edipretoro/scrarls
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Processing correctly links extracted from a post

Browse Source
This commit is contained in:
edipretoro 2026-01-02 15:11:22 +01:00
parent 1d0cb8ed5d
commit a7952bc32c
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
scrarls.py
View File

@ -165,7 +165,7 @@ class TvShow(CrawlSpider):
item['date'] = self.parse_date(article.css('.entry-meta-header-before::text').getall()[1].strip()) item['date'] = self.parse_date(article.css('.entry-meta-header-before::text').getall()[1].strip())
item['summary'] = "".join(article.xpath('.//div[@class="entry-summary"]/node()').extract()) item['summary'] = "".join(article.xpath('.//div[@class="entry-summary"]/node()').extract())
item['image_url'] = article.css('.entry-summary > p > img::attr(src)').get() item['image_url'] = article.css('.entry-summary > p > img::attr(src)').get()
item['download_url'] = "#".join(article.css('.entry-summary > p > a[href ^= "https://rapidgator"]::attr(href)').extract()) item['download_url'] = article.css('.entry-summary > p > a[href ^= "https://rapidgator"]::attr(href)').extract()
yield item yield item
def parse_date(self, formatted_date: str): def parse_date(self, formatted_date: str):