aboutsummaryrefslogtreecommitdiff
path: root/crawler/neodarznet/spiders/scrape.py
diff options
context:
space:
mode:
Diffstat (limited to 'crawler/neodarznet/spiders/scrape.py')
-rw-r--r--crawler/neodarznet/spiders/scrape.py3
1 files changed, 2 insertions, 1 deletions
diff --git a/crawler/neodarznet/spiders/scrape.py b/crawler/neodarznet/spiders/scrape.py
index e16ede2..0f54c4a 100644
--- a/crawler/neodarznet/spiders/scrape.py
+++ b/crawler/neodarznet/spiders/scrape.py
@@ -39,5 +39,6 @@ class NeodarznetSpider(CrawlSpider):
yield {
'url': response.url,
'title': response.css('title::text').extract_first(),
- 'content': ''.join(sel.select("//div[@class='bodya']//text()").extract()).strip()
+ 'content': ''.join(sel.select("//div[@class='bodya']//text()").extract()).strip(),
+ 'content_length': len(response.body)
}