Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-08-11 09:13:57 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update Entrepeneur Magazine

Browse Source
This commit is contained in:
Kovid Goyal 2015-07-09 16:34:11 +05:30
parent 8ff707afd6
commit c9002607f6
1 changed files with 18 additions and 30 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

48
recipes/entrepeneur.recipe
View File

@ -23,7 +23,7 @@ class EntrepeneurMagRecipe(BasicNewsRecipe):
remove_javascript = True remove_javascript = True
keep_only_tags = [ keep_only_tags = [
dict(attrs={'class':['headline']}), dict(attrs={'class':['headline', 'hero topimage']}),
dict(itemprop='articlebody'), dict(itemprop='articlebody'),
] ]
remove_tags = [ remove_tags = [
@ -35,39 +35,27 @@ class EntrepeneurMagRecipe(BasicNewsRecipe):
def parse_index(self): def parse_index(self):
root = self.index_to_soup(self.INDEX + '/magazine/index.html', as_tree=True) root = self.index_to_soup(self.INDEX + '/magazine/index.html', as_tree=True)
for href in root.xpath('//div[@class="Ddeck title"]/a/@href'): for href in root.xpath('//h2[@class="sectiontitle nb"]/a/@href'):
return self.parse_ent_index(self.INDEX + href) return self.parse_ent_index(self.INDEX + href)
def parse_ent_index(self, url): def parse_ent_index(self, url):
root = self.index_to_soup(url, as_tree=True) root = self.index_to_soup(url, as_tree=True)
img = root.xpath('//div[@class="magcoverissue"]/img')[0] img = root.xpath('//a[@class="hero"]/img[@class="lazy"]')[0]
self.cover_url = img.get('src') self.cover_url = img.get('data-original')
self.timefmt = ' [%s]' % img.get('alt').rpartition('-')[-1].strip() self.timefmt = ' [%s]' % img.get('alt').rpartition('-')[-1].strip()
body = root.xpath('//div[@class="cbody"]')[0] body = root.xpath('//div[@id="latest"]')[0]
current_section = 'Unknown'
current_articles = []
ans = [] ans = []
for x in body.xpath('descendant::*[name() = "h2" or name() = "h3"]'): for x in body.xpath('descendant::h3'):
if x.tag == 'h2': title = self.tag_to_string(x)
if current_articles: try:
ans.append((current_section, current_articles)) a = x.xpath('./a')[0]
current_section = self.tag_to_string(x) except IndexError:
current_articles = [] continue
self.log('Found section:', current_section) url = self.INDEX + a.get('href')
else: d = x.getnext()
title = self.tag_to_string(x) desc = self.tag_to_string(d) if d is not None else ''
try: self.log('\t', title, 'at:', url)
a = x.xpath('./a')[0] self.log('\t\t', desc)
except IndexError: ans.append({'title':title, 'url':url, 'description':desc})
continue
url = self.INDEX + a.get('href')
d = x.getnext()
desc = self.tag_to_string(d) if d is not None else ''
self.log('\t', title, 'at:', url)
self.log('\t\t', desc)
current_articles.append({'title':title, 'url':url, 'description':desc})
if current_articles: return [('Articles', ans)]
ans.append((current_section, current_articles))
return ans