def download(threadUrl):
"""
"""
d = PyQuery(url=threadUrl, parser='soup')
links = d('a[href^="job.php?action=download&aid="]')
# 获取 verify 的值
tmp = d('script:contains("var verifyhash =")').text()
verify = re.search(r"var verifyhash = '(.*?)'", tmp).group(1)
total = len(links)
d.make_links_absolute()
for i, e in enumerate(links.items(), start=1):
filename = e.text()
print('%s/%s %s' % (i, total, filename))
if not os.path.exists(os.path.join(SAVE_PATH, filename)):
params = urlencode(
{'check': 1, 'verify': verify, 'nowtime': int(time.time() * 1000)})
url = '%s?%s' % (e.attr['href'], params)
print(' fetch: ' + url)
downDoc = PyQuery(url, headers=headers)
# 第0个是电信下载点，第1个是移动下载点
downUrl = BASE_URL + downDoc('a[href^="remotedown.php"]').eq(1).attr('href')
addToIDM(downUrl, SAVE_PATH, filename)
time.sleep(1.5)
wefiler_urls = checkWefiler(d)
if wefiler_urls:
print(wefiler_urls)
def addAllToIDM(allList):
print('-' * 40)
for url, name in allList:
addToIDM(url, SAVE_PATH, name)
print('添加到IDM成功：{}'.format(name))
print("全部添加到IDM，请开始用IDM下载")
def _addToDownload(url, fileName=None):
""" url 是附件的下载链接
"""
url = url.replace('attachment.php?', 'forum.php?mod=attachment&').replace('&', '&')
addToIDM(url)
# fileName = trimFileName(fileName)
# addToIDM(url, DOWN_PATH, fileName)
print(' 添加到IDM: %s' % fileName)
def _addToDownload(url, fileName=None):
""" url 是附件的下载链接
"""
url = url.replace('attachment.php?',
'forum.php?mod=attachment&').replace('&', '&')
addToIDM(url)
# fileName = trimFileName(fileName)
# addToIDM(url, DOWN_PATH, fileName)
print(' 添加到IDM: %s' % fileName)
def parseFlvcd(url, format='hight'):
# 不知道是否需要 urllib.parse.quote(videourl)
print('目标：{}，清晰度：{}'.format(url, format))
url = "http://www.flvcd.com/parse.php?kw=" + url + '&format=' + format
d = PyQuery(url)
filename = d('input[name="filename"]').attr('value')
filename = re.sub('[\\\|\:\*\"\?\<\>]', "_", filename)
urltxt = d('input[name="inf"]').attr('value')
url = urltxt.strip()
addToIDM(url, SAVE_PATH, filename)
def download(url):
d = PyQuery(url)
title = d('.m-cdes h2').text()
# title = trimFileName(title) # 整个公开课的标题
# info = d('.m-cdes p:first').text() # 本课程共4集 翻译完 欢迎学习
path = os.path.join(BASE_PATH, title)
print('保存的位置：' + path)
# 有2个列表
for e in d('#list2 .u-ctitle').items():
ctitle = e.text() # 一节课的标题
downUrl = e.siblings('.u-cdown .downbtn').attr('href')
#没翻译的为None
if downUrl:
filename = ctitle + '.mp4'
addToIDM(downUrl, path, filename) # retcode=0
def download(url):
d = PyQuery(url)
title = d('.m-cdes h2').text()
# title = trimFileName(title) # 整个公开课的标题
# info = d('.m-cdes p:first').text() # 本课程共4集 翻译完 欢迎学习
path = os.path.join(BASE_PATH, title)
print('保存的位置：' + path)
# 有2个列表
for e in d('#list2 .u-ctitle').items():
ctitle = e.text() # 一节课的标题
downUrl = e.siblings('.u-cdown .downbtn').attr('href')
#没翻译的为None
if downUrl:
filename = ctitle + '.mp4'
addToIDM(downUrl, path, filename) # retcode=0
