(raw_html)
| 6 | |
| 7 | |
| 8 | def cleanhtml(raw_html): |
| 9 | cleanr = re.compile("<.*?>") |
| 10 | cleantext = re.sub(cleanr, "", raw_html) |
| 11 | return ( |
| 12 | cleantext.replace("\n", " ") |
| 13 | .replace("\t", " ") |
| 14 | .replace("{", "") |
| 15 | .replace("}", "") |
| 16 | .replace("|", "") |
| 17 | .replace("<", "") |
| 18 | .replace(">", "") |
| 19 | .replace("show file signature", "") |
| 20 | .replace("[[", "") |
| 21 | .replace("]]", "") |
| 22 | .replace("web url", "") |
| 23 | .replace("cite", "") |
| 24 | .strip() |
| 25 | ) |
| 26 | |
| 27 | |
| 28 | r = requests.get( |