我试图通过正则表达式传递大量的随机html字符串,我的Python 2.6脚本对此感到窒息：
原文链接：https://www.f2er.com/regex/357310.htmlUnicodeEncodeError：’ascii’编解码器无法编码字符
我在这个词的末尾追溯到一个商标上标：Protection™ – 我不需要捕获非ascii的东西,但这是一个麻烦,我希望将来会更多地遇到它.
是否有处理非ascii字符的模块？或者,在python中处理/转义非ascii内容的最佳方法是什么？
谢谢！
完整错误：
E
======================================================================
ERROR: test_untitled (__main__.Untitled)
----------------------------------------------------------------------
Traceback (most recent call last):
File "C:\Python26\Test2.py",line 26,in test_untitled
ofile.write(Test + '\n')
UnicodeEncodeError: 'ascii' codec can't encode character u'\u2122' in position 1005: ordinal not in range(128)
完整脚本：
from selenium import selenium
import unittest,time,re,csv,logging
class Untitled(unittest.TestCase):
def setUp(self):
self.verificationErrors = []
self.selenium = selenium("localhost",4444,"*firefox","http://www.BaseDomain.com/")
self.selenium.start()
self.selenium.set_timeout("90000")
def test_untitled(self):
sel = self.selenium
spamReader = csv.reader(open('SubDomainList.csv','rb'))
for row in spamReader:
sel.open(row[0])
time.sleep(10)
Test = sel.get_text("//html/body/div/table/tbody/tr/td/form/div/table/tbody/tr[7]/td")
Test = Test.replace(",","")
Test = Test.replace("\n","")
ofile = open('TestOut.csv','ab')
ofile.write(Test + '\n')
ofile.close()
def tearDown(self):
self.selenium.stop()
self.assertEqual([],self.verificationErrors)
if __name__ == "__main__":
unittest.main()
