pictuga
/
morss
1
1
Fork 0
Code Issues Pull Requests Actions Packages Releases Activity

Improve feedify string grabbing

master
pictuga 2013-10-01 20:18:55 +02:00
parent 050be7690d
commit 685bc7988e
2 changed files with 17 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
feedify.ini
View File

@ -6,6 +6,6 @@ path=
title= //head/title/text() title= //head/title/text()
items= //div[class=tweet] items= //div[class=tweet]
item_title= (.//span[class=username]//text())[2] item_title= .//span[class=username]//text()
item_link= .//a[class=details]/@href item_link= .//a[class=details]/@href
item_content= .//p[class=tweet-text] item_content= .//p[class=tweet-text]

26
feedify.py
View File

@ -14,7 +14,7 @@ def toclass(query):
repl = r'[@class and contains(concat(" ", normalize-space(@class), " "), " \1 ")]' repl = r'[@class and contains(concat(" ", normalize-space(@class), " "), " \1 ")]'
return re.sub(pattern, repl, query) return re.sub(pattern, repl, query)
def getRule(link=URL): def getRule(link):
config = ConfigParser() config = ConfigParser()
config.read('feedify.ini') config.read('feedify.ini')
@ -29,10 +29,16 @@ def getRule(link=URL):
def supported(link): def supported(link):
return getRule(link) is not False return getRule(link) is not False
def getString(expr, html): def getString(html, expr):
match = html.xpath(toclass(expr)) matches = html.xpath(toclass(expr))
if len(match): if len(matches):
return match[0].text_content() out = ''
for match in matches:
if isinstance(match, basestring):
out += match
elif isinstance(match, lxml.html.HtmlElement):
out += lxml.html.tostring(match)
return out
else: else:
return '' return ''
@ -48,22 +54,22 @@ def build(link, data=None):
feed = feeds.FeedParserAtom() feed = feeds.FeedParserAtom()
if 'title' in rule: if 'title' in rule:
feed.title = html.xpath(toclass(rule['title']))[0] feed.title = getString(html, rule['title'])
if 'items' in rule: if 'items' in rule:
for item in html.xpath(toclass(rule['items'])): for item in html.xpath(toclass(rule['items'])):
feedItem = {} feedItem = {}
if 'item_title' in rule: if 'item_title' in rule:
feedItem['title'] = item.xpath(toclass(rule['item_title']))[0] feedItem['title'] = getString(item, rule['item_title'])
if 'item_link' in rule: if 'item_link' in rule:
url = item.xpath(toclass(rule['item_link']))[0] url = getString(item, rule['item_link'])
url = urlparse.urljoin(link, url) url = urlparse.urljoin(link, url)
feedItem['link'] = url feedItem['link'] = url
if 'item_desc' in rule: if 'item_desc' in rule:
feedItem['desc'] = lxml.html.tostring(item.xpath(toclass(rule['item_desc']))[0], encoding='unicode') feedItem['desc'] = getString(item, rule['item_desc'])
if 'item_content' in rule: if 'item_content' in rule:
feedItem['content'] = lxml.html.tostring(item.xpath(toclass(rule['item_content']))[0]) feedItem['content'] = getString(item, rule['item_content'])
feed.items.append(feedItem) feed.items.append(feedItem)
return feed return feed