def addArticle( self, title, revision=None, wikidb=None, imagedb=None, ): """Add article with given title and revision to ZIP file. This will add all referenced templates and images, too. @param title: article title @type title: unicode @param revision: article revision (optional) @type revision: int @param wikidb: WikiDB to use @param imagedb: ImageDB to use (optional) """ if title in self.articles: return self.articles[title] = {} self.status(article=title) recorddb = RecordDB(wikidb, self.articles, self.templates, self.sources) raw = recorddb.getRawArticle(title, revision=revision) if raw is None: log.warn('Could not get article %r' % title) return mo = self.redirect_rex.search(raw) if mo: raw = recorddb.getRawArticle(mo.group('redirect')) if raw is None: log.warn('Could not get redirected article %r (from %r)' % (mo.group('redirect'), title)) return self.parseArticle( title, revision=revision, raw=raw, wikidb=wikidb, imagedb=imagedb, ) self.article_count += 1 if self.num_articles: self.status(progress=self.article_count * 100 // self.num_articles)
def fetch_article_job(job_id): recorddb = RecordDB(wikidb, self.articles, self.templates, self.sources) raw = recorddb.getRawArticle(title, revision=revision) if raw is None: log.warn('Could not get article %r' % title) return mo = self.redirect_rex.search(raw) if mo: raw = recorddb.getRawArticle(mo.group('redirect')) if raw is None: log.warn('Could not get redirected article %r (from %r)' % (mo.group('redirect'), title)) return
def fetch_article_job(job_id): recorddb = RecordDB(wikidb, self.articles, self.templates, self.sources) raw = recorddb.getRawArticle(title, revision=revision) if raw is None: log.warn('Could not get article %r' % title) return mo = self.redirect_rex.search(raw) if mo: raw = recorddb.getRawArticle(mo.group('redirect')) if raw is None: log.warn('Could not get redirected article %r (from %r)' % ( mo.group('redirect'), title )) return
def addArticle(self, title, revision=None, wikidb=None, imagedb=None, ): """Add article with given title and revision to ZIP file. This will add all referenced templates and images, too. @param title: article title @type title: unicode @param revision: article revision (optional) @type revision: int @param wikidb: WikiDB to use @param imagedb: ImageDB to use (optional) """ if title in self.articles: return self.articles[title] = {} self.status(article=title) recorddb = RecordDB(wikidb, self.articles, self.templates, self.sources) raw = recorddb.getRawArticle(title, revision=revision) if raw is None: log.warn('Could not get article %r' % title) return mo = self.redirect_rex.search(raw) if mo: raw = recorddb.getRawArticle(mo.group('redirect')) if raw is None: log.warn('Could not get redirected article %r (from %r)' % ( mo.group('redirect'), title )) return self.parseArticle(title, revision=revision, raw=raw, wikidb=wikidb, imagedb=imagedb, ) self.article_count += 1 if self.num_articles: self.status(progress=self.article_count*100//self.num_articles)
def fetch_article_job(job_id): if self.fetcharticle_status: self.fetcharticle_status(article=title) recorddb = RecordDB(wikidb, self.articles, self.templates, self.sources) raw = recorddb.getRawArticle(title, revision=revision) if raw is None: log.warn('Could not get article %r' % title) else: mo = self.redirect_rex.search(raw) if mo: raw = recorddb.getRawArticle(mo.group('redirect')) if raw is None: log.warn('Could not get redirected article %r (from %r)' % ( mo.group('redirect'), title )) self.article_count += 1 if self.fetcharticle_status: self.fetcharticle_status(progress=self.article_count*100/self.num_articles)