Update scraper.py

hanzalot · Aug 14, 2016 · e95d485 · e95d485
1 parent 1a77e1d
commit e95d485
Showing 1 changed file with 4 additions and 4 deletions.
diff --git a/scraper.py b/scraper.py
@@ -53,10 +53,10 @@ def parse_best_seller_page(self, response):
         bs_list = response.xpath("//*[@id='main']/div[1]/section[1]/ol/li/article")
         number = 1
         for entry in bs_list:
-            title = response.xpath(".//[@class='title']/text()").extract()
-            author = response.xpath(".//[@class='author']/text()").extract()
-            publisher = response.xpath(".//[@class='publisher']/text()").extract()
-            description = response.xpath(".//[@class='description']/text()").extract()
+            title = response.xpath(".//h3[contains(@class, 'title')]/text()").extract()
+            author = response.xpath(".//p[contains(@class, 'author']/text()").extract()
+            publisher = response.xpath(".//p[contains(@class, 'publisher']/text()").extract()
+            description = response.xpath(".//p[contains(@class, 'description']/text()").extract()
             isbn = response.xpath(".//meta/@content").extract()
             print "label,number,title[0],author[0],publisher[0],description[0],isbn[1],isbn[0]"
             number+=1