From ad6212da067fdc05a8564e79943692fd9d466110 Mon Sep 17 00:00:00 2001 From: neodarz Date: Sun, 3 Feb 2019 20:02:18 +0100 Subject: Add ability to update a page in db if updated --- crawler/nevrax/pipelines.py | 5 +++-- crawler/nevrax/spiders/scrape.py | 3 ++- 2 files changed, 5 insertions(+), 3 deletions(-) (limited to 'crawler/nevrax') diff --git a/crawler/nevrax/pipelines.py b/crawler/nevrax/pipelines.py index 775d5df..dbbb782 100644 --- a/crawler/nevrax/pipelines.py +++ b/crawler/nevrax/pipelines.py @@ -9,8 +9,9 @@ class NevraxPipeline(object): def process_item(self, item, spider): try: page = Nevrax.get(Nevrax.url == item['url']) - q = Nevrax.update(**item).where(Nevrax.url == item['url']) - q.execute() + if page.content_length != item['content_length']: + q = Nevrax.update(**item).where(Nevrax.url == item['url']) + q.execute() logging.info("Update item {}".format(page)) except Nevrax.DoesNotExist: page = Nevrax.create(**item) diff --git a/crawler/nevrax/spiders/scrape.py b/crawler/nevrax/spiders/scrape.py index 8a7b8ec..785ec3f 100644 --- a/crawler/nevrax/spiders/scrape.py +++ b/crawler/nevrax/spiders/scrape.py @@ -41,5 +41,6 @@ class NevraxSpider(CrawlSpider): yield { 'url': response.url, 'title': response.css('title::text').extract_first(), - 'content': ''.join(sel.select("//body//text()").extract()).strip() + 'content': ''.join(sel.select("//body//text()").extract()).strip(), + 'content_length': len(response.body) } -- cgit v1.2.1