def __init__(self, numero, palavra):
self.numero = numero
self.nivel = 0
self.palavra_original = ""
self.palavra_canonica = ""
self.tags = []
self.tag_inicial = ""
nivelEnd = StringUtil.find(palavra, ".")
parentesesInicio = StringUtil.find(palavra, "(")
parentesesFim = StringUtil.find(palavra, ")")
if (nivelEnd == -1):
raise Exception("Erro: Formato da palavra inválido('" + palavra +
"'). Palavra.__init__")
self.nivel = palavra[:nivelEnd]
if (parentesesInicio == -1 or parentesesFim == -1):
self.tag_inicial = palavra[nivelEnd + 2:]
else:
tagsDentroParenteses = palavra[parentesesInicio +
1:(parentesesFim -
len(palavra))].split()
self.tag_inicial = palavra[nivelEnd + 2:parentesesInicio]
self.palavra_original = palavra.split()[-1].replace("*", "")
self.palavra_canonica = tagsDentroParenteses[0].replace(
"\"", "").replace("*", "")
self.tags = tagsDentroParenteses[1:]
def etapa2_removeDadosNaoNecessarios(etapa1_retorno_palavras):
"""
Transforma o retorno do palavras em uma lista e remove dados/linhas não necessárias.
ex: "<ß>"/"<servicos>"
:param etapa1_retorno_palavras: Retorno do método "etapa1_getResultadoPalavras"
:return: lista com as informações relavantes do retorno do palavras.
"""
etapa1_retorno_palavras_list = etapa1_retorno_palavras.split(
BREAK_LINE)
listaFinal = []
dentroA1 = False
for i in range(len(etapa1_retorno_palavras_list)):
if (etapa1_retorno_palavras_list[i] == 'A1'):
dentroA1 = True
continue
if (dentroA1
and StringUtil.isEmpty(etapa1_retorno_palavras_list[i])):
dentroA1 = False
if (dentroA1):
listaFinal.append(
StringUtil.removeStrings([TAB, BREAK_LINE],
etapa1_retorno_palavras_list[i],
" "))
return listaFinal
def testStringUtil(self):
# print(random.randint(1, 10))
# print(random.randint(5000, 5017))
# from utils.StringUtil import is_empty
# is_empty("")
from utils import StringUtil
print(
StringUtil.hump_case_underline_lower("oneHTTPRequest12AaureBBBXu"))
print(StringUtil.underline2hump("hello_word"))
print(StringUtil.hump2underline("URLCamelCaseHello12Word"))
json_str = """{"userName":"******"}"""
print(StringUtil.json_hump2underline(json_str))
def testSplit(self):
strs = StringUtil.split(",,", ",")
for i in range(len(strs)):
self.assertEqual("", strs[i])
strs = StringUtil.split("1,,", ",")
self.assertEqual("1", strs[0])
self.assertEqual("", strs[1])
self.assertEqual("", strs[2])
strs = StringUtil.split("1,,1", ",")
self.assertEqual("1", strs[0])
self.assertEqual("", strs[1])
self.assertEqual("1", strs[2])
def sendMail(self,
mailTo: list,
subject: str,
content: str, cc: list = [],
_charset: str = "UTF-8",
mimeType: MimeType = MimeType.PLAIN
):
"""
发送邮件的方法
:param mailTo: toAddr 发送到的邮箱地址 需要是数组
:param subject: 标题
:param content: 内容
:param cc 抄送
:param _charset 编码
:param mimeType 邮件格式
"""
if not isinstance(mailTo, list):
logging.error("mailTo: TypeError: must be list")
return
if cc is not None and not isinstance(cc, list):
logging.error("cc: TypeError: must be list")
return
mail = MIMEMultipart()
msg = MIMEText(content, _subtype=mimeType.value, _charset=_charset)
mail.attach(msg)
mail['To'] = self.__formatAddr("<%s>" % StringUtil.arrayToStr(mailTo, ';'))
if not CommonUtil.isEmpty(cc):
mail['Cc'] = StringUtil.arrayToStr(cc, ';')
mailTo = mailTo + cc
mail['Subject'] = Header(subject, 'UTF-8').encode()
mail['From'] = self.__formatAddr(self.__fromAlias + ' <%s>' % self.__mailFrom)
try:
server = smtplib.SMTP(self.__smtpServer, self.__smtpPort)
server.set_debuglevel(1)
server.login(self.__mailFrom, self.__password)
server.sendmail(self.__mailFrom, mailTo, mail.as_string())
except smtplib.SMTPException:
logging.error("邮件发送失败")
finally:
server.quit()
def path_join(*path):
"""
路径拼接
:param path:路径字符串数组
:return:
"""
final_path = ""
for i in range(len(path)):
p = path[i]
if StringUtil.is_empty(p):
continue
if StringUtil.check_startswith(p):
p = p[1:]
if StringUtil.check_endswith(p):
p = p[:-1]
if i == 0:
final_path = p
else:
final_path = os.path.join(final_path, p)
def short_time_mail_apply():
"""
随机申请shorttimemail.com邮箱
:return: 邮箱号
"""
prefix = StringUtil.random_lowercase_alphanumeric(9)
suffix = "@shorttimemail.com"
data = {"prefix": prefix, "suffix": suffix}
# post续期30分钟：/mail/continue
# post销毁：/mail/destory
# post删除邮件：/mail/delete ，参数：{ ids: ids.join('|') }以|分割字符串
res = HttpUtil.get_json(url=Constants.SHORT_TIME_MAIL + "/mail/apply", data=data)
if res.code != 200:
raise MsgException(res.msg)
return prefix + suffix
def testIsEmpty(self):
self.assertTrue(StringUtil.isEmpty(""))
self.assertTrue(StringUtil.isEmpty(None))
self.assertFalse(StringUtil.isEmpty("me"))
def testRegex(self):
string = r"1234"
self.assertTrue(StringUtil.matchRegex(r"[0-9]*", string))
def testSubString(self):
string = "0123456789"
self.assertEqual(StringUtil.subString(string, 0, 6), "012345")
self.assertEqual(StringUtil.subString(string, 0, 6, 2), "024")
def testArrayToString(self):
list = [1, 2, 3]
self.assertEqual("1,2,3", StringUtil.arrayToStr(list, ","))
self.assertEqual("[1,2,3]", StringUtil.arrayToStr(list, ",", "[", "]"))
def get_url_dp(product):
"""
通过ChromeDP获取下载产品信息
:param product: 产品
:return:
"""
if product == "" or product is None:
raise MsgException("产品不能为空")
if netsarang_info is not None and netsarang_info and product in netsarang_info.keys(
):
info = netsarang_info[product]
# 如果数据不为空，并且日期为今天，这么做是为了避免消耗过多的性能，每天只查询一次
if len(info) > 1 and not info and TimeUtil.date_compare_to(
info[0], datetime.now()) == 0:
return info[1]
prefix = StringUtil.random_lowercase_alphanumeric(9)
suffix = Mail.lin_shi_you_xiang_suffix()
Mail.lin_shi_you_xiang_apply(prefix)
mail = prefix + suffix
send_mail_dp(mail, product)
time.sleep(10)
mail_list = Mail.lin_shi_you_xiang_list(prefix)
mail_len = len(mail_list)
if mail_len == 0 or not mail_list:
raise MsgException("邮件列表为空！")
mailbox = mail_list[mail_len - 1]["mailbox"]
if mailbox is None or mailbox == "":
raise MsgException("邮件列表为空！")
mail_id = mail_list[mail_len - 1]["id"]
if mail_id is None or mail_id == "":
raise MsgException("邮件ID为空！")
# 获取最新一封邮件
mail_content = Mail.lin_shi_you_xiang_get_mail(mailbox, mail_id)
# 解密，邮件协议Content-Transfer-Encoding指定了base64
html_text = base64.b64decode(mail_content.split("AmazonSES")[1])
# 解析解密后的HTML
html = BeautifulSoup(html_text, features="html.parser")
# 查找带token的标签的值
href = html.find("a", {"target": "_blank"}).text
# 请求token链接地址获取下载链接
# bs = ReptileUtil.selenium_bs(href)
# href = bs.find("a", {"target": "download_frame"})["href"]
try:
driver = ReptileUtil.selenium_driver(href)
driver.implicitly_wait(10)
href = driver.find_element_by_css_selector(
"a[target='download_frame']").get_attribute("href")
finally:
# 关闭当前窗口。
driver.close()
# 关闭浏览器并关闭chreomedriver进程
driver.quit()
href = href.replace(".exe", "r.exe")
# 把产品信息存储到变量
netsarang_info[product] = [datetime.now(), href]
return href
获取邮箱列表
:param prefix: 邮箱前缀
:return:
"""
url = Constants.LIN_SHI_YOU_XIANG + "/api/v1/mailbox/" + prefix
return HttpUtil.get_json(url=url, data=None)
def lin_shi_you_xiang_get_mail(prefix, id):
url = Constants.LIN_SHI_YOU_XIANG + "/mailbox/" + prefix + "/" + id + "/source"
return HttpUtil.get(url=url, data=None).text
def lin_shi_you_xiang_delete(prefix, id):
"""
删除邮件delete请求
:param id: 邮件编号
:param prefix: 邮箱前缀
:return:
"""
url = Constants.LIN_SHI_YOU_XIANG + "/api/v1/mailbox/" + prefix + "/" + id
res = HttpUtil.delete(url=url, data=None)
res_json = json.loads(res.text)
if __name__ == '__main__':
prefix = StringUtil.random_lowercase_alphanumeric(9)
suffix = lin_shi_you_xiang_suffix()
lin_shi_you_xiang_apply(prefix)
lin_shi_you_xiang_list(prefix)