1. 导出网易博客相册的图片地址

简述网易blog的相册比原来的网易相册复杂许多，一层一层的javascript分析头都大了，所以就用pywin32调用IE来干这个活了。又改了改，速度快了点。

1.1. 代码

# coding:cp936
import win32com.client
import time
import re
import sys
class Album163blog:
    def __init__(self, name, nextword=u'下一页', percount=8):
        self.name = name
        self.nextword = nextword
        self.percount = percount
        self.curpage = 1
        self.pages = 100 #we will modify it's value in self.connect()
        self.ie = win32com.client.Dispatch('InternetExplorer.Application')
        
    def __home__(self):
        return 'http://%s.blog.163.com/album/' % self.name
    
    def __pageloaded__(self):
        return self.curpage >= self.pages and True or len(self.imgs_href()) >= self.percount
    
    def __pages__(self):
        url = [x.href for x in self.ie.Document.links if x.href.find('.blog.163.com/album/#p') >= 0][-2:][0]
        return int(url[url.find('#p')+2:])
    
    def visible(self, v=True):
        self.ie.Visible = v
        return self
    
    def connect(self):
        self.ie.Navigate2(self.__home__())
        time.sleep(1)
        while self.ie.Busy and self.ie.ReadyState != 4: #READYSTATE_COMPLETE
            time.sleep(1)
        while not self.__pageloaded__():
            time.sleep(1)
        self.pages = self.__pages__()
        return self
    
    def next(self):
        self.curpage += 1
        if self.curpage > self.pages:
            return False
        link = [x for x in self.ie.Document.links if x.innerText.find(self.nextword) >= 0][0]
        link.click()
        while not self.__pageloaded__():
            time.sleep(1)
        return True
    
    def imgs_href(self):
        def urlconv(url):
            return re.sub(r'prevPhoto.do\?', 'prevPhDownload.do?host=%s&' % self.name, url)
        return [urlconv(u) for u in set([x.href for x in self.ie.Document.links if x.href.find(u'prevPhoto') >=0])]

if __name__ == '__main__':
    name = sys.argv[1]
    #name = 'dwl2981332'
    ab = Album163blog(name)
    ab.visible().connect()

    while True:
        links = ab.imgs_href()
        print '\n'.join(links)
        if not ab.next():
            break

MicroProj/2007-10-14

1. 导出网易博客相册的图片地址

1.1. 代码