def scrape_category(first_category_page, site_url="http://books.toscrape.com"):
page_to_scrape = first_category_page
pre_books_to_scrape = []
books_to_scrape = []
while True:
ctext("Category page book list", "yellow")
category_books = get_books_url_from_category_url(page_to_scrape)
pprint(category_books)
ctext("Next category page", "yellow")
page_to_scrape = get_category_next_page(page_to_scrape)
print(page_to_scrape)
pre_books_to_scrape.append(category_books)
if not page_to_scrape:
break
for book_list in pre_books_to_scrape:
for book in book_list:
books_to_scrape.append(book)
ctext("Full Book list from category to scrape :", "green")
pprint(books_to_scrape)
ctext(f"there are {len(books_to_scrape)} books to scrape", 'green')
for book_to_scrape in books_to_scrape:
scrape_a_book_and_hydrate_csv(book_to_scrape, site_url)
ctext("Done")
def find_subdomains(script):
subdomain_regex = re.findall(
r"[%\\]?[a-zA-Z0-9][a-zA-Z0-9-_.]*\." + args.u, str(script))
for subdomain in subdomain_regex:
parsed_subdomain = ""
# If the subdomain is preceded by URL encoding, we removed it.
if "%" in subdomain:
# Sort for double URL encoding
while "%25" in subdomain:
subdomain = subdomain.replace("%25", "%")
parsed_subdomain = subdomain.split("%")[-1][2:]
# If the subdomain is preceded by \x escape sequence, remove it.
elif "\\x" in subdomain:
ctext("[+] " + subdomain, "red")
parsed_subdomain = subdomain.split("\\x")[-1][2:]
# If the subdomain is preceded by \u unicode sequence, remove it.
elif "\\u" in subdomain:
ctext("[+] " + subdomain, "red")
parsed_subdomain = subdomain.split("\\u")[-1][4:]
# Otherwise proceed as normal.
else:
parsed_subdomain = subdomain
if parsed_subdomain not in SUBDOMAINS_ENUMERATED:
if args.v:
ctext("[+] " + subdomain, "green")
SUBDOMAINS_ENUMERATED.append(subdomain)
'''
If our total subdomains discovered is not the same length as our sites visited, scan the rest of our subdomains.
'''
if len(list(set(SUBDOMAINS_ENUMERATED))) != len(list(set(SITES_VISITED))):
for site in SUBDOMAINS_ENUMERATED:
find_scripts(site)
def find_subdomains(script):
"""
Once we have our list of javascript code, we must find all subdomains in the code.
As such, we compare it to a regex and then sort for the various exceptions one might expect to find.
"""
subdomain_regex = re.findall(
r"[%\\]?[a-zA-Z0-9][a-zA-Z0-9-_.]*\." + args.u, str(script))
for subdomain in subdomain_regex:
# If the subdomain is preceded by URL encoding, we removed it.
if "%" in subdomain:
# Sort for double URL encoding
while "%25" in subdomain:
subdomain = subdomain.replace("%25", "%")
parsed_subdomain = subdomain.split("%")[-1][2:]
# If the subdomain is preceded by \x escape sequence, remove it.
elif "\\x" in subdomain:
ctext("[+] " + subdomain, "red")
parsed_subdomain = subdomain.split("\\x")[-1][2:]
# If the subdomain is preceded by \u unicode sequence, remove it.
elif "\\u" in subdomain:
ctext("[+] " + subdomain, "red")
parsed_subdomain = subdomain.split("\\u")[-1][4:]
# Otherwise proceed as normal.
else:
parsed_subdomain = subdomain
if parsed_subdomain not in SUBDOMAINS_ENUMERATED:
if args.v:
ctext("[+] " + subdomain, "green")
SUBDOMAINS_ENUMERATED.append(subdomain)
# If our total subdomains discovered is not the same length as our sites visited, scan the rest of our subdomains.
if len(list(set(SUBDOMAINS_ENUMERATED))) != len(list(set(SITES_VISITED))):
for site in SUBDOMAINS_ENUMERATED:
find_scripts(site)
def find_subdomains(script):
subdomain_regex = re.findall(
r"[%\\]?[a-zA-Z0-9][a-zA-Z0-9-_.]*\." + args.u, str(script))
for subdomain in subdomain_regex:
if "%" in subdomain:
# If the subdomain is preceded by URL encoding, we removed it.
parsed_subdomain = subdomain.split("%")[-1][2:]
if parsed_subdomain not in SUBDOMAINS_ENUMERATED:
if args.v:
ctext(parsed_subdomain, "green", "black")
SUBDOMAINS_ENUMERATED.append(parsed_subdomain)
elif "\\x" in subdomain:
# If the subdomain is preceded by \x escape sequence, remove it.
parsed_subdomain = subdomain.split("\\x")[-1][2:]
if parsed_subdomain not in SUBDOMAINS_ENUMERATED:
if args.v:
ctext(parsed_subdomain, "green", "black")
SUBDOMAINS_ENUMERATED.append(parsed_subdomain)
else:
# Otherwise proceed as normal.
if subdomain not in SUBDOMAINS_ENUMERATED:
if args.v:
ctext(subdomain, "green", "black")
SUBDOMAINS_ENUMERATED.append(subdomain)
'''
If our total subdomains discovered is not the same length as our sites visited, scan the rest of our subdomains.
'''
if len(list(set(SUBDOMAINS_ENUMERATED))) != len(list(set(SITES_VISITED))):
for site in SUBDOMAINS_ENUMERATED:
find_scripts(site)
def ascii_banner():
ctext(" `. ___", "red")
ctext(" __,' __`. _..----....____",
"red")
ctext(" __...--.'``;. ,. ;``--..__ .' ,-._ _.-'",
"red")
ctext(" _..-''-------' `' `' `' O ``-''._ (,;') _,'", "red")
ctext(",'________________ \`-._`-','", "red")
ctext(" `._ ```````````------...___ '-.._'-:", "red")
ctext(" ```--.._ ,. ````--...__\-.", "red")
ctext(" `.--. `-` ____ | |`", "red")
ctext(" `. `. ,'`````. ; ;`", "red")
ctext(" `._`. __________ `. \'__/`", "red")
ctext(" `-:._____/______/___/____`. \ `", "red")
ctext(" SUBSCRAPER | `._ `. \\", "red")
ctext(" SUBSCRAPER `._________`-. `. `.___", "red")
ctext(" SUBSCRAPER v1.0.0 `------'`", "red")
ctext("\nSubdomains Found:\n")
def WhichLineSide(x, y, x0, y0, x1, y1):
det = x * y0 + y * x1 + x0 * y1 - x1 * y0 - y1 * x - x0 * y
return sign(det)
colors = [
'black', 'grey', 'red', 'green', 'yellow', 'blue', 'magenta', 'cyan',
'white'
]
if __name__ == '__main__':
print('This is a module!')
ctext(
''
) # For some reason colors in windows terminal don't work until I've called ctext() at least once, so here it is, unfortunately
class Figure:
def __init__(self, color='white'):
if color not in colors:
raise ValueError(
'\'color\' must be one of these values: \'white\', \'red\', \'green\', \'blue\', \'yellow\', \'magenta\', \'cyan\', \'grey\', \'black\'.'
)
self.color = color
class Rectangle(Figure):
def __init__(self, x, y, w, h, color='white', fill=False):
Figure.__init__(self, color)
def errout(self):
ctext(str(self), text="red", bg="black")
