def fetch_page(page_url):
html = fetch_url(page_url)
html = html.decode()
# print( html)
match = re.findall(r'<img src="([^"]+.douban.com/view/group_topic/large/public/p\d+\.jpg)"', html)
if match is None:
print("no image in this page\n")
return False
file_table = kv.get("attitude")
page_images = kv.get("page_images")
image_page = kv.get("image_page")
for image_url in match:
file_name = image_url[image_url.rfind("/") + 1 :]
file_name = "images/" + file_name
image_page[file_name] = page_url
page_images.setdefault(page_url, []).append(file_name)
page_images[page_url] = list(set(page_images[page_url]))
kv.save("page_images", page_images)
kv.save("image_page", image_page)
if file_name in file_table:
if file_table[file_name] == "d":
print("hate", file_name)
continue
if os.path.isfile(file_name):
print("skip", file_name)
continue
print("save", file_name)
urllib.request.urlretrieve(image_url, file_name)
def fetch_page(page_url):
html = fetch_url(page_url)
html = html.decode()
# print( html)
match = re.findall(
r'<img src="([^"]+.douban.com/view/group_topic/large/public/p\d+\.jpg)"',
html)
if match is None:
print("no image in this page\n")
return False
file_table = kv.get('attitude')
page_images = kv.get('page_images')
image_page = kv.get('image_page')
for image_url in match:
file_name = image_url[image_url.rfind('/') + 1:]
file_name = 'images/' + file_name
image_page[file_name] = page_url
page_images.setdefault(page_url, []).append(file_name)
page_images[page_url] = list(set(page_images[page_url]))
kv.save('page_images', page_images)
kv.save('image_page', image_page)
if file_name in file_table:
if file_table[file_name] == 'd':
print('hate', file_name)
continue
if os.path.isfile(file_name):
print("skip", file_name)
continue
print("save", file_name)
urllib.request.urlretrieve(image_url, file_name)
print('default is Pass')
action = 'p'
attitude[f] = action
if action == 'd':
print('delete', f)
os.remove(f)
if action == 'la' or action == 'da':
if can_open:
action = action[0]
page_images = kv.get('page_images')
images = page_images[page_url]
for image in images:
if image not in attitude:
print(action, image)
attitude[image] = action
else:
print('u already', attitude[image], image)
else:
print('error, can not do to all')
continue
if action == 'o':
if can_open:
webbrowser.open(page_url)
else:
print('error, can not open')
else:
break
kv.save('attitude', attitude)
# -*- coding: UTF-8 -*-
import os
import kv
import cgi
import json
import log
# enable debugging
import cgitb
cgitb.enable()
print("Content-Type: application/json;charset=utf-8\r")
print("\r")
root = os.getcwd()
attitude_map = kv.get('attitude')
post = cgi.FieldStorage()
action = post['action'].value
action = action[0]
f = post['file'].value
attitude_map[f] = action
file_path = root+'/'+f
if action == 'd' and os.path.isfile(file_path):
os.remove(file_path)
kv.save('attitude', attitude_map)
print(json.dumps({'code': 0, 'action':action, 'file': f}));
import os
import kv
import cgi
import json
import log
# enable debugging
import cgitb
cgitb.enable()
print("Content-Type: application/json;charset=utf-8\r")
print("\r")
root = os.getcwd()
attitude_map = kv.get("attitude")
post = cgi.FieldStorage()
action = post["action"].value
action = action[0]
f = post["file"].value
attitude_map[f] = action
file_path = root + "/" + f
if action == "d" and os.path.isfile(file_path):
os.remove(file_path)
kv.save("attitude", attitude_map)
print(json.dumps({"code": 0, "action": action, "file": f}))
print('default is Pass')
action = 'p'
attitude[f] = action
if action == 'd':
print('delete', f)
os.remove(f)
if action == 'la' or action == 'da':
if can_open:
action = action[0]
page_images = kv.get('page_images')
images = page_images[page_url]
for image in images:
if image not in attitude:
print(action, image)
attitude[image] = action
else:
print('u already',attitude[image],image)
else:
print('error, can not do to all')
continue
if action == 'o':
if can_open:
webbrowser.open(page_url)
else:
print('error, can not open')
else:
break
kv.save('attitude', attitude)
