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

Fix Time Magazine

Browse Source
This commit is contained in:
Kovid Goyal 2012-10-22 08:08:49 +05:30
parent 1db24f5192
commit d210af8860
1 changed files with 22 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

30
recipes/time_magazine.recipe
View File

@ -23,16 +23,15 @@ class Time(BasicNewsRecipe):
keep_only_tags = [ keep_only_tags = [
{ {
'class':['tout1', 'entry-content', 'external-gallery-img', 'image-meta'] 'class':['primary-col', 'tout1']
}, },
] ]
remove_tags = [ remove_tags = [
{'class':['thumbnail', 'button']}, {'class':['button', 'entry-sharing group', 'wp-paginate',
'moving-markup', 'entry-comments']},
] ]
extra_css = '.entry-date { padding-left: 2ex }'
recursions = 10
match_regexps = [r'/[0-9,]+-(2|3|4|5|6|7|8|9)(,\d+){0,1}.html',r'http://www.time.com/time/specials/packages/article/.*']
preprocess_regexps = [(re.compile( preprocess_regexps = [(re.compile(
r'<meta .+/>'), lambda m:'')] r'<meta .+/>'), lambda m:'')]
@ -45,7 +44,7 @@ class Time(BasicNewsRecipe):
br.select_form(predicate=lambda f: 'action' in f.attrs and f.attrs['action'] == 'https://auth.time.com/login.php') br.select_form(predicate=lambda f: 'action' in f.attrs and f.attrs['action'] == 'https://auth.time.com/login.php')
br['username'] = self.username br['username'] = self.username
br['password'] = self.password br['password'] = self.password
br['magcode'] = ['TD'] # br['magcode'] = ['TD']
br.find_control('turl').readonly = False br.find_control('turl').readonly = False
br['turl'] = 'http://www.time.com/time/magazine' br['turl'] = 'http://www.time.com/time/magazine'
br.find_control('rurl').readonly = False br.find_control('rurl').readonly = False
@ -104,7 +103,14 @@ class Time(BasicNewsRecipe):
method='text').strip() method='text').strip()
if not title: continue if not title: continue
url = a[0].get('href') url = a[0].get('href')
url = re.sub('/magazine/article/0,9171','/subscriber/printout/0,8816', url) if url.startswith('/'):
url = 'http://www.time.com'+url
if '/article/0,' in url:
soup = self.index_to_soup(url)
a = soup.find('a', href=lambda x:x and '/printout/' in x)
url = a['href'].replace('/printout', '/subscriber/printout')
else:
url += 'print/' if url.endswith('/') else '/print/'
if url.startswith('/'): if url.startswith('/'):
url = 'http://www.time.com'+url url = 'http://www.time.com'+url
desc = '' desc = ''
@ -112,10 +118,18 @@ class Time(BasicNewsRecipe):
if p: if p:
desc = html.tostring(p[0], encoding=unicode, desc = html.tostring(p[0], encoding=unicode,
method='text') method='text')
self.log('\t', title, ':\n\t\t', desc) self.log('\t', title, ':\n\t\t', url)
yield { yield {
'title' : title, 'title' : title,
'url' : url, 'url' : url,
'date' : '', 'date' : '',
'description' : desc 'description' : desc
} }
def preprocess_html(self, soup):
for fig in soup.findAll('figure'):
img = fig.find('img')
if img is not None:
fig.replaceWith(img)
return soup