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
@@ -62,7 +62,7 @@ def categorias(item):
    data = httptools.downloadpage(item.url).data
    data = re.sub(r"\n|\r|\t|&nbsp;|<br>", "", data)
    if item.title=="PornStars" :
-        data = scrapertools.get_match(data,'</i> Hall Of Fame Pornstars</h1>(.*?)</section>')
+        data = scrapertools.find_single_match(data,'</i> Hall Of Fame Pornstars</h1>(.*?)</section>')
    patron  = '<a class="thumb" href="([^"]+)">.*?<img src="([^"]+)".*?<div class="vidcountSp">(.*?)</div>.*?<a class="categoryTitle".*?>([^"]+)</a>'
    matches = re.compile(patron,re.DOTALL).findall(data)
    for scrapedurl,scrapedthumbnail,cantidad,scrapedtitle in matches: