fork download
  1. html = '''
  2. <tr bgcolor="#CCCCCC">
  3. <td colspan="2"><font color="#000000" face="Verdana, Arial, Helvetica, sans-serif" size="1"><span class="txt_arial_8pt_black">1º
  4.  
  5. Período Ideal</span></font></td>
  6. <td><font color="#000000" face="Verdana, Arial, Helvetica, sans-serif" size="1"><span class="txt_arial_8pt_black">Créd.<br/>
  7.  
  8. Aula</span></font></td>
  9. <td><font color="#000000" face="Verdana, Arial, Helvetica, sans-serif" size="1"><span class="txt_arial_8pt_black">Créd.<br/>
  10.  
  11. Trab.</span></font></td>
  12. <td align="center"><font color="#000000" face="Verdana, Arial, Helvetica, sans-serif" size="1"><span class="txt_arial_8pt_black">CH</span></font></td>
  13. <td align="center" width="6%"><font color="#000000" face="Verdana, Arial, Helvetica, sans-serif" size="1"><span class="txt_arial_8pt_black">CE</span></font></td>
  14. <td align="center" width="6%"><font color="#000000" face="Verdana, Arial, Helvetica, sans-serif" size="1"><span class="txt_arial_8pt_black">CP</span></font></td>
  15. <td align="center" width="6%"><font color="#000000" face="Verdana, Arial, Helvetica, sans-serif" size="1"><span class="txt_arial_8pt_black">ATPA</span></font></td>
  16. </tr>'''
  17.  
  18. import re
  19. print('DOTALL - acha todos')
  20. for texto in re.findall(r'<span class="txt_arial_8pt_black">(.*?)</span>', html, re.DOTALL):
  21. print(texto)
  22.  
  23. print('MULTILINE - nao acha todos')
  24. for texto in re.findall(r'<span class="txt_arial_8pt_black">(.*?)</span>', html, re.MULTILINE):
  25. print(texto)
  26.  
Success #stdin #stdout 0.03s 9556KB
stdin
Standard input is empty
stdout
DOTALL - acha todos
1º 

                          Período Ideal
Créd.<br/>

                          Aula
Créd.<br/>

                          Trab.
CH
CE
CP
ATPA
MULTILINE - nao acha todos
CH
CE
CP
ATPA