Hi Oleg You can use BeautifulSoup
from BeautifulSoup import BeautifulSoup >>> html = '\r\n\r\n\r\n<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 >>> Strict//EN" >>> "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd";>\r\n\r\n<html >>> xmlns="http://www.w3.org/1999/xhtml";>\r\n <head>\r\n <meta >>> http-equiv="content-type" content="text/html; charset=utf-8" />\r\n \r\n >>> \n<title>Japanese innovation | >>> \xd0\xaf\xd0\xbf\xd0\xbe\xd0\xbd\xd0\xb8\xd1\x8f >>> \xd0\xb8\xd0\xbd\xd0\xbd\xd0\xbe\xd0\xb2\xd0\xb0\xd1\x86\xd0\xb8\xd0\xb8</title>\n\r\n >>> \n<meta name="keywords" >>> content="\xd0\xaf\xd0\xbf\xd0\xbe\xd0\xbd\xd0\xb8\xd1\x8f, >>> \xd0\xa2\xd0\xb5\xd1\x85\xd0\xbd\xd0\xbe\xd0\xbb\xd0\xbe\xd0\xb3\xd0\xb8\xd0\xb8, >>> \xd0\x98\xd0\xbd\xd0\xbd\xd0\xbe\xd0\xb2\xd0\xb0\xd1\x86\xd0\xb8\xd0\xb8, >>> \xd0\x94\xd0\xbe\xd0\xbc\xd0\xb0\xd1\x88\xd0\xbd\xd1\x8f\xd1\x8f >>> \xd1\x81\xd1\x82\xd1\x80\xd0\xb0\xd0\xbd\xd0\xb8\xd1\x86\xd0\xb0" />\n<meta >>> name="description" >>> content="\xd0\xaf\xd0\xbf\xd0\xbe\xd0\xbd\xd0\xb8\xd1\x8f, >>> \xd1\x8f\xd0\xbf\xd0\xbe\xd0\xbd\xd1\x81\xd0\xba\xd0\xb8\xd0\xb5 >>> \xd0\xb8\xd0\xbd\xd0\xbd\xd0\xbe\xd0\xb2\xd0\xb0\xd1\x86\xd0\xb8\xd0\xb8, >>> \xd1\x8f\xd0\xbf\xd0\xbe\xd0\xbd\xd1\x81\xd0\xba\xd0\xb8\xd0\xb5 >>> \xd1\x82\xd0\xb5\xd1\x85\xd0\xbd\xd0\xbe\xd0\xbb\xd0\xbe\xd0\xb3\xd0\xb8\xd0\xb8, >>> \xd0\xbd\xd0\xb0\xd1\x83\xd0\xba\xd0\xb0 >>> \xd0\xaf\xd0\xbf\xd0\xbe\xd0\xbd\xd0\xb8\xd0\xb8, >>> \xd1\x83\xd1\x87\xd0\xb5\xd0\xbd\xd0\xbd\xd1\x8b\xd0\xb5 >>> \xd0\xaf\xd0\xbf\xd0\xbe\xd0\xbd\xd0\xb8\xd1\x8f, >>> \xd0\xba\xd0\xbe\xd0\xbc\xd0\xbf\xd0\xb0\xd0\xbd\xd0\xb8\xd0\xb8 >>> \xd0\xaf\xd0\xbf\xd0\xbe\xd0\xbd\xd0\xb8\xd1\x8f, >>> \xd1\x82\xd0\xbe\xd0\xb2\xd0\xb0\xd1\x80\xd1\x8b >>> \xd0\xaf\xd0\xbf\xd0\xbe\xd0\xbd\xd0\xb8\xd1\x8f" />\n\r\n\r\n' >>> soup = BeautifulSoup(html) >>> print soup.prettify() <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" "http:// www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> <html xmlns="http://www.w3.org/1999/xhtml";> <head> <meta http-equiv="content-type" content="text/html; charset=utf-8" / > <title> Japanese innovation | Япония инновации </title> <meta name="keywords" content="Япония, Технологии, Инновации, Домашняя страница" /> <meta name="description" content="Япония, японские инновации, японские технологии, наука Японии, ученные Япония, компании Япония, товары Япония" /> </head> </html> best wishes Ray McBride On 9 Sep, 10:06, Oleg Oltar <[email protected]> wrote: > Hi! > > One of my tests returned following text () > > The test: > from django.test.client import Client > c = Client() > resp = c.get("/") > resp.content > > In [25]: resp.content > Out[25]: '\r\n\r\n\r\n<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 > Strict//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd";>\r\n\r\n<html > xmlns="http://www.w3.org/1999/xhtml";>\r\n <head>\r\n <meta > http-equiv="content-type" content="text/html; charset=utf-8" />\r\n > \r\n \n<title>Japanese innovation | > \xd0\xaf\xd0\xbf\xd0\xbe\xd0\xbd\xd0\xb8\xd1\x8f > \xd0\xb8\xd0\xbd\xd0\xbd\xd0\xbe\xd0\xb2\xd0\xb0\xd1\x86\xd0\xb8\xd0\xb8</title>\n\r\n > \n<meta name="keywords" > content="\xd0\xaf\xd0\xbf\xd0\xbe\xd0\xbd\xd0\xb8\xd1\x8f, > \xd0\xa2\xd0\xb5\xd1\x85\xd0\xbd\xd0\xbe\xd0\xbb\xd0\xbe\xd0\xb3\xd0\xb8\xd0\xb8, > \xd0\x98\xd0\xbd\xd0\xbd\xd0\xbe\xd0\xb2\xd0\xb0\xd1\x86\xd0\xb8\xd0\xb8, > \xd0\x94\xd0\xbe\xd0\xbc\xd0\xb0\xd1\x88\xd0\xbd\xd1\x8f\xd1\x8f > \xd1\x81\xd1\x82\xd1\x80\xd0\xb0\xd0\xbd\xd0\xb8\xd1\x86\xd0\xb0" />\n<meta > name="description" > content="\xd0\xaf\xd0\xbf\xd0\xbe\xd0\xbd\xd0\xb8\xd1\x8f, > \xd1\x8f\xd0\xbf\xd0\xbe\xd0\xbd\xd1\x81\xd0\xba\xd0\xb8\xd0\xb5 > \xd0\xb8\xd0\xbd\xd0\xbd\xd0\xbe\xd0\xb2\xd0\xb0\xd1\x86\xd0\xb8\xd0\xb8, > \xd1\x8f\xd0\xbf\xd0\xbe\xd0\xbd\xd1\x81\xd0\xba\xd0\xb8\xd0\xb5 > \xd1\x82\xd0\xb5\xd1\x85\xd0\xbd\xd0\xbe\xd0\xbb\xd0\xbe\xd0\xb3\xd0\xb8\xd0\xb8, > \xd0\xbd\xd0\xb0\xd1\x83\xd0\xba\xd0\xb0 > \xd0\xaf\xd0\xbf\xd0\xbe\xd0\xbd\xd0\xb8\xd0\xb8, > \xd1\x83\xd1\x87\xd0\xb5\xd0\xbd\xd0\xbd\xd1\x8b\xd0\xb5 > \xd0\xaf\xd0\xbf\xd0\xbe\xd0\xbd\xd0\xb8\xd1\x8f, > \xd0\xba\xd0\xbe\xd0\xbc\xd0\xbf\xd0\xb0\xd0\xbd\xd0\xb8\xd0\xb8 > \xd0\xaf\xd0\xbf\xd0\xbe\xd0\xbd\xd0\xb8\xd1\x8f, > \xd1\x82\xd0\xbe\xd0\xb2\xd0\xb0\xd1\x80\xd1\x8b > \xd0\xaf\xd0\xbf\xd0\xbe\xd0\xbd\xd0\xb8\xd1\x8f" />\n\r\n\r\n > > Is there a way I can convert it to normal readable text? (I need for example > to find a string of text in this response to check if my test case Pass or > failed) --~--~---------~--~----~------------~-------~--~----~ You received this message because you are subscribed to the Google Groups "Django users" group. To post to this group, send email to [email protected] To unsubscribe from this group, send email to [email protected] For more options, visit this group at http://groups.google.com/group/django-users?hl=en -~----------~----~----~----~------~----~------~--~---
