Search code examples
pythonxmllxmlelementtreewiki

Extract Wikipedia Data From XML Data dumps


I have been trying to extract the text from some Wikipedia dumps. I need to get the text from the id, title, ns, timestamp, username, ip, and text tags in the full-history English Wikipedia dump.

I read and modified the code from https://www.heatonresearch.com/2017/03/03/python-basic-wikipedia-parsing.html.

I was able to write the code below:

import xml.etree.ElementTree as etree
import codecs
import csv
import time
import os

PATH_WIKI_XML = '/home/wikipedia'
FILENAME_WIKI = 'enwiki-latest-pages-meta-history1.xml-p24706p25444'
FILENAME_ARTICLES = 'articles.csv'
FILENAME_TEMPLATE = 'articles_template.csv'
ENCODING = "utf-8"


def hms_string(sec_elapsed):
    h = int(sec_elapsed / (60 * 60))
    m = int((sec_elapsed % (60 * 60)) / 60)
    s = sec_elapsed % 60
    return "{}:{:>02}:{:>05.2f}".format(h, m, s)


def strip_tag_name(t):
    t = elem.tag
    idx = k = t.rfind("}")
    if idx != -1:
        t = t[idx + 1:]
    return t


pathWikiXML = os.path.join(PATH_WIKI_XML, FILENAME_WIKI)
pathArticles = os.path.join(PATH_WIKI_XML, FILENAME_ARTICLES)
pathTemplateRedirect = os.path.join(PATH_WIKI_XML, FILENAME_TEMPLATE)

totalCount = 0
articleCount = 0
templateCount = 0
title = None
timestamp= None
username= None
ip= None
text=None
start_time = time.time()

with codecs.open(pathArticles, "w", ENCODING) as articlesFH, \
        codecs.open(pathTemplateRedirect, "w", ENCODING) as templateFH:
    
    articlesWriter = csv.writer(articlesFH, quoting=csv.QUOTE_MINIMAL)
    templateWriter = csv.writer(templateFH, quoting=csv.QUOTE_MINIMAL)

    articlesWriter.writerow(['id', 'title', 'timestamp','username','ip','text'])
    templateWriter.writerow(['id', 'title'])

    for event, elem in etree.iterparse(pathWikiXML, events=('start', 'end')):
        tname = strip_tag_name(elem.tag)

        if event == 'start':
            if tname == 'page':
                title = ''
                id = -1
                inrevision = False
                incontributor= False
                ns = 0
            elif tname == 'revision':
                # Do not pick up on revision id's
                inrevision = True
            elif tname == 'contributor':
                incontributor = True
        else:
            if tname == 'title':
                title = elem.text
            elif tname == 'id' and not inrevision and not incontributor:
                id = int(elem.text)
            elif tname == 'ns':
                ns = int(elem.text)
            elif tname == 'timestamp':
                timestamp = int(elem.text)
            elif tname == 'username':
                username = elem.text
            elif tname == 'ip':
                ip = elem.text
            elif tname == 'text':
                text = elem.text
                                                                              
            elif tname == 'page':
                totalCount += 1

                if ns == 10:
                    templateCount += 1
                    templateWriter.writerow([id, title])
                elif len(title) > 0:
                    articleCount += 1
                    articlesWriter.writerow(['id', 'title', 'timestamp','username','ip','text'])

                # if totalCount > 100000:
                #  break

                if totalCount > 1 and (totalCount % 100000) == 0:
                    print("{:,}".format(totalCount))

            elem.clear()

elapsed_time = time.time() - start_time

print("Total pages: {:,}".format(totalCount))
print("Template pages: {:,}".format(templateCount))
print("Article pages: {:,}".format(articleCount))
print("Elapsed time: {}".format(hms_string(elapsed_time)))

However, the resulting csv file only had the id and the title. The other columns were empty and I guess its because the timestamp tag is nested within the revision tag but my event only deals with start and end of the page tag. username and IP are also nested in the contributor tag as seen in the sample XML file below. Can someone advise me how I can solve this? Should I loop events within events to extract the text from the desired nested tags? Is there a code that can work for me here? The desired output is a file with the desired tags as headers and the text in rows. Remember, one page can have many revisions and different meta data for each revision. I want to get all the text from the desired tags as well as the metadata within a page and after I have everything from that page, proceed to the next page. Thanks.

<mediawiki xmlns="http://www.mediawiki.org/xml/export-0.10/" 
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" 
xsi:schemaLocation="http://www.mediawiki.org/xml/export-0.10/ 
http://www.mediawiki.org/xml/export-0.10.xsd" version="0.10" xml:lang="sco">
  <siteinfo>
    <sitename>Wikipedia</sitename>
    <dbname>scowiki</dbname>
    <base>http://sco.wikipedia.org/wiki/Main_Page</base>
    <generator>MediaWiki 1.25wmf12</generator>
    <case>first-letter</case>
    <namespaces>
      <namespace key="-2" case="first-letter">Media</namespace>
      <namespace key="-1" case="first-letter">Special</namespace>
      <namespace key="0" case="first-letter" />
      <namespace key="1" case="first-letter">Talk</namespace>
      <namespace key="2" case="first-letter">User</namespace>
      <namespace key="3" case="first-letter">User talk</namespace>
      <namespace key="4" case="first-letter">Wikipedia</namespace>
      <namespace key="5" case="first-letter">Wikipedia talk</namespace>
      <namespace key="6" case="first-letter">File</namespace>
      <namespace key="7" case="first-letter">File talk</namespace>
      <namespace key="8" case="first-letter">MediaWiki</namespace>
      <namespace key="9" case="first-letter">MediaWiki talk</namespace>
      <namespace key="10" case="first-letter">Template</namespace>
      <namespace key="11" case="first-letter">Template talk</namespace>
      <namespace key="12" case="first-letter">Help</namespace>
      <namespace key="13" case="first-letter">Help talk</namespace>
      <namespace key="14" case="first-letter">Category</namespace>
      <namespace key="15" case="first-letter">Category talk</namespace>
      <namespace key="100" case="first-letter">Portal</namespace>
      <namespace key="101" case="first-letter">Portal talk</namespace>
      <namespace key="828" case="first-letter">Module</namespace>
      <namespace key="829" case="first-letter">Module talk</namespace>
    </namespaces>
  </siteinfo>
  <page>
    <title>Inglis leid</title>
    <ns>0</ns>
    <id>2</id>
    <revision>
      <id>7</id>
      <timestamp>2005-06-22T10:17:05Z</timestamp>
      <contributor>
        <ip>24.251.198.251</ip>
      </contributor>
      <model>wikitext</model>
      <format>text/x-wiki</format>
      <text xml:space="preserve">Tha '''Inglis''' (English) leid is a west [[Gairmanic leid]] at cam frae Ingland an thats forebear wis [[auld Inglis]]. Tha name &quot;English&quot; cams frae tha pairt o [[Gairmanie]] caw'd &quot;Angeln&quot;. Inglis is tha waruld's seicont maist widelie spaken first leid, an his aboot 340 million hameborn speikers waruldwide.

[[en:English language]]</text>
      <sha1>6m5yxiaalrm6te7e3x3fiw1aq7wk9ir</sha1>
    </revision>
  </page>
</mediawiki>

Solution

  • Updated

    After reading your comments below, you should definitely aim to break up the really big things into the smallest possible things, then process the smallest things in turn:

    • In the first stage, take any number of huge XML files with many pages and produce many small XMLs with a single page.

    • In the second stage, iterate each page-file, extracting the data, and writing your CSV.

    This will take longer, but:

    • It's more fault tolerant: if you hit an error and the thing breaks you can fix the error and pick up where you left off
    • It'll be far easier to diagnose errors when you can cleanly divide them into the categories "something is wrong with making the big thing smaller" and "something is wrong with extracting data from the small thing".

    This will be especially true with terabytes of data: there's no way you want to try and get that in a single pass.

    Stage 1

    #!/usr/bin/env python3
    import xml.etree.ElementTree as ET
    
    NS = {'xmlns': 'http://www.mediawiki.org/xml/export-0.10/'}
    
    strip_ns = lambda t: t.split('}')[1] if '}' in t else t
    
    # Open XML for input, and iterate
    xml_f = open('big.xml')
    for (event, elem) in ET.iterparse(xml_f, events=['start', 'end']):
        tag_name = strip_ns(elem.tag)
    
        if event == 'start' and tag_name == 'page':
            pg_title = elem.find('xmlns:title', NS).text.replace(' ', '_')
            pg_ns = elem.find('xmlns:ns', NS).text
            pg_id = elem.find('xmlns:id', NS).text
    
            xml_pg_fname = f'{pg_title}_{pg_ns}_{pg_id}.xml'  # e.g., Inglis_leid_0_2.xml
            xml_byte_str = ET.tostring(elem, encoding='utf-8', default_namespace=NS['xmlns'])  # definitely use default_namespace
    
            with open(xml_pg_fname, 'wb') as f_out:
                f_out.write(xml_byte_str)
    
    
    # Close big
    xml_f.close()
    

    Stage 2

    Now you can easily and safely use XPath to get at the data.

    #!/usr/bin/env python3
    import csv
    import xml.etree.ElementTree as ET
    
    # Set up the namespace that needs to be a part of every XPath query
    ns_dict = {'xmlns': 'http://www.mediawiki.org/xml/export-0.10/'}
    
    # Open a file and parse it
    page = ET.parse('Inglis_leid_0_2.xml')
    
    # With the page "element", find its direct children (always using `xmlns:` and passing `ns_dict`)
    # `./xmlns:<element>` means "find, from here (at page), the element that's only 1 level (directly) under page"
    
    pg_title = page.find('./xmlns:title', ns_dict)
    pg_ns = page.find('./xmlns:ns', ns_dict)
    pg_id = page.find('./xmlns:id', ns_dict)
    
    # Get the revision element
    revision = page.find('./xmlns:revision', ns_dict)
    
    rev_id = revision.find('./xmlns:id', ns_dict)
    rev_ts = revision.find('./xmlns:timestamp', ns_dict)
    
    # Find ip under contributor
    contrib_ip = revision.find('./xmlns:contributor/xmlns:ip', ns_dict)
    
    print('page title:', pg_title.text)
    print('page id:', pg_id.text)
    print('rev id:', rev_id.text)
    print('rev timestamp:', rev_ts.text)
    print('contributor ip:', contrib_ip.text)
    
    # From here, write out to a CSV
    with open('out.csv', 'w', newline='') as f:
        writer = csv.writer(f)
        writer.writerow(['Page title', 'Page id', 'Rev id', 'Rev timestamp', 'Contributor ip'])
        writer.writerow([pg_title.text, pg_id.text, pg_ns.text, rev_id.text, rev_ts.text, contrib_ip.text])