mediawiki_dump_tools/Mediawiki-Utilities/examples/xml_dump.iteration.py

   1 """
   2 Prints out all rev_ids that appear in dump.xml.
   3 """
   4 from mw.xml_dump import Iterator
   5
   6 # Construct dump file iterator
   7 dump = Iterator.from_file(open("examples/dump.xml"))
   8
   9 # Iterate through pages
  10 for page in dump:
  11
  12         # Iterate through a page's revisions
  13         for revision in page:
  14                 print(revision.id)