='a', attrs={'class':['edit']}):
tag.parent.extract()
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
tag.extract()
return soup
extra_css = '''
h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
h2{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:medium;}
p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
'''
feeds = [(u'4 & 5 Star Rated Recipes', u'http://feeds.feedburner.com/Bigovencom-RecipeRaves?format=xml')]