def parse_captcha(self, site):
soup_obj = HttpUtils.get("https://pt.sjtu.edu.cn/login.php",
headers=site.login_headers)
captcha_image_list = soup_obj.select("form img")
# if captcha image exists, parse expression and return
if len(captcha_image_list) > 0:
image_url = "https://pt.sjtu.edu.cn/" + captcha_image_list[0]["src"]
HttpUtils.download_file(image_url, "/tmp/cap.png", over_write=True)
return PuTaoCaptchaParser.analyze("/tmp/cap.png")
else:
return "XxXx"
def do_process(cls, item):
path = item[0]
url = item[1]
retry = item[2]
if retry <= 5:
if not HttpUtils.download_file(url=url, dest_path=path):
item[2] += 1
cls.task_pool.put(item)
cls.init_thread()
else:
print("Exceed max retry time: " + path)
def login(self, site):
if not self.isLogin and site.login_needed and not self.check_login(
site):
soup_obj = HttpUtils.get("https://pt.sjtu.edu.cn/login.php",
headers=site.login_headers)
# parse captcha image and return result
image_url = "https://pt.sjtu.edu.cn/" + soup_obj.select(
"form img")[0]["src"]
HttpUtils.download_file(image_url, "/tmp/cap.png", over_write=True)
site.check_code = PuTaoCaptchaParser.analyze("/tmp/cap.png")
resp = HttpUtils.post(site.login_page,
data=self.build_post_data(site),
headers=site.login_headers,
returnRaw=True)
self.isLogin = self.check_login(site)
return self.isLogin
else:
self.isLogin = True
return True
def convert(cls, text, audio_file_path):
url = 'http://tts.baidu.com/text2audio?idx=1&tex=%s&cuid=baidu_speech_demo&cod=1&lan=zh&ctp=1&pdt=1&spd=4&per=5&vol=5&pit=7' % text
url = quote(url, safe=string.printable)
HttpUtils.download_file(url, audio_file_path, over_write=True)