regex debugger e altre modifiche varie

This commit is contained in:
marco
2019-07-30 21:14:12 +02:00
committed by mac12m99
parent 4dc1d6b91d
commit cbb45094a5
4 changed files with 31 additions and 42 deletions

View File

@@ -17,13 +17,10 @@
"casacinemainfo": "https://www.casacinema.info",
"cb01anime": "https://www.cineblog01.ink",
"cinemalibero": "https://www.cinemalibero.best",
"cinemastreaming": "https://cinemastreaming.icu",
"documentaristreamingda": "https://documentari-streaming-da.com",
"dreamsub": "https://www.dreamsub.stream",
"eurostreaming": "https://eurostreaming.pink",
"eurostreaming_video": "https://www.eurostreaming.best",
"fastsubita": "http://fastsubita.com",
"ffilms":"https://ffilms.org",
"filmigratis": "https://filmigratis.net",
"filmgratis": "https://www.filmaltadefinizione.net",
"filmontv": "https://www.comingsoon.it",

View File

@@ -9,9 +9,8 @@ from core import scrapertoolsV2, httptools, servertools, tmdb, support
from core.item import Item
from lib import unshortenit
from platformcode import logger, config
from specials import autoplay
#impostati dinamicamente da getUrl()
#impostati dinamicamente da findhost()
host = ""
headers = ""
@@ -56,31 +55,15 @@ def mainlist(item):
return locals()
@support.scrape
def menu(item):
findhost()
itemlist= []
data = httptools.downloadpage(item.url, headers=headers).data
data = re.sub('\n|\t', '', data)
block = scrapertoolsV2.find_single_match(data, item.args + r'<span.*?><\/span>.*?<ul.*?>(.*?)<\/ul>')
support.log('MENU BLOCK= ',block)
patron = r'href="?([^">]+)"?>(.*?)<\/a>'
matches = re.compile(patron, re.DOTALL).findall(block)
for scrapedurl, scrapedtitle in matches:
itemlist.append(
Item(
channel=item.channel,
title=scrapedtitle,
contentType=item.contentType,
action='peliculas',
url=host + scrapedurl
)
)
return support.thumb(itemlist)
patronBlock = item.args + r'<span.*?><\/span>.*?<ul.*?>(.*?)<\/ul>'
patron = r'href="?(?P<url>[^">]+)"?>(?P<title>.*?)<\/a>'
thumb = ''
action = 'peliculas'
return locals()
def newest(categoria):

View File

@@ -112,21 +112,15 @@ def dbg():
web_pdb.set_trace()
def scrape2(item, patron = '', listGroups = [], headers="", blacklist="", data="", patronBlock="",
patronNext="", action="findvideos", addVideolibrary = True, typeContentDict={}, typeActionDict={}):
def regexDbg(item, patron, headers, data=''):
import json, urllib2, webbrowser
url = 'https://regex101.com'
html = httptools.downloadpage(item.url, headers=headers, ignore_response_code=True).data.replace("'", '"')
html = re.sub('\n|\t', ' ', html)
m = re.search(r'\((?!\?)', patron)
n = 0
dbg()
while m:
patron = patron[:m.end()] + '?P<' + listGroups[n] + '>' + patron[m.end():]
m = re.search(r'\((?!\?)', patron)
n += 1
if not data:
html = httptools.downloadpage(item.url, headers=headers, ignore_response_code=True).data.replace("'", '"')
html = re.sub('\n|\t', ' ', html)
else:
html = data
headers = {'content-type': 'application/json'}
data = {
@@ -141,6 +135,17 @@ def scrape2(item, patron = '', listGroups = [], headers="", blacklist="", data="
permaLink = json.loads(r)['permalinkFragment']
webbrowser.open(url + "/r/" + permaLink)
def scrape2(item, patron = '', listGroups = [], headers="", blacklist="", data="", patronBlock="",
patronNext="", action="findvideos", addVideolibrary = True, typeContentDict={}, typeActionDict={}):
m = re.search(r'\((?!\?)', patron)
n = 0
while m:
patron = patron[:m.end()] + '?P<' + listGroups[n] + '>' + patron[m.end():]
m = re.search(r'\((?!\?)', patron)
n += 1
regexDbg(item, patron, headers)
return
def scrape(func):
@@ -182,7 +187,7 @@ def scrape(func):
addVideolibrary = args['addVideolibrary'] if 'addVideolibrary' in args else True
blacklist = args['blacklist'] if 'blacklist' in args else ''
data = args['data'] if 'data' in args else ''
headers = args['headers'] if 'headers' in args else ''
headers = args['headers'] if 'headers' in args else func.__globals__['headers']
patron = args['patron'] if 'patron' in args else ''
patronNext = args['patronNext'] if 'patronNext' in args else ''
patronBlock = args['patronBlock'] if 'patronBlock' in args else ''
@@ -190,6 +195,7 @@ def scrape(func):
typeContentDict = args['type_content_dict'] if 'type_content_dict' in args else {}
if 'pagination' in args: pagination = args['pagination'] if args['pagination'] else 20
else: pagination = ''
log('PATRON= ', patron)
if not data:
data = httptools.downloadpage(item.url, headers=headers, ignore_response_code=True).data.replace("'", '"')
@@ -215,11 +221,14 @@ def scrape(func):
matches = scrapertoolsV2.find_multiple_matches_groups(block, patron)
log('MATCHES =', matches)
if 'debug' in args:
regexDbg(item, patron, headers, block)
known_keys = ['url', 'title', 'title2', 'episode', 'thumb', 'quality', 'year', 'plot', 'duration', 'genere',
'rating', 'type', 'lang'] # by greko aggiunto episode
lang = '' # aggiunto per gestire i siti con pagine di serietv dove si hanno i video in ita e in subita
pag = item.page if item.page else 1 # pagination
pag = item.page if item.page else 1 # pagination
for i, match in enumerate(matches):
if pagination and (pag - 1) * pagination > i: continue # pagination

View File

@@ -645,7 +645,7 @@ def get_languages(channel):
:return: list
'''
logger.info()
list_language = ['No filtrar']
list_language = ['Non filtrare']
list_controls, dict_settings = channeltools.get_channel_controls_settings(channel)
for control in list_controls:
try: