Created
August 27, 2018 21:22
-
-
Save kirussian911/51d96c9e1051e412843e101a9e59d1e4 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import os | |
import re | |
import urllib.request | |
import requests | |
def load_source(website): | |
site = urllib.request.urlopen(website) | |
read_site = site.read() | |
return read_site | |
def parse_img(source): | |
links = [] | |
t = str(source) | |
pattern = '<img width="\d+" height="\d+" src="' | |
result = re.split(pattern, t) | |
# рабочий вариант через replace | |
# t = str(source).replace('550', ' ').replace('375', ' ').split('<img width=" " height=" " src="') | |
for i in result: | |
r = str(i).split('""') | |
links.append(r[0]) | |
return links | |
# Здесь мы получаем имя файла и сохраняем его | |
def download(links): | |
folder = 'ali' | |
if not os.path.exists('folder'): | |
os.makedirs('ali') | |
path = os.path.abspath(folder) | |
print(path) | |
for i in links: | |
try: | |
v = requests.get(i, stream=True) | |
filename = i.replace('?', '/').split('/')[8] | |
#https://i0.wp.com/aliholic.com/wp-content/uploads/2018/08/magnetic-phone-holder-e153497563539jpg0.?resize=375%2C375&ssl=1" | |
print(filename) # magnetic-phone-holder-e1534975635390.jpg | |
with open(filename, 'bw') as f: | |
for chunk in v.iter_content(4096): | |
f.write(chunk) | |
except: | |
pass | |
def main(): | |
print('start page: ') | |
source = load_source('https://aliholic.com/shop/') | |
links = parse_img(source) | |
download((links)) | |
print('Tnx') | |
if __name__=='__main__': | |
main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment