From c918daf26d477f4db4453a52f3a0242edc464302 Mon Sep 17 00:00:00 2001 From: doubaniux Date: Mon, 16 Nov 2020 13:36:31 +0100 Subject: [PATCH] fix summary scraping problem of douban movies --- common/scraper.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/common/scraper.py b/common/scraper.py index 973746c8..44b8c78d 100644 --- a/common/scraper.py +++ b/common/scraper.py @@ -357,8 +357,8 @@ def scrape_douban_movie(url): brief_elem = content.xpath("//span[@class='all hidden']") if not brief_elem: - brief_elem = content.xpath("//span[@property='v:summary']") - brief = brief_elem[0].xpath('./text()')[0].strip() if brief_elem else None + brief_elem = content.xpath("//span[@property='v:summary']/text()") + brief = '\n'.join([e.strip() for e in brief_elem]) if brief_elem else None img_url_elem = content.xpath("//img[@rel='v:image']/@src") img_url = img_url_elem[0].strip() if img_url_elem else None