def main():
# 开始准备
prepare()
while_n = 0 # 循环计数器
imglist = []
makedir(Config.directory)
print 'Generate search url'
URL = baseURL()
# 下载 #############
# 获取搜索结果数量并与_count比较取其较小值
count = min(searchResult(URL), Config.count)
# 没有搜索结果时退出
if not count:
print "No search result at current condition."
sys.exit(1)
# 获得指定数量的url, 存放于list
print 'Fetching page',
while len(imglist) < count:
print while_n,
while_n += 1
tmplist = getImageUrlList(URL)
imglist = imglist + tmplist
URL = nextPage(URL, len(tmplist))
print '' # 换行
count = len(imglist)
print "There're %d files to download" % count
# 将已有文件从imglist中去除
imglist = [url for url in imglist
if not getFilenameFromURL(url) in os.listdir(Config.directory)]
print "There's %d files already downloaded." % (count - len(imglist))
# 下载该list
print 'Fetching list of %d files' % len(imglist)
queue = Queue()
for url in imglist:
queue.put(url)
failure = []
for i in range(Config.thread_count):
start_new_thread(downloadFromQueue, (
queue, failure, Config.directory, Config.timeout))
queue.join()
print "%d failed to fetch." % len(failure)
count = 500 # 要下载的数量，自动进到20的倍数
# 代理设置
proxy = 'http://localhost:7001'
use_proxy = False
# 开始准备
if use_proxy: # 设置代理
proxy_install(proxy)
while_n = 0 # 循环计数器
imglist = []
makedir(directory)
print 'Generate search url'
searchURL = search(keyword.encode('gbk'), addtional)
# 下载 #############
# 获取搜索结果数量并与count比较取其较小值
count = min(searchResult(searchURL), count)
# 没有搜索结果时退出
if not count:
print "No search result at current condition."
sys.exit(1)
# 获得指定数量的url, 存放于list ,one page by one page
print 'Fetching page',
while len(imglist) < count:
print while_n,
#mark the times of while
while_n += 1
tmplist = getImageUrlList(searchURL)
imglist = imglist + tmplist
searchURL = nextPage(searchURL, len(tmplist))
print '' # 换行
count = len(imglist)