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

...

Browse Source
This commit is contained in:
Kovid Goyal 2014-06-07 20:36:00 +05:30
parent bb77b5a27e
commit 70ec3dba42
1 changed files with 13 additions and 44 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

57
recipes/outlook_india.recipe
View File

@ -39,7 +39,9 @@ class OutlookIndia(BasicNewsRecipe):
"ctl00_cphpagemiddle_divregulars", "ctl00_cphpagemiddle_divregulars",
"ctl00_cphpagemiddle_divquotes"]}), "ctl00_cphpagemiddle_divquotes"]}),
] ]
remove_tags = [dict(name=['script','object','hr']),] remove_tags = [
dict(name=['script','object','hr']),
]
def get_browser(self): def get_browser(self):
br = BasicNewsRecipe.get_browser(self) br = BasicNewsRecipe.get_browser(self)
@ -51,7 +53,6 @@ class OutlookIndia(BasicNewsRecipe):
return br return br
def parse_index(self): def parse_index(self):
soup = self.index_to_soup('http://www.outlookindia.com/issues.aspx') soup = self.index_to_soup('http://www.outlookindia.com/issues.aspx')
# find cover pic # find cover pic
cover = soup.find('img', attrs={'id':"ctl00_cphpagemiddle_dlissues_ctl00_imgcoverpic"}, src=True) cover = soup.find('img', attrs={'id':"ctl00_cphpagemiddle_dlissues_ctl00_imgcoverpic"}, src=True)
@ -62,52 +63,20 @@ class OutlookIndia(BasicNewsRecipe):
# end find cover pic # end find cover pic
# find current issue # find current issue
div = soup.find('div', attrs={'class':re.compile('cententcellpadding')}) div = soup.find('div', attrs={'class':re.compile('cententcellpadding')})
soup = self.index_to_soup(div.find('a')['href'])
if div is None:
return None
href = div.find('a')['href']
# end find current issue # end find current issue
soup = self.index_to_soup(href)
articles = [] articles = []
for a in soup.findAll('a', href=True, attrs={'class':['contentpgsubheadinglink',"contentpgtext",]}) + \
for a in soup.findAll('a', attrs={'class':['contentpgsubheadinglink',"contentpgtext",]}): soup.findAll('a', href=True, attrs={'id':["ctl00_cphpageleft_hlglitterati","ctl00_cphpageleft_hlposcape",]}):
if a and 'href' in a: if a['href'].startswith('http:'):
continue # Clarification type article, has different markup
url = 'http://www.outlookindia.com/' + a['href'] url = 'http://www.outlookindia.com/' + a['href']
else:
url =''
title = self.tag_to_string(a) title = self.tag_to_string(a)
self.log('Found article:', title, 'at', url)
desc = '' articles.append({'title':title, 'date':'', 'url':url, 'description':''})
date = '' if articles:
articles.append({ return [('Current Issue', articles)]
'title':title,
'date':date,
'url':url,
'description':desc,
})
for a in soup.findAll('a', attrs={'id':["ctl00_cphpageleft_hlglitterati","ctl00_cphpageleft_hlposcape",]}):
if a and 'href' in a:
url = 'http://www.outlookindia.com/' + a['href']
else:
url =''
title = self.tag_to_string(a)
desc = ''
date = ''
articles.append({
'title':title,
'date':date,
'url':url,
'description':desc,
})
return [('Current Issue', articles)]
def preprocess_html(self, soup): def preprocess_html(self, soup):
for item in soup.findAll(style=True): for item in soup.findAll(style=True):