@@ -59,16 +59,14 @@ def response(resp):
59 url = link.attrib.get('href')
59 url = link.attrib.get('href')
60 title = extract_text(link)
60 title = extract_text(link)
61 contentXPath = result.xpath('.//div[@class="sn_txt"]/div//span[@class="sn_snip"]')
61 contentXPath = result.xpath('.//div[@class="sn_txt"]/div//span[@class="sn_snip"]')
62− if contentXPath is not None:
63− content = escape(extract_text(contentXPath))
62+ content = escape(extract_text(contentXPath))
65 # parse publishedDate
64 # parse publishedDate
66 publishedDateXPath = result.xpath('.//div[@class="sn_txt"]/div'
65 publishedDateXPath = result.xpath('.//div[@class="sn_txt"]/div'
67 '//span[contains(@class,"sn_ST")]'
66 '//span[contains(@class,"sn_ST")]'
68 '//span[contains(@class,"sn_tm")]')
67 '//span[contains(@class,"sn_tm")]')
70− if publishedDateXPath is not None:
71− publishedDate = escape(extract_text(publishedDateXPath))
69+ publishedDate = escape(extract_text(publishedDateXPath))
73 if re.match("^[0-9]+ minute(s|) ago$", publishedDate):
71 if re.match("^[0-9]+ minute(s|) ago$", publishedDate):
74 timeNumbers = re.findall(r'\d+', publishedDate)
72 timeNumbers = re.findall(r'\d+', publishedDate)