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

Merge branch 'master' of https://github.com/t3d/calibre

Browse Source
This commit is contained in:
Kovid Goyal 2014-02-21 08:32:21 +05:30
commit f5335a41ce
1 changed files with 32 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

40
recipes/gosc_full.recipe
View File

@ -24,20 +24,27 @@ class GN(BasicNewsRecipe):
doc = html.fromstring(raw) doc = html.fromstring(raw)
page = doc.xpath('//div[@class="c"]//div[@class="search-result"]/div[1]/div[2]/h1//a/@href') page = doc.xpath('//div[@class="c"]//div[@class="search-result"]/div[1]/div[2]/h1//a/@href')
return page[4] if time.strftime("%w") in ['3','4']:
return page[5]
else:
return page[4]
def parse_index(self): def parse_index(self):
soup = self.index_to_soup('http://gosc.pl' + self.find_last_issue()) soup = self.index_to_soup('http://gosc.pl' + self.find_last_issue())
self.cover_url = 'http://www.gosc.pl' + soup.find('div',attrs={'class':'fl-w100 release-wp'}).findAll('a')[-4].contents[0]['src'] self.cover_url = 'http://www.gosc.pl' + soup.find('div',attrs={'class':'fl-w100 release-wp'}).findAll('a')[-4].contents[0]['src']
feeds = [] feeds = []
# wstepniak enlisted = []
a = soup.find('div',attrs={'class':'release-wp-b'}).find('a') # editorial:
a = soup.find('div',attrs={'class':'release-wp-b'})
art = a.find('a')
articles = [ articles = [
{'title' : self.tag_to_string(a), {'title' : self.tag_to_string(art),
'url' : 'http://www.gosc.pl' + a['href'] 'url' : 'http://www.gosc.pl' + art['href'],
'description' : self.tag_to_string(a.find('p',attrs={'class':'b lead'}))
}] }]
feeds.append((u'Wstępniak',articles)) feeds.append((u'Wstępniak',articles))
# kategorie enlisted.append(articles[0].get('url'))
# columns:
for addr in soup.findAll('a',attrs={'href':re.compile('kategoria')}): for addr in soup.findAll('a',attrs={'href':re.compile('kategoria')}):
if addr.string != u'wszystkie artyku\u0142y z tej kategorii \xbb': if addr.string != u'wszystkie artyku\u0142y z tej kategorii \xbb':
main_block = self.index_to_soup('http://www.gosc.pl' + addr['href']) main_block = self.index_to_soup('http://www.gosc.pl' + addr['href'])
@ -45,6 +52,20 @@ class GN(BasicNewsRecipe):
if len(articles) > 0: if len(articles) > 0:
section = addr.string section = addr.string
feeds.append((section, articles)) feeds.append((section, articles))
enlisted.extend(list(article.get('url') for article in articles))
# not assigned content:
page = 1
not_assigned = []
while True:
soup = self.index_to_soup('http://gosc.pl' + self.find_last_issue().replace('przeglad','wszystko') + '/' + str(page))
articles = list(self.find_articles(soup))
not_assigned.extend([ x for x in articles if x.get('url') not in enlisted ])
page+=1
pages = soup.find('span', attrs={'class':'pgr_nrs'})
if str(page) not in [self.tag_to_string(x)[1] for x in pages.findAll('a')]:
break
feeds.insert(1,(u'Nieprzypisane', not_assigned))
return feeds return feeds
def find_articles(self, main_block): def find_articles(self, main_block):
@ -52,7 +73,9 @@ class GN(BasicNewsRecipe):
art = a.find('a') art = a.find('a')
yield { yield {
'title' : self.tag_to_string(art), 'title' : self.tag_to_string(art),
'url' : 'http://www.gosc.pl' + art['href'] 'url' : 'http://www.gosc.pl' + art['href'],
'date' : self.tag_to_string(a.find('p', attrs={'class':'sr-date'})),
'description' : self.tag_to_string(a.find('p', attrs={'class':'sr-lead'}))
} }
def append_page(self, soup, appendtag): def append_page(self, soup, appendtag):
@ -77,7 +100,7 @@ class GN(BasicNewsRecipe):
for r in soup.findAll(attrs={'class':['di_dr', 'doc_image']}): for r in soup.findAll(attrs={'class':['di_dr', 'doc_image']}):
del r['style'] del r['style']
for r in soup.findAll(attrs={'class':'cm-i-a'}): for r in soup.findAll(attrs={'class':'cm-i-a'}):
r.replaceWith( r.prettify() + '<div style="clear:both"></div>') r.replaceWith( '<div style="clear:both"></div>' + r.prettify() + '<div style="clear:both"></div>')
return soup return soup
keep_only_tags = [ keep_only_tags = [
@ -88,6 +111,7 @@ class GN(BasicNewsRecipe):
dict(name='p', attrs={'class':['r tr', 'l l-2', 'wykop', 'tags']}), dict(name='p', attrs={'class':['r tr', 'l l-2', 'wykop', 'tags']}),
dict(name='div', attrs={'class':['doc_actions', 'cf', 'fr1_cl']}), dict(name='div', attrs={'class':['doc_actions', 'cf', 'fr1_cl']}),
dict(name='div', attrs={'id':'vote'}), dict(name='div', attrs={'id':'vote'}),
dict(name='link'),
dict(name='a', attrs={'class':'img_enlarge'}) dict(name='a', attrs={'class':'img_enlarge'})
] ]