From fdb3fdae3e75951467b36ee693313ffbf659c200 Mon Sep 17 00:00:00 2001 From: Étienne Loks Date: Mon, 12 Aug 2019 16:15:23 +0200 Subject: Increment page number --- commcrawler/scrapy.py | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/commcrawler/scrapy.py b/commcrawler/scrapy.py index 8b91ac6..bc17225 100644 --- a/commcrawler/scrapy.py +++ b/commcrawler/scrapy.py @@ -331,7 +331,7 @@ def launch_crawl(crawl_item, excluded_domains=None): NUMBER_PER_PAGE = 250 page = 0 page_number = total // NUMBER_PER_PAGE - while page >= page_number: + while page <= page_number: process = CrawlerProcess(settings=scrap_settings) idx = 0 current_idx = page * NUMBER_PER_PAGE @@ -396,7 +396,8 @@ def launch_crawl(crawl_item, excluded_domains=None): ) ) if has_url_to_process: - process.start() + process.start(stop_after_crawl=False) + page += 1 crawl_item.crawl_ended = timezone.now() crawl_item.status = "M" crawl_item.save() -- cgit v1.2.3