| Ken Russell | 67f6322 | 2016-12-18 17:50:32 -0700 | [diff] [blame] | 1 | #!/usr/bin/python |
| 2 | |
| 3 | import sys |
| 4 | import html5lib |
| 5 | |
| 6 | htmlfilename = sys.argv[1] |
| 7 | htmlfile = open(htmlfilename) |
| 8 | try: |
| 9 | doc = html5lib.parse(htmlfile, treebuilder="dom") |
| 10 | finally: |
| 11 | htmlfile.close() |
| 12 | |
| 13 | def elementHasClass(el, classArg): |
| 14 | """ |
| 15 | Return true if and only if classArg is one of the classes of el |
| 16 | """ |
| 17 | classes = [ c for c in el.getAttribute("class").split(" ") if c is not "" ] |
| 18 | return classArg in classes |
| 19 | |
| 20 | def elementTextContent(el): |
| 21 | """ |
| 22 | Implementation of DOM Core's .textContent |
| 23 | """ |
| 24 | textContent = "" |
| 25 | for child in el.childNodes: |
| 26 | if child.nodeType == 3: # Node.TEXT_NODE |
| 27 | textContent += child.data |
| 28 | elif child.nodeType == 1: # Node.ELEMENT_NODE |
| 29 | textContent += elementTextContent(child) |
| 30 | else: |
| 31 | # Other nodes are ignored |
| 32 | pass |
| 33 | return textContent |
| 34 | |
| 35 | preList = doc.getElementsByTagName("pre") |
| 36 | idlList = [elementTextContent(p) for p in preList if elementHasClass(p, "idl") ] |
| 37 | print "\n\n".join(idlList) |