tanner/qotnews
1
0
Fork 1
Code Issues Pull Requests Releases Wiki Activity

remove unnecessary sitemap.xml request.

Browse Source
This commit is contained in:
Jason Schwarzenberger 2020-11-04 11:22:15 +13:00
parent db6aad84ec
commit 9f4ff4acf0
1 changed files with 7 additions and 24 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

31
apiserver/feeds/news.py
View File

@ -109,36 +109,20 @@ class Sitemap:
return [x.find('loc').text for x in articles] or [] return [x.find('loc').text for x in articles] or []
def story(self, ref): def story(self, ref):
markup = xml(lambda x: self.sitemap_url) markup = xml(lambda x: ref)
if not markup: return [] if not markup:
soup = BeautifulSoup(markup, features='lxml')
articles = soup.find('urlset').findAll('url')
articles = list(filter(None, [a if a.find('lastmod') is not None else None for a in articles]))
articles = list(filter(None, [a if a.find('loc').text == ref else None for a in articles]))
if len(articles) == 0:
return False return False
r = articles[0]
if not r:
return False
html = xml(lambda x: ref)
if not html:
return False
data = extruct.extract(html)
s = {} s = {}
s['author_link'] = '' s['author_link'] = ''
s['score'] = '' s['score'] = 0
s['comments'] = [] s['comments'] = []
s['num_comments'] = 0 s['num_comments'] = 0
s['link'] = ref s['link'] = ref
s['url'] = ref s['url'] = ref
s['date'] = unix(r.find('lastmod').text) s['date'] = 0
data = extruct.extract(markup)
s = parse_extruct(s, data) s = parse_extruct(s, data)
return s return s
@ -162,17 +146,16 @@ class Category:
if not markup: if not markup:
return False return False
data = extruct.extract(markup)
s = {} s = {}
s['author_link'] = '' s['author_link'] = ''
s['score'] = '' s['score'] = 0
s['comments'] = [] s['comments'] = []
s['num_comments'] = 0 s['num_comments'] = 0
s['link'] = ref s['link'] = ref
s['url'] = ref s['url'] = ref
s['date'] = 0 s['date'] = 0
data = extruct.extract(markup)
s = parse_extruct(s, data) s = parse_extruct(s, data)
return s return s