From 835767b55664719a4f591c71e6dd37e5a7e3f477 Mon Sep 17 00:00:00 2001 From: yoshiko2 Date: Sun, 2 Jul 2023 00:24:44 +0800 Subject: [PATCH] Add site msin #4 --- scrapinglib/msin.py | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/scrapinglib/msin.py b/scrapinglib/msin.py index 5476fb5..3751b9f 100644 --- a/scrapinglib/msin.py +++ b/scrapinglib/msin.py @@ -14,7 +14,7 @@ class Msin(Parser): expr_title_unsubscribe = '//div[@class="mv_title unsubscribe"]/text()' expr_studio = '//a[@class="mv_writer"]/text()' expr_director = '//a[@class="mv_writer"]/text()' - expr_actor = '(//div[@class="performer_text"]/a/text())[1]' + expr_actor = '//div[contains(text(),"出演者：")]/following-sibling::div[1]/div/div[@class="performer_text"]/a/text()' expr_label = '//a[@class="mv_mfr"]/text()' expr_series = '//a[@class="mv_mfr"]/text()' expr_release = '//a[@class="mv_createDate"]/text()' @@ -42,6 +42,8 @@ class Msin(Parser): # if tags are null, use genres if len(super().getTags(htmltree)) == 0: self.expr_tags = self.expr_genres + if len(super().getActors(htmltree)) == 0: + self.expr_actor = self.expr_director result = self.dictformat(htmltree) return result