crawlers

descarga_por_dia/alChile/alChile/spiders/noticias.py

 import scrapy, re
 
-
-## scrapy crawl noticias -t json --nolog -o noticias.json -a year=2017 -a month=3 -a day=22
-
+"""
+scrapy crawl noticias -t json --nolog -o noticias.json -a year=2017 -a month=3 -a day=22
+"""
 
 TAG_RE = re.compile(r'<[^>]+>')
 def remove_tags(text):

descarga_por_dia/desdeElBalcon/desdeElBalcon/spiders/noticias.py

 import scrapy, re
 from datetime import datetime, timedelta, tzinfo
 
-## scrapy crawl noticias -t json --nolog -o noticias.json -a year=2017 -a month=3 -a day=22
+"""
+scrapy crawl noticias -t json --nolog -o noticias.json -a year=2017 -a month=3 -a day=22
+"""
 
 TAG_RE = re.compile(r'<[^>]+>')
 def remove_tags(text):
@@ -46,12 +48,12 @@ class QuotesSpider(scrapy.Spider):
     def parse(self, response):
         pagination = response.xpath('//*[@class="pagination"]/a[@class="page-numbers"]/@href').extract()
 
-		if ( len(pagination) > 0 ):
+        if len(pagination) > 0:
             pagination = pagination[-1].strip('/')
             pages = int(pagination[pagination.rfind('/')+1:])
 
             for page in range(0, pages):
-				if ( page == 0 ):
+                if page == 0:
                     yield scrapy.Request(url=response.url, callback=self.parse_page, dont_filter=True)
 
                 else: