Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update Galaxy's Edge

Browse Source
This commit is contained in:
Kovid Goyal 2013-07-19 09:21:33 +05:30
parent 54054c1c9f
commit dc3dde863a
1 changed files with 3 additions and 44 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

45
recipes/galaxys_edge.recipe
View File

@ -14,19 +14,12 @@ class GalaxyEdge(BasicNewsRecipe):
auto_cleanup = True
#keep_only_tags = [dict(id='content')]
#remove_tags = [dict(attrs={'class':['article-links', 'breadcr']}),
#dict(id=['email-section', 'right-column', 'printfooter', 'topover',
#'slidebox', 'th_footer'])]
extra_css = '.photo-caption { font-size: smaller }'
def parse_index(self):
soup = self.index_to_soup('http://www.galaxysedge.com/')
main = soup.find('table', attrs={'width':'911'})
toc = main.find('td', attrs={'width':'225'})
main = soup.find('table', attrs={'width':'944'})
toc = main.find('td', attrs={'width':'204'})
current_section = None
current_articles = []
@ -72,37 +65,3 @@ class GalaxyEdge(BasicNewsRecipe):
return feeds
#def preprocess_raw_html(self, raw, url):
#return raw.replace('<body><p>', '<p>').replace('</p></body>', '</p>')
#def postprocess_html(self, soup, first_fetch):
#for t in soup.findAll(['table', 'tr', 'td','center']):
#t.name = 'div'
#return soup
#def parse_index(self):
#today = time.strftime('%Y-%m-%d')
#soup = self.index_to_soup(
#'http://www.thehindu.com/todays-paper/tp-index/?date=' + today)
#div = soup.find(id='left-column')
#feeds = []
#current_section = None
#current_articles = []
#for x in div.findAll(['h3', 'div']):
#if current_section and x.get('class', '') == 'tpaper':
#a = x.find('a', href=True)
#if a is not None:
#current_articles.append({'url':a['href']+'?css=print',
#'title':self.tag_to_string(a), 'date': '',
#'description':''})
#if x.name == 'h3':
#if current_section and current_articles:
#feeds.append((current_section, current_articles))
#current_section = self.tag_to_string(x)
#current_articles = []
#return feeds