Created
April 17, 2018 15:07
-
-
Save BIGBALLON/c06da67e3625c2cb12793b158ff81341 to your computer and use it in GitHub Desktop.
tgram stickers download script
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
# *-* coding: UTF-8 *-* | |
__author__ = 'BG' | |
import urllib2 | |
import os | |
import re | |
class ZOLPIC: | |
def __init__(self): | |
if not os.path.exists('./PIC'): | |
os.mkdir(r'./PIC') | |
def getHtml(self,url): | |
try: | |
html = urllib2.urlopen(url) | |
html = html.read().decode('gbk').encode('utf-8') | |
return html | |
except: | |
return None | |
def startCrawler(self): | |
pic = [ "https://tgram.ru/stickers/dotastickers", | |
"https://tgram.ru/stickers/miawu", | |
"https://tgram.ru/stickers/YOTSUBA", | |
"https://tgram.ru/stickers/Gnu_Linux", | |
"https://tgram.ru/stickers/garfield", | |
"https://tgram.ru/stickers/punda", | |
"https://tgram.ru/stickers/MoviesNVR", | |
"https://tgram.ru/stickers/khafan2", | |
"https://tgram.ru/stickers/papcapic", | |
"https://tgram.ru/stickers/viber_Benny", | |
"https://tgram.ru/stickers/ZebraTelecom", | |
"https://tgram.ru/stickers/BeelineRacoon", | |
"https://tgram.ru/stickers/Tuzki_2", | |
"https://tgram.ru/stickers/SpongeBobStickers", | |
"https://tgram.ru/stickers/minion_rush", | |
"https://tgram.ru/stickers/nyapack", | |
"https://tgram.ru/stickers/viber_Kuma", | |
"https://tgram.ru/stickers/Tuziki", | |
"https://tgram.ru/stickers/pokelife", | |
"https://tgram.ru/stickers/CuttheRope", | |
"https://tgram.ru/stickers/FacebookLikes", | |
"https://tgram.ru/stickers/MemeStickers", | |
"https://tgram.ru/stickers/dotastickers"] | |
for p in pic: | |
cur_page = self.getHtml(p) | |
link_list = re.findall(r'<img class="img-responsive" src="(.*?)" alt=',cur_page) | |
file_path = r'./PIC/'+ p.split('/')[-1] + r'/' | |
if not os.path.exists(file_path): | |
print 'create folder %s' % file_path | |
os.mkdir(file_path) | |
for link in link_list: | |
file_name = file_path + link.split('/')[-1] | |
if not os.path.exists(file_name): | |
print 'download pic %s' % file_name | |
picsrc = urllib2.urlopen(link).read() | |
open( file_name,"wb").write(picsrc) | |
if __name__ == '__main__': | |
spider = ZOLPIC() | |
spider.startCrawler() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment