Corrección scrapertools.cachepage y scrapertools.get_match

2019-04-03 17:19:52 +02:00
parent 867a14fe23
commit 550e67da94
33 changed files with 76 additions and 112 deletions
@@ -23,7 +23,7 @@ def categorias(item):
    logger.info()
    itemlist = []
    data = httptools.downloadpage(item.url).data
-    data = scrapertools.get_match(data,'<h3>Categories</h3>(.*?)</ul>')
+    data = scrapertools.find_single_match(data,'<h3>Categories</h3>(.*?)</ul>')
    patron  = '<li class="cat-item cat-item-\d+"><a href="(.*?)" >(.*?)</a>'
    matches = re.compile(patron,re.DOTALL).findall(data)
    for scrapedurl,scrapedtitle in matches: