Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-08 18:54:09 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update Der Tagesspiegel

Browse Source
This commit is contained in:
Kovid Goyal 2012-01-13 23:05:55 +05:30
parent 0dbaf01e9e
commit 6e0a0db64d
1 changed files with 7 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
recipes/tagesspiegel.recipe
View File

@ -14,6 +14,7 @@ class TagesspiegelRSS(BasicNewsRecipe):
language = 'de' language = 'de'
oldest_article = 7 oldest_article = 7
max_articles_per_feed = 100 max_articles_per_feed = 100
publication_type = 'newspaper'
extra_css = ''' extra_css = '''
.hcf-overline{color:#990000; font-family:Arial,Helvetica,sans-serif;font-size:xx-small;display:block} .hcf-overline{color:#990000; font-family:Arial,Helvetica,sans-serif;font-size:xx-small;display:block}
@ -33,13 +34,16 @@ class TagesspiegelRSS(BasicNewsRecipe):
no_javascript = True no_javascript = True
remove_empty_feeds = True remove_empty_feeds = True
encoding = 'utf-8' encoding = 'utf-8'
remove_tags = [{'class':'hcf-header'}] remove_tags = [{'class':'hcf-header'}, {'class':'hcf-atlas'}, {'class':'hcf-date hcf-separate'}]
def print_version(self, url): def print_version(self, url):
url = url.split('/') url = url.split('/')
url[-1] = 'v_print,%s?p='%url[-1] url[-1] = 'v_print,%s?p='%url[-1]
return '/'.join(url) return '/'.join(url)
def get_masthead_url(self):
return 'http://www.tagesspiegel.de/images/tsp_logo/3114/6.png'
def parse_index(self): def parse_index(self):
soup = self.index_to_soup('http://www.tagesspiegel.de/zeitung/') soup = self.index_to_soup('http://www.tagesspiegel.de/zeitung/')
@ -51,7 +55,7 @@ class TagesspiegelRSS(BasicNewsRecipe):
ans = [] ans = []
maincol = soup.find('div', attrs={'class':re.compile('hcf-main-col')}) maincol = soup.find('div', attrs={'class':re.compile('hcf-main-col')})
for div in maincol.findAll(True, attrs={'class':['hcf-teaser', 'hcf-header', 'story headline']}): for div in maincol.findAll(True, attrs={'class':['hcf-teaser', 'hcf-header', 'story headline', 'hcf-teaser hcf-last']}):
if div['class'] == 'hcf-header': if div['class'] == 'hcf-header':
try: try:
@ -61,7 +65,7 @@ class TagesspiegelRSS(BasicNewsRecipe):
except: except:
continue continue
elif div['class'] == 'hcf-teaser' and getattr(div.contents[0],'name','') == 'h2': elif div['class'] in ['hcf-teaser', 'hcf-teaser hcf-last'] and getattr(div.contents[0],'name','') == 'h2':
a = div.find('a', href=True) a = div.find('a', href=True)
if not a: if not a:
continue continue