[fix] handle missing url in twitter results

This commit is contained in:
Adam Tauber 2015-08-25 13:12:51 +02:00
parent c706bea788
commit 28493d41a3
1 changed files with 6 additions and 2 deletions

View File

@ -55,10 +55,14 @@ def response(resp):
# parse results # parse results
for tweet in dom.xpath(results_xpath): for tweet in dom.xpath(results_xpath):
link = tweet.xpath(link_xpath)[0] try:
link = tweet.xpath(link_xpath)[0]
content = extract_text(tweet.xpath(content_xpath)[0])
except Exception:
continue
url = urljoin(base_url, link.attrib.get('href')) url = urljoin(base_url, link.attrib.get('href'))
title = extract_text(tweet.xpath(title_xpath)) title = extract_text(tweet.xpath(title_xpath))
content = extract_text(tweet.xpath(content_xpath)[0])
pubdate = tweet.xpath(timestamp_xpath) pubdate = tweet.xpath(timestamp_xpath)
if len(pubdate) > 0: if len(pubdate) > 0: