def calcio2():
##return a list of links
url2 = ops('aHR0cDovLzE3Mi42Ny4yMDkuMjM1Lw==').decode("utf-8")
links = []
headers = {
'Host':
ops('ZGFkZHlsaXZlLmNsdWI=').decode("utf-8"),
'User-Agent':
'Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:47.0) Gecko/20100101 Firefox/47.0'
}
req = requests.get(url2, headers=headers).text
soup = BeautifulSoup(
req, 'html.parser') ##div class="col-lg-3 col-md-4 col-xs-4 mb-30"
for i in soup.findAll("article", class_="col-xs-12"):
##links
link = str((i.findAll('p'))[0]) ##only soccer
regex = r'>(.*?)\<\/span\>'
link = re.findall(regex, link)
for i in link:
i = i.replace('<br/>', '')
i = re.findall('^(.*?)>', i)
i = str(i)
i = i.replace('<a href=',
': ').replace('"',
'').replace('[\'',
'').replace('\']', '')
i = i.replace('/stream/', '/embed/')
links.append(i)
return links
def testpage(author):
author=author.replace(' ','-').lower()
base_url = "aHR0cHM6Ly9kd25sZy50ZWwvYm9vay1uLw=="
author = author.rstrip()
try:
new_url = ops(base_url).decode("utf-8") + author + "/"
a=urllib.request.urlopen(new_url)
a.getcode()
return True
except urllib.error.HTTPError as e:
return False
def calcio():
url2 = ops('aHR0cDovLzE3Mi42Ny4xODguMTc1L3Byb2cudHh0').decode("utf-8")
headers = {
'Host':
ops('c3BvcnR6b25saW5lLnRv').decode("utf-8"),
'User-Agent':
'Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:47.0) Gecko/20100101 Firefox/47.0'
}
html = requests.get(url2, headers=headers).text
html = html.splitlines()
links = []
lan = []
for line in html:
if 'HD' in line or 'BR' in line:
lan += [line]
if 'http' in line:
if not '24/7 CHANNELS' in line: line = updategmt(line)
links += [line]
return links, lan
def retrive_books(authors, bformat="pdf"):
reg_ex_interno = r'a href="\/book-n[^>]+>([^<]+)'
if bformat == "mobi": reg_ex_books = r'>([^\.]+\.mobi)<\/a>'
elif bformat == "pdf": reg_ex_books = r'>([^\.]+\.pdf)<\/a>'
else: reg_ex_books = r'>([^\.]+\.epub)<\/a>'
base_url = "aHR0cHM6Ly9kd25sZy50ZWwvYm9vay1uLw==" #b64 to evoid being triggered by target searches
downloaded_titles = []
for author in authors:
if 1:
author = author.rstrip()
new_url = ops(base_url).decode("utf-8") + author + "/"
print("\nWorking on " + author)
req = urllib.request.Request(new_url)
resp = urllib.request.urlopen(req)
respData = resp.read()
books = re.findall(reg_ex_interno, str(respData))
responso=[]
for book in books:
if "Directory" not in book:
print("Processing book " + book)
url_download_book = new_url + book + "/"
req = urllib.request.Request(url_download_book)
resp = urllib.request.urlopen(req)
respData = resp.read()
titles = re.findall(reg_ex_books, str(respData))
for title in titles:
download_url = url_download_book + title
filename = author.replace("-", " ") + " - " + title.replace("-", " ")
if 1:
filename = author.replace("-", " ") + " - " + title.replace("-", " ").replace(".pdf",'')
#strin="Download "+filename+": "+url_download_book
strin="Download "+filename+": \n"+download_url+"\n\n"+download_url.replace(".pdf",".epub")+"\n\n"+download_url.replace(".pdf",".mobi")
responso.append(strin)
else:
print("Something bad happened :/")
return responso
def encodecode(stringa):
dec = ops(stringa).decode("utf-8")
enc = ops(stringa).encode()
return 'E: ' + enc + '\n\nD: ' + dec
import requests, time, random
from bs4 import BeautifulSoup
from base64 import b64decode as ops
dec = ops('aHR0cHM6Ly9pdC4xbGliLmV1').decode("utf-8")
def scrapedeep(url):
req = requests.get(url).text
soup = BeautifulSoup(req, 'html.parser')
i = soup.find('a', class_="btn btn-primary dlButton addDownloadedBook")
i = dec + i.get('href')
return i
def scrapeResults(url):
#prende l'url e vede i vari risultati, li apre e prende i collegamenti diretti
#div id searchResultBox
req = requests.get(url).text
results = []
soup = BeautifulSoup(req, 'html.parser')
for i in soup.find_all("div",
class_="resItemBox resItemBoxBooks exactMatch"):
r = random.randint(1, 13) / 10
time.sleep(r)
try:
it = i.find('h3')
it = it.find('a')
link = dec + it.get('href')
nome = it.get_text()
def dump(authors, sleep_time=2, bformat="epub"):
reg_ex_interno = r'a href="\/book-n[^>]+>([^<]+)'
if bformat == "mobi": reg_ex_books = r'>([^\.]+\.mobi)<\/a>'
elif bformat == "pdf": reg_ex_books = r'>([^\.]+\.pdf)<\/a>'
else: reg_ex_books = r'>([^\.]+\.epub)<\/a>'
base_url = "aHR0cHM6Ly9kd25sZy50ZWwvYm9vay1uLw==" #b64 to evoid being triggered by target searches
try:
for author in authors:
try:
author = author.rstrip()
new_url = ops(base_url).decode("utf-8") + author + "/"
print("\nWorking on " + author)
req = urllib.request.Request(new_url)
resp = urllib.request.urlopen(req)
respData = resp.read()
print("Downloaded author page")
cartella = './d/' + author + '/'
choice = "y"
if not os.path.isdir(cartella):
os.mkdir(cartella)
else:
choice = input(
"La cartella esiste già. Vuoi riscaricare questo autore? y/n: "
)
if choice == "y":
books = re.findall(reg_ex_interno, str(respData))
print("Verranno scaricati:")
for b in books:
print(b)
c = input("Press enter to continue, type 0 to abort: ")
if c == '0':
break
for book in books:
if "Directory" not in book:
print("Progessing book " + book)
url_download_book = new_url + book + "/"
req = urllib.request.Request(url_download_book)
resp = urllib.request.urlopen(req)
respData = resp.read()
titles = re.findall(reg_ex_books, str(respData))
for title in titles:
download_url = url_download_book + title
filename = author.replace(
"-", " ") + " - " + title.replace(
"-", " ")
try:
req = urllib.request.Request(
download_url,
data=None,
headers={
'User-Agent':
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/35.0.1916.47 Safari/537.36'
})
definitive_filename = filename.title()
definitive_filename = definitive_filename.replace(
"Epub", "epub")
out_file = open(
os.path.join(cartella,
definitive_filename),
'wb')
with urllib.request.urlopen(
download_url) as response:
print(
"==============================================================="
)
print("Downloading! " +
definitive_filename)
print(
"==============================================================="
)
data = response.read(
) # a `bytes` object
out_file.write(data)
print("Sleeping for " + str(sleep_time) +
" seconds\n")
time.sleep(sleep_time)
except:
print("Something bad happened :/")
except:
print(
"Something Happened, I don't know what and I don't give a f**k about. If u didn't select 'epub', try to do it now"
)
print(
"===============================================================\n\n\n\n\n"
)
run()
except KeyboardInterrupt:
exit(0)