From cab7a67b32f7947fb4cd552cadd4dd32959cd4fa Mon Sep 17 00:00:00 2001 From: kcy1019 Date: Thu, 19 Nov 2015 23:28:45 +0900 Subject: [PATCH] Fix GoogleParser first-child selector problem --- GoogleScraper/parsing.py | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/GoogleScraper/parsing.py b/GoogleScraper/parsing.py index dd2417be..bd1334dd 100644 --- a/GoogleScraper/parsing.py +++ b/GoogleScraper/parsing.py @@ -354,17 +354,17 @@ class GoogleParser(Parser): 'us_ip': { 'container': '#center_col', 'result_container': 'div.g ', - 'link': 'h3.r > a:first-child::attr(href)', + 'link': 'h3.r > a::attr(href)', 'snippet': 'div.s span.st::text', - 'title': 'h3.r > a:first-child::text', + 'title': 'h3.r > a::text', 'visible_link': 'cite::text' }, 'de_ip': { 'container': '#center_col', 'result_container': 'li.g ', - 'link': 'h3.r > a:first-child::attr(href)', + 'link': 'h3.r > a::attr(href)', 'snippet': 'div.s span.st::text', - 'title': 'h3.r > a:first-child::text', + 'title': 'h3.r > a::text', 'visible_link': 'cite::text' }, 'de_ip_news_items': { @@ -379,17 +379,17 @@ class GoogleParser(Parser): 'us_ip': { 'container': '#center_col', 'result_container': 'li.ads-ad', - 'link': 'h3.r > a:first-child::attr(href)', + 'link': 'h3.r > a::attr(href)', 'snippet': 'div.s span.st::text', - 'title': 'h3.r > a:first-child::text', + 'title': 'h3.r > a::text', 'visible_link': '.ads-visurl cite::text', }, 'de_ip': { 'container': '#center_col', 'result_container': '.ads-ad', - 'link': 'h3 > a:first-child::attr(href)', + 'link': 'h3 > a::attr(href)', 'snippet': '.ads-creative::text', - 'title': 'h3 > a:first-child::text', + 'title': 'h3 > a::text', 'visible_link': '.ads-visurl cite::text', } },