well that was a tiny change to make the scraping working again lol
This commit is contained in:
@@ -28,7 +28,8 @@ class unloze_spider(scrapy.Spider):
|
|||||||
Parsing content in the events sections
|
Parsing content in the events sections
|
||||||
"""
|
"""
|
||||||
newest_thread = None
|
newest_thread = None
|
||||||
threads = response.xpath("//div[@class='structItem-title']/@uix-href").extract()
|
#threads = response.xpath("//div[@class='structItem-title']/@uix-href").extract()
|
||||||
|
threads = response.xpath("//div[@class='structItem-title']/a/@href").extract()
|
||||||
for thread in threads:
|
for thread in threads:
|
||||||
if "poll" in thread.lower() or "nomination-thread" in thread.lower() or "events-suggestion-thread" in thread.lower():
|
if "poll" in thread.lower() or "nomination-thread" in thread.lower() or "events-suggestion-thread" in thread.lower():
|
||||||
continue
|
continue
|
||||||
|
|||||||
Reference in New Issue
Block a user