This commit is contained in:
Alhaziel01
2021-07-22 12:27:51 +02:00
5 changed files with 32 additions and 36 deletions

View File

@@ -26,7 +26,7 @@
"guardaserieicu": "https://guardaserie.network",
"hd4me": "https://hd4me.net",
"ilcorsaronero": "https://ilcorsaronero.link",
"ilgeniodellostreaming": "https://ilgeniodellostreaming.mba",
"ilgeniodellostreaming": "https://ilgeniodellostreaming.rip",
"ilgeniodellostreaming_cam": "https://ilgeniodellostreaming.city",
"italiaserie": "https://italiaserie.city",
"mediasetplay": "https://www.mediasetplay.mediaset.it",

View File

@@ -93,17 +93,15 @@ def peliculas(item):
@support.scrape
def episodios(item):
anime = True
def get_ep(item):
find = ''
data = support.match(item, headers=headers).data
match = support.match(data, patron=r'(?: /> |<p>)(?:(?P<season>\d+)&#215;)?(?P<episode>\d+)(?:\s+&#8211;\s+)?(?P<title>[^<]+)<a (?P<data>.*?)(?:<br|</p)').matches
if match:
for m in match:
find += '{}{:02d}|{}|{}|'.format(m[0]+'x' if m[0] else '', int(m[1]), clean_title(m[2]), m[3])
return find
data = get_ep(item)
patron = r'(?P<episode>[^|]+)\|(?P<title>[^|]+)\|(?P<data>[^|]+)\|'
# debug = True
patron = r'>\s*(?:(?P<season>\d+)(?:&#215;|x|×))?(?P<episode>\d+)(?:\s+&#8211;\s+)?[ ]+(?P<title2>[^<]+)[ ]+<a (?P<data>.*?)(?:<br|</p)'
# data = ''
# match = support.match(item, headers=headers, patron=r'(?: /> |<p>)(?:(?P<season>\d+)&#215;)?(?P<episode>\d+)(?:\s+&#8211;\s+)?(?P<title>[^<]+)<a (?P<data>.*?)(?:<br|</p)').matches
# if match:
# for m in match:
# data += '{}{:02d}|{}|{}|'.format(m[0]+'x' if m[0] else '', int(m[1]), clean_title(m[2]), m[3])
#
# patron = r'(?P<episode>[^|]+)\|(?P<title>[^|]+)\|(?P<data>[^|]+)\|'
return locals()

View File

@@ -112,8 +112,8 @@ class CipherSuiteAdapter(host_header_ssl.HostHeaderSSLAdapter):
request.url = urlparse.urlunparse(parse)
try:
ret = super(CipherSuiteAdapter, self).send(request, **kwargs)
if 400 <= ret.status_code < 500:
raise Exception
# if 400 <= ret.status_code < 500:
# raise Exception
except (requests.exceptions.HTTPError, requests.exceptions.ConnectionError, requests.exceptions.SSLError) as e:
logger.info('Request for ' + domain + ' with ip ' + ip + ' failed')
logger.info(e)

View File

@@ -552,13 +552,13 @@ def scrape(func):
if patronNext and inspect.stack()[1][3] not in ['newest'] and len(inspect.stack()) > 2 and inspect.stack()[2][3] not in ['get_channel_results']:
nextPage(itemlist, item, data, patronNext, function)
for it in itemlist:
if it.contentEpisodeNumber and it.contentSeason:
it.title = '[B]{:d}x{:02d} - {}[/B]'.format(it.contentSeason, it.contentEpisodeNumber, it.infoLabels['title'] if it.infoLabels['title'] else it.fulltitle)
if it.contentLanguage:
it.title += typo(it.contentLanguage, '_ [] color kod')
if it.quality:
it.title += typo(it.quality, '_ [] color kod')
# for it in itemlist:
# if it.contentEpisodeNumber and it.contentSeason:
# it.title = '[B]{:d}x{:02d} - {}[/B]'.format(it.contentSeason, it.contentEpisodeNumber, it.infoLabels['title'] if it.infoLabels['title'] else it.fulltitle)
# if it.contentLanguage:
# it.title += typo(it.contentLanguage, '_ [] color kod')
# if it.quality:
# it.title += typo(it.quality, '_ [] color kod')
# next page for pagination
if pagination and len(matches) > pag * pagination and not search:

View File

@@ -11,28 +11,26 @@ else:
import re
import time
import requests
try:
from platformcode import logger
except ImportError:
logger = None
HEADERS = {
'Host': 'translate.google.com',
'User-Agent': 'android'
}
HEADERS = {'User-Agent': 'android',
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
"Accept-Language": "it-IT,it;q=0.8,en-US;q=0.5,en;q=0.3", "Accept-Charset": "UTF-8",
"Accept-Encoding": "gzip"}
MAX_CONECTION_THREAD = 10
SL = 'en'
TL = 'it'
BASE_URL_PROXY = 'https://translate.googleusercontent.com'
BASE_URL_TRANSLATE = 'https://translate.google.com/translate?hl=it&sl=' + SL + '&tl=' + TL + '&u=[TARGET_URL]&sandbox=0' # noqa: E501
BASE_URL_TRANSLATE = 'https://translate.google.com/translate?hl=it&sl=' + SL + '&tl=' + TL + '&u=[TARGET_URL]' # noqa: E501
def checker_url(html, url):
grep_regex = re.findall(r'(?:href="|src="|value=")([^"]+)', html) # noqa: E501
grep_regex = re.findall(r'(?:href="|src="|value=")(https?://translate[^"]+)', html) # noqa: E501
for url_result_regex in grep_regex:
if url in url_result_regex:
return url_result_regex.replace('&amp;', '&')
@@ -44,6 +42,8 @@ def process_request_proxy(url):
try:
domain = urlparse.urlparse(url).netloc
session = requests.Session()
session.headers.update(HEADERS)
target_url = \
BASE_URL_TRANSLATE.replace('[TARGET_URL]', request.quote(url))
@@ -53,7 +53,7 @@ def process_request_proxy(url):
else:
print(target_url)
return_html = requests.get(target_url, timeout=20, headers=HEADERS)
return_html = session.get(target_url, timeout=20)
if not return_html:
return
@@ -68,10 +68,9 @@ def process_request_proxy(url):
else:
print(url_request)
request_final = requests.get(
request_final = session.get(
url_request,
timeout=20,
headers={'User-Agent': 'android'}
timeout=20
)
url_request_proxy = checker_url(
@@ -86,10 +85,9 @@ def process_request_proxy(url):
result = None
while not data or 'Sto traducendo' in data:
time.sleep(0.5)
result = requests.get(
result = session.get(
url_request_proxy,
timeout=20
# headers={'User-Agent': 'android'}
)
data = result.content.decode('utf-8', 'ignore')
if not PY3:
@@ -99,7 +97,7 @@ def process_request_proxy(url):
data = re.sub('\s(\w+)=(?!")([^<>\s]+)', r' \1="\2"', data)
data = re.sub('https://translate\.googleusercontent\.com/.*?u=(.*?)&amp;usg=[A-Za-z0-9_-]+', '\\1', data)
data = re.sub('https?://[a-zA-Z0-9-]+' + domain.replace('.', '-') + '\.translate\.goog(/[a-zA-Z0-9#/-]+)', 'https://' + domain + '\\1', data)
data = re.sub('https?://[a-zA-Z0-9-]*' + domain.replace('.', '-') + '\.translate\.goog(/[a-zA-Z0-9#/-]+)', 'https://' + domain + '\\1', data)
data = re.sub('\s+<', '<', data)
data = data.replace('&amp;', '&').replace('https://translate.google.com/website?sl=' + SL + '&tl=' + TL + '&ajax=1&u=', '')