Fix regex
This commit is contained in:
t1254362
@@ -1,100 +1,100 @@
|
|||||||
# -*- coding: utf-8 -*-
|
# -*- coding: utf-8 -*-
|
||||||
|
|
||||||
import re
|
import re
|
||||||
|
|
||||||
from core import httptools
|
from core import httptools
|
||||||
from core.item import Item
|
from core.item import Item
|
||||||
from platformcode import logger
|
from platformcode import logger
|
||||||
from urlparse import urljoin
|
from urlparse import urljoin
|
||||||
from core import servertools
|
from core import servertools
|
||||||
|
|
||||||
|
|
||||||
HOST="http://yespornplease.com"
|
HOST="http://yespornplease.com"
|
||||||
|
|
||||||
def mainlist(item):
|
def mainlist(item):
|
||||||
logger.info()
|
logger.info()
|
||||||
itemlist = []
|
itemlist = []
|
||||||
itemlist.append(item.clone(action="links", title="Novedades", url=HOST))
|
itemlist.append(item.clone(action="links", title="Novedades", url=HOST))
|
||||||
itemlist.append(item.clone(action="categories", title="Categorías", url=urljoin(HOST, "categories")))
|
itemlist.append(item.clone(action="categories", title="Categorías", url=urljoin(HOST, "categories")))
|
||||||
itemlist.append(item.clone(action="search", title="Buscar", url=urljoin(HOST, "search")))
|
itemlist.append(item.clone(action="search", title="Buscar", url=urljoin(HOST, "search")))
|
||||||
return itemlist
|
return itemlist
|
||||||
|
|
||||||
|
|
||||||
def search(item, texto):
|
def search(item, texto):
|
||||||
logger.info("texto = %s" %(texto))
|
logger.info("texto = %s" %(texto))
|
||||||
|
|
||||||
item.url = urljoin(HOST, "search&q=" + texto)
|
item.url = urljoin(HOST, "search&q=" + texto)
|
||||||
try:
|
try:
|
||||||
return links(item)
|
return links(item)
|
||||||
# Se captura la excepción, para no interrumpir al buscador global si un canal falla
|
# Se captura la excepción, para no interrumpir al buscador global si un canal falla
|
||||||
except:
|
except:
|
||||||
import sys
|
import sys
|
||||||
for line in sys.exc_info():
|
for line in sys.exc_info():
|
||||||
logger.error("%s" % line)
|
logger.error("%s" % line)
|
||||||
return []
|
return []
|
||||||
|
|
||||||
def categories(item):
|
def categories(item):
|
||||||
logger.info()
|
logger.info()
|
||||||
data = httptools.downloadpage(item.url).data
|
data = httptools.downloadpage(item.url).data
|
||||||
|
|
||||||
result = []
|
result = []
|
||||||
|
|
||||||
categories = re.findall("href=[\"'](?P<url>/search[^\"']+).*?>(?P<name>[^<>]+)</div>.*?badge[^>]+>(?P<counter>\d+)", data, re.DOTALL | re.MULTILINE)
|
categories = re.findall("href=[\"'](?P<url>/search[^\"']+).*?>(?P<name>[^<>]+)</div>.*?badge[^>]+>(?P<counter>\d+)", data, re.DOTALL | re.MULTILINE)
|
||||||
for url, name, counter in categories:
|
for url, name, counter in categories:
|
||||||
result.append(item.clone(action = "links", title = "%s (%s videos)" % (name, counter), url = urljoin(item.url, url)))
|
result.append(item.clone(action = "links", title = "%s (%s videos)" % (name, counter), url = urljoin(item.url, url)))
|
||||||
|
|
||||||
return result
|
return result
|
||||||
|
|
||||||
def get_page(url):
|
def get_page(url):
|
||||||
page = re.search("p=(\d+)", url)
|
page = re.search("p=(\d+)", url)
|
||||||
if page:
|
if page:
|
||||||
return int(page.group(1))
|
return int(page.group(1))
|
||||||
return 1
|
return 1
|
||||||
|
|
||||||
def get_page_url(url, page):
|
def get_page_url(url, page):
|
||||||
logger.debug("URL: %s to page %d" % (url, page))
|
logger.debug("URL: %s to page %d" % (url, page))
|
||||||
resultURL = re.sub("([&\?]p=)(?:\d+)", "\g<1>%d" % page, url)
|
resultURL = re.sub("([&\?]p=)(?:\d+)", "\g<1>%d" % page, url)
|
||||||
if resultURL == url:
|
if resultURL == url:
|
||||||
resultURL += ("&" if "?" in url else "?") + "p=%d" % (page)
|
resultURL += ("&" if "?" in url else "?") + "p=%d" % (page)
|
||||||
|
|
||||||
logger.debug("Result: %s" % (resultURL))
|
logger.debug("Result: %s" % (resultURL))
|
||||||
return resultURL
|
return resultURL
|
||||||
|
|
||||||
|
|
||||||
def links(item):
|
def links(item):
|
||||||
logger.info()
|
logger.info()
|
||||||
data = httptools.downloadpage(item.url).data
|
data = httptools.downloadpage(item.url).data
|
||||||
|
|
||||||
reExpr = "<img\s+src=['\"](?P<img>[^'\"]+)[^>]+title[^'\"]*['\"](?P<title>[^\"]+)[^>]+id[^'\"]*['\"](?P<id>[^'\"]+)[^>]*>(?:[^<]*<[^>]+>(?P<quality>[^<]+)<)?[^<]*<[^>]*duration[^>]*>(?P<duration>[^<]+)"
|
reExpr = "<img\s+src=['\"](?P<img>[^'\"]+)[^>]+(?:title|alt)[^'\"]*['\"](?P<title>[^\"]+)[^>]+id[^'\"]*['\"](?P<id>[^'\"]+)[^>]*>(?:[^<]*<[^>]+>(?P<quality>[^<]+)<)?[^<]*<[^>]*duration[^>]*>(?P<duration>[^<]+)"
|
||||||
reResults = re.findall(reExpr, data, re.MULTILINE | re.DOTALL)
|
reResults = re.findall(reExpr, data, re.MULTILINE | re.DOTALL)
|
||||||
result = []
|
result = []
|
||||||
|
|
||||||
for img, title, vID, quality, duration in reResults:
|
for img, title, vID, quality, duration in reResults:
|
||||||
logger.info("[link] %(title)s [%(quality)s] [%(duration)s]: %(vid)s (%(img)s" % ({"title": title, "duration": duration, "vid": vID, "img": img, "quality": quality if quality else "--"}))
|
logger.info("[link] %(title)s [%(quality)s] [%(duration)s]: %(vid)s (%(img)s" % ({"title": title, "duration": duration, "vid": vID, "img": img, "quality": quality if quality else "--"}))
|
||||||
|
|
||||||
formattedQuality = ""
|
formattedQuality = ""
|
||||||
if quality:
|
if quality:
|
||||||
formattedQuality += " [%s]" % (quality)
|
formattedQuality += " [%s]" % (quality)
|
||||||
|
|
||||||
titleFormatted = "%(title)s%(quality)s [%(duration)s]" % ({"title": title, "quality": formattedQuality, "duration": duration})
|
titleFormatted = "%(title)s%(quality)s [%(duration)s]" % ({"title": title, "quality": formattedQuality, "duration": duration})
|
||||||
result.append(item.clone(action = "play", title = titleFormatted, url = urljoin(item.url, "/view/%s" % (vID)), thumbnail = urljoin(item.url, img), vID = vID))
|
result.append(item.clone(action = "play", title = titleFormatted, url = urljoin(item.url, "/view/%s" % (vID)), thumbnail = urljoin(item.url, img), vID = vID))
|
||||||
|
|
||||||
# Has pagination
|
# Has pagination
|
||||||
paginationOccurences = data.count('class="prevnext"')
|
paginationOccurences = data.count('class="prevnext"')
|
||||||
if paginationOccurences:
|
if paginationOccurences:
|
||||||
page = get_page(item.url)
|
page = get_page(item.url)
|
||||||
logger.info("Page " + str(page) + " Ocurrences: " + str(paginationOccurences))
|
logger.info("Page " + str(page) + " Ocurrences: " + str(paginationOccurences))
|
||||||
if page > 1:
|
if page > 1:
|
||||||
result.append(item.clone(action = "links", title = "<< Anterior", url = get_page_url(item.url, page - 1)))
|
result.append(item.clone(action = "links", title = "<< Anterior", url = get_page_url(item.url, page - 1)))
|
||||||
|
|
||||||
if paginationOccurences > 1 or page == 1:
|
if paginationOccurences > 1 or page == 1:
|
||||||
result.append(item.clone(action = "links", title = "Siguiente >>", url = get_page_url(item.url, page + 1)))
|
result.append(item.clone(action = "links", title = "Siguiente >>", url = get_page_url(item.url, page + 1)))
|
||||||
|
|
||||||
|
|
||||||
return result
|
return result
|
||||||
|
|
||||||
def play(item):
|
def play(item):
|
||||||
logger.info(item)
|
logger.info(item)
|
||||||
embededURL = urljoin(item.url, "/e/%s/width-650/height-400/autoplay-0/" % (item.vID))
|
embededURL = urljoin(item.url, "/view/%s" % (item.vID))
|
||||||
itemlist = servertools.find_video_items(item.clone(url = embededURL))
|
itemlist = servertools.find_video_items(item.clone(url = embededURL))
|
||||||
return itemlist
|
return itemlist
|
||||||
|
|||||||
Reference in New Issue
Block a user