Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-07 10:14:46 -04:00
Code Issues Packages Projects Releases Wiki Activity

More detailed sections for guardian recipe

Browse Source
This commit is contained in:
Tom Scholl 2011-04-07 22:16:12 +00:00
parent b3413d8226
commit 43b57cb343
1 changed files with 11 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
recipes/guardian.recipe
View File

@ -28,7 +28,7 @@ class Guardian(BasicNewsRecipe):
# List of section titles to ignore # List of section titles to ignore
# For example: ['Sport'] # For example: ['Sport']
ignore_sections = [] ignore_sections = []
timefmt = ' [%a, %d %b %Y]' timefmt = ' [%a, %d %b %Y]'
keep_only_tags = [ keep_only_tags = [
dict(name='div', attrs={'id':["content","article_header","main-article-info",]}), dict(name='div', attrs={'id':["content","article_header","main-article-info",]}),
@ -87,8 +87,14 @@ class Guardian(BasicNewsRecipe):
idx = soup.find('div', id='book-index') idx = soup.find('div', id='book-index')
for s in idx.findAll('strong', attrs={'class':'book'}): for s in idx.findAll('strong', attrs={'class':'book'}):
a = s.find('a', href=True) a = s.find('a', href=True)
yield (self.tag_to_string(a), a['href']) section_title = self.tag_to_string(a)
if not section_title in self.ignore_sections:
prefix = ''
if section_title != 'Main section':
prefix = section_title + ': '
for subsection in s.parent.findAll('a', attrs={'class':'book-section'}):
yield (prefix + self.tag_to_string(subsection), subsection['href'])
def find_articles(self, url): def find_articles(self, url):
soup = self.index_to_soup(url) soup = self.index_to_soup(url)
div = soup.find('div', attrs={'class':'book-index'}) div = soup.find('div', attrs={'class':'book-index'})
@ -109,15 +115,12 @@ class Guardian(BasicNewsRecipe):
'title': title, 'url':url, 'description':desc, 'title': title, 'url':url, 'description':desc,
'date' : strftime('%a, %d %b'), 'date' : strftime('%a, %d %b'),
} }
def parse_index(self): def parse_index(self):
try: try:
feeds = [] feeds = []
for title, href in self.find_sections(): for title, href in self.find_sections():
if not title in self.ignore_sections: feeds.append((title, list(self.find_articles(href))))
feeds.append((title, list(self.find_articles(href))))
return feeds return feeds
except: except:
raise NotImplementedError raise NotImplementedError