Class Wikia

pattern/web/__init__.py:1981–2035

# Author: Robert Elwell (2012)

class Wikia(MediaWiki):

    def __init__(self, domain="www", license=None, throttle=5.0, language="en"):
        """ Mediawiki search engine for http://[domain].wikia.com.
        """
        SearchEngine.__init__(self, license or MEDIAWIKI_LICENSE, throttle, language)
        self._subdomain = domain

    @property
    def _url(self):
        s = MEDIAWIKI
        s = s.replace("{SUBDOMAIN}", self._subdomain)
        s = s.replace("{DOMAIN}", "wikia.com")
        s = s.replace("{API}", '/api.php')
        return s

    @property
    def MediaWikiArticle(self):
        return WikiaArticle
    @property
    def MediaWikiSection(self):
        return WikiaSection
    @property
    def MediaWikiTable(self):
        return WikiaTable

    def all(self, **kwargs):
        if kwargs.pop("batch", True):
            # We can take advantage of Wikia's search API to reduce bandwith.
            # Instead of executing a query to retrieve each article,
            # we query for a batch of (10) articles.
            iterator = self.list(_id="pageid", **kwargs)
            while True:
                batch, done = [], False
                try:
                    for i in range(10): batch.append(iterator.next())
                except StopIteration:
                    done = True # No more articles, finish batch and raise StopIteration.
                url = URL(self._url.replace("api.php", "wikia.php"), method=GET, query={
                  "controller": "WikiaSearch",
                      "method": "getPages",
                         "ids": '|'.join(str(id) for id in batch),
                      "format": "json"
                })
                kwargs.setdefault("unicode", True)
                kwargs.setdefault("cached", True)
                kwargs["timeout"] = 10 * (1 + len(batch))
                data = url.download(**kwargs)
                data = json.loads(data)
                for x in (data or {}).get("pages", {}).values():
                    yield WikiaArticle(title=x.get("title", ""), source=x.get("html", ""))
                if done:
                    raise StopIteration
        for title in self.list(**kwargs):
            yield self.search(title, **kwargs)

class WikiaArticle(MediaWikiArticle):
    def __repr__(self):