Skip to content

crawlersNoticias
crawlersNoticias
Commit fc91c136 authored by Renán Sosa Guillen's avatar Renán Sosa Guillen
Browse files
Options

laJornadaMaya update

parent c908a556
Pipeline #3 failed with stages
      Hide whitespace changes
      Inline Side-by-side
      Showing with 2 additions and 0 deletions
      descarga_hacia_atras/laJornadaMaya/laJornadaMaya/spiders/noticias.py
      View file @ fc91c136
      ...@@ -221,6 +221,7 @@ class QuotesSpider(scrapy.Spider): ...@@ -221,6 +221,7 @@ class QuotesSpider(scrapy.Spider):
      topic = flow_info['news_section'].capitalize() topic = flow_info['news_section'].capitalize()
      for p in response.xpath('//article').css('div.txt').extract(): for p in response.xpath('//article').css('div.txt').extract():
      p = p.replace("<br>", "\n")
      text += remove_tags(p) + "\n" text += remove_tags(p) + "\n"
      ## News item info ## ## News item info ##
      ...@@ -252,6 +253,7 @@ class QuotesSpider(scrapy.Spider): ...@@ -252,6 +253,7 @@ class QuotesSpider(scrapy.Spider):
      topic = flow_info['news_section'].capitalize() topic = flow_info['news_section'].capitalize()
      for p in response.xpath('//article').css('div.txt').extract(): for p in response.xpath('//article').css('div.txt').extract():
      p = p.replace("<br>", "\n")
      text += remove_tags(p) + "\n" text += remove_tags(p) + "\n"
      ## News item info ## ## News item info ##
      ......
      Markdown is supported
      0% or
      You are about to add 0 people to the discussion. Proceed with caution.
      Finish editing this message first!
      Please register or to comment