示例#1
0
    def copy(
        self,
        src_item: ItemPage,
        dest_item: ItemPage,
        props: Iterable[wp.WikidataProperty],
    ):
        """Copy properties from the source item to the destination item

            Returns a tuple of (successes, failures)
        """
        src_item.get()
        dest_item.get()

        failures = 0
        successes = 0

        for prop in props:
            if prop.pid not in src_item.claims:
                print(f"{prop} not found in {src_item.title()}")
                failures += 1
                continue

            src_claims = src_item.claims[prop.pid]
            if len(src_claims) > 1:
                copy_multiple = click.confirm(
                    f"There are {len(src_claims)} values for {prop}. Are you sure you want to copy all of them?"
                )
                # copy_multiple = False
                if not copy_multiple:
                    print(
                        f"Cannot copy {prop} from {format(src_item)} to {format(dest_item)}. Only scalar properties can be copied"
                    )
                    failures += 1
                    continue

            if prop.pid in dest_item.claims:
                print(f"{prop} already has a value in {format(dest_item)}")
                failures += 1
                continue

            targets = [claim.getTarget() for claim in src_claims]

            for target in targets:
                if hasattr(target, "get"):
                    target.get()

                target_str = printable_target_value(target)

                print(
                    f"Copying {prop}={target_str} from {format(src_item)} to {format(dest_item)}"
                )

                new_claim = Claim(self.repo, prop.pid)
                new_claim.setTarget(target)
                dest_item.addClaim(
                    new_claim, summary=f"Setting {prop.pid} ({prop.name})"
                )
                successes += 1
        return (successes, failures)
def main(dry=False):
    dry_str = ""
    if dry:
        print("Running in dry-run mode, will not implement any changes")
        dry_str = "[DRY-RUN MODE] "
    repo = Site().data_repository()
    for episode_id, title, series_label in episodes_with_titles_and_missing_labels(
    ):
        print(f"{dry_str}Fixing {series_label}:{title} ({episode_id})")
        if not dry:
            episode_item = ItemPage(repo, episode_id)
            episode_item.get()
            episode_item.editLabels({"en": title})
示例#3
0
def create_seasons(series_id,
                   number_of_seasons,
                   quickstatements=False,
                   dry=False):
    series_title = ItemPage(Site().data_repository(), series_id)
    series_title.get(force=True)
    series_label = series_title.labels['en']
    for i in range(1, number_of_seasons + 1):
        label = f"{series_label}, season {i}"
        descr = f"season {i} of {series_label}"
        if quickstatements:
            create_season_quickstatements(series_id, label, descr, i)
        else:
            create_season(series_id, label, descr, i, dry)
示例#4
0
def main(dry=False):
    dry_str = ""
    if dry:
        print("Running in dry-run mode, will not implement any changes")
        dry_str = "[DRY-RUN MODE] "
    repo = Site().data_repository()
    for movie_id, title in movies_with_missing_labels_with_title():
        print(
            f"{dry_str}Setting label='{title}' for {movie_id} ( https://www.wikidata.org/wiki/{movie_id} )"
        )
        if not dry:
            movie_item = ItemPage(repo, movie_id)
            movie_item.get()
            movie_item.editLabels({"en": title})
    def setUpClass(cls):
        """Set up test class."""
        super(TestIsbnWikibaseBot, cls).setUpClass()

        # Check if the unit test item page and the property both exist
        item_ns = cls.get_repo().item_namespace
        for page in cls.get_site().search('IsbnWikibaseBotUnitTest',
                                          total=1,
                                          namespaces=item_ns):
            cls.test_page_qid = page.title()
            item_page = ItemPage(cls.get_repo(), page.title())
            for pid, claims in item_page.get()['claims'].items():
                for claim in claims:
                    prop_page = pywikibot.PropertyPage(cls.get_repo(),
                                                       claim.getID())
                    prop_page.get()
                    if ('ISBN-10' in prop_page.labels.values()
                            and claim.getTarget() == '097522980x'):
                        return
            raise unittest.SkipTest(u'%s: "ISBN-10" property was not found in '
                                    u'"IsbnWikibaseBotUnitTest" item page' %
                                    cls.__name__)
        raise unittest.SkipTest(
            u'%s: "IsbnWikibaseBotUnitTest" item page was not found' %
            cls.__name__)
示例#6
0
def main(dry=False):
    dry_str = ""
    if dry:
        print("Running in dry-run mode, will not implement any changes")
        dry_str = "[DRY-RUN MODE] "
    repo = Site().data_repository()
    for movie_id, movie_label in movies_with_missing_titles():
        print(
            f"{dry_str}Setting title='{movie_label}' for {movie_id} ( https://www.wikidata.org/wiki/{movie_id} )"
        )
        if not dry:
            movie_item = ItemPage(repo, movie_id)
            movie_item.get()
            claim = Claim(repo, wp.TITLE.pid)
            claim.setTarget(WbMonolingualText(movie_label, "en"))
            movie_item.addClaim(claim)
示例#7
0
    def get_typed_item(self, item_id: str) -> api.BaseType:
        item_page = ItemPage(self.repo, item_id)
        item_page.get()
        if INSTANCE_OF.pid not in item_page.claims:
            raise ValueError(f"{item_id} has no 'instance of' property")

        claims = item_page.claims[INSTANCE_OF.pid]
        instance_ids = {claim.getTarget().id for claim in claims}
        if TELEVISION_SERIES_EPISODE in instance_ids:
            return Episode(item_page, self.repo)
        if TELEVISION_SERIES_SEASON in instance_ids:
            return Season(item_page, self.repo)
        if TELEVISION_SERIES in instance_ids or ANIMATED_SERIES in instance_ids:
            return Series(item_page, self.repo)

        raise ValueError(f"Unsupported item with instance QIDs {instance_ids}")
示例#8
0
def create_seasons(series_id,
                   number_of_seasons,
                   quickstatements=False,
                   dry=False):
    """Creates multiple season items on WikiData

    Arguments
    ---------
    series_id: str
        The Wiki ID of the series ItemPage
    number_of_seasons: int
        The number of season to create for this series
    quickstatements: bool
        if True, simply print out a list of quickstatements.
        if False, then create the items on WikiData directly
    dry: bool
        Whether or not this function should run in dry-run mode.
        In dry-run mode, no real changes are made to WikiData, they are only
        logged to stdout.

    Returns
    -------
    season_ids: List[str]
        The Wiki IDs of the seasons that were created
    """
    series_title = ItemPage(Site().data_repository(), series_id)
    series_title.get(force=True)
    series_label = series_title.labels['en']
    season_ids = []
    for i in tqdm(range(1, number_of_seasons + 1)):
        label = f"{series_label}, season {i}"
        descr = f"season {i} of {series_label}"
        if quickstatements:
            create_season_quickstatements(series_id, label, descr, i)
        else:
            season_id = create_season(series_id, label, descr, i, dry)
            season_ids.append(season_id)

    return season_ids
示例#9
0
def copy_delayed(
    src_item: ItemPage, dest_item: ItemPage, props: Iterable[wp.WikidataProperty]
) -> Iterable[api.Fix]:
    repo = Site().data_repository()

    src_item.get()
    dest_item.get()

    claims = []

    for prop in props:
        src_claims = src_item.claims.get(prop.pid, [])

        if len(src_claims) > 1:
            print(
                f"Cannot copy {prop} from {format(src_item)} to {format(dest_item)}. Only scalar properties can be copied"
            )
            continue

        if prop.pid in dest_item.claims:
            print(f"{prop} already has a value in {format(dest_item)}")
            continue

        targets = [claim.getTarget() for claim in src_claims]

        for target in targets:
            target.get()

            target_str = printable_target_value(target)

            print(
                f"Creating claim to copy {prop}={target_str} from {format(src_item)} to {format(dest_item)}"
            )

            new_claim = Claim(repo, prop.pid)
            new_claim.setTarget(target)
            summary = f"Setting {prop.pid} ({prop.name})"
            claims.append(api.ClaimFix(new_claim, summary, dest_item))
    return claims
示例#10
0
def main(dry=False):
    dry_str = ""
    if dry:
        print("Running in dry-run mode, will not implement any changes")
        dry_str = "[DRY-RUN MODE] "
    repo = Site().data_repository()
    for item_link, item_id, title in items_with_missing_labels_with_title():
        print(
            f"{dry_str} ( {str(item_link).ljust(40, ' ')} ) Fixing {str(item_id).ljust(9, ' ')}: {title}"
        )
        if dry:
            continue

        # Labels have a character limit, so ignore if trying to add it will result in an error
        if len(title) >= 250:
            continue

        item = ItemPage(repo, item_id)
        item.get()
        try:
            item.editLabels({"en": title})
        except (APIError, OtherPageSaveError) as e:
            print(f"An error occurred while adding label for {item_id}: {e}")
def main(dry=False):
    dry_str = ""
    if dry:
        print("Running in dry-run mode, will not implement any changes")
        dry_str = "[DRY-RUN MODE] "
    repo = Site().data_repository()
    seen = set()
    for board_game_id, bgg_id in board_games_with_missing_labels():
        if board_game_id in seen:
            continue
        seen.add(board_game_id)
        board_game_name = utils.bgg_title(bgg_id)
        if board_game_name is None:
            print(f"Unable to fetch name for {board_game_id}.")
            continue
        wiki_url = f"https://www.wikidata.org/wiki/{board_game_id}"
        print(
            f"{dry_str}Setting label='{board_game_name}' for {board_game_id} ( {wiki_url} )"
        )
        if not dry:
            bg_item = ItemPage(repo, board_game_id)
            bg_item.get()
            bg_item.editLabels({"en": board_game_name})
示例#12
0
    def setUpClass(cls):
        """Set up test class."""
        super(TestIsbnWikibaseBot, cls).setUpClass()

        # Check if the unit test item page and the property both exist
        item_ns = cls.get_repo().item_namespace
        for page in cls.get_site().search("IsbnWikibaseBotUnitTest", step=1, total=1, namespaces=item_ns):
            cls.test_page_qid = page.title()
            item_page = ItemPage(cls.get_repo(), page.title())
            for pid, claims in item_page.get()["claims"].items():
                for claim in claims:
                    prop_page = pywikibot.PropertyPage(cls.get_repo(), claim.getID())
                    prop_page.get()
                    if "ISBN-10" in prop_page.labels.values() and claim.getTarget() == "097522980x":
                        return
            raise unittest.SkipTest(
                '%s: "ISBN-10" property was not found in ' '"IsbnWikibaseBotUnitTest" item page' % cls.__name__
            )
        raise unittest.SkipTest('%s: "IsbnWikibaseBotUnitTest" item page was not found' % cls.__name__)
示例#13
0
import daty
from pprint import pprint
from pywikibot import Site, ItemPage

site = Site('wikidata', 'wikidata')
repo = site.data_repository()

item_page = ItemPage(repo, 'Q4115189')
data = item_page.get()

target_page = ItemPage(repo, 'Q17')

for P in data['claims']:
    for c in data['claims'][P]:
        if hasattr(c, 'qualifiers'):
            #print(c.qualifiers)
            if 'P710' in c.qualifiers:
                for q in c.qualifiers['P710']:
                    print(q.hash)
                    q.setTarget(target_page)
                    print(q.hash)
                    repo.editQualifier(c, q)
                    #q.changeTarget(target_page)
                    #print(q)

#del item_page
#print(data)

#data['descriptions']['it'] = "LE MIE MANI SONO INCREDIBILI"

#for p in data['claims']:
示例#14
0
def update_wikidata(project: Project, edit_group_hash: str):
    """ Update wikidata entry with data from github """
    # Wikidata boilerplate
    wikidata = Settings.wikidata_repo
    q_value = project.project.replace("http://www.wikidata.org/entity/", "")
    item = ItemPage(wikidata, title=q_value)
    item.get()

    url_raw = project.repo
    url_normalized = str(normalize_url(url_raw))
    if Settings.normalize_repo_url:
        normalize_repo_url(item, url_normalized, url_raw, q_value,
                           edit_group_hash)

    set_website(item, project, url_normalized, edit_group_hash)
    set_license(item, project, url_normalized, edit_group_hash)

    # Add all stable releases
    stable_releases = project.stable_release
    stable_releases.sort(
        key=lambda x: LooseVersion(re.sub(r"[^0-9.]", "", x.version)))

    if len(stable_releases) == 0:
        logger.info("No stable releases")
        return

    versions = [i.version for i in stable_releases]
    if len(versions) != len(set(versions)):
        duplicates = [
            release for release in stable_releases
            if versions.count(release.version) > 1
        ]
        logger.warning("There are duplicate releases in {}: {}".format(
            q_value, duplicates))
        return

    latest_version: Optional[str] = stable_releases[-1].version

    existing_versions = item.claims.get(Properties.software_version, [])
    github_version_names = [i.version for i in stable_releases]

    for i in existing_versions:
        if i.getRank() == "preferred" and i.getTarget(
        ) not in github_version_names:
            logger.warning(
                "There's a preferred rank for {} for a version which is not in the github page: {}"
                .format(q_value, i.getTarget()))
            latest_version = None

    if len(stable_releases) > 100:
        logger.warning("Limiting {} to 100 of {} stable releases".format(
            q_value, len(stable_releases)))
        stable_releases = stable_releases[-100:]
    else:
        logger.info("There are {} stable releases".format(
            len(stable_releases)))

    for release in stable_releases:
        claim, created = get_or_create_claim(item, Properties.software_version,
                                             release.version, edit_group_hash)
        if created:
            logger.info("Added '{}'".format(release.version))

        # Assumption: A preexisting publication date is more reliable than the one from github
        date_p = Properties.publication_date
        if date_p not in claim.qualifiers:
            get_or_create_qualifiers(claim, date_p, release.date,
                                     edit_group_hash)

        title = "Release %s" % release.version
        get_or_create_sources(claim, release.page, project.retrieved,
                              edit_group_hash, title, release.date)

        # Give the latest release the preferred rank
        # And work around a bug in pywikibot
        try:
            set_claim_rank(claim, latest_version, release, edit_group_hash)
        except AssertionError:
            logger.warning(
                f"Using the fallback for setting the preferred rank of {q_value}"
            )

            item.get(force=True)

            claim, created = get_or_create_claim(item,
                                                 Properties.software_version,
                                                 release.version,
                                                 edit_group_hash)
            assert not created
            set_claim_rank(claim, latest_version, release, edit_group_hash)
示例#15
0
def create_episode(series_id, season_id, title, series_ordinal, season_ordinal,
                   dry):
    """Creates a season item on WikiData

    Arguments
    ---------
    series_id: str
        The Wiki ID of the series ItemPage
    season_id: str
        The Wiki ID of the season ItemPage
    title: str
        The title of this episode. This is used to set the label.
    series_ordinal: int
        The ordinal of this episode, within the series
    season_ordinal: int
        The ordinal of this episode, within the season
    dry: bool
        Whether or not this function should run in dry-run mode.
        In dry-run mode, no real changes are made to WikiData, they are only
        logged to stdout.

    Returns
    -------
    episode_id: str
        The Wiki ID of the episode item
    """
    dry_str = "[DRY-RUN] " if dry else ""
    print(f"{dry_str}Creating episode with label='{title}'")

    episode = None
    if not dry:
        repoutil = RepoUtils(Site().data_repository())

        season = ItemPage(repoutil.repo, season_id)
        season.get()

        # Check if season has part_of_the_series set to series_id
        if wp.PART_OF_THE_SERIES.pid not in season.claims:
            raise ValueError(
                f"The season {season_id} does not have a PART_OF_THE_SERIES ({wp.PART_OF_THE_SERIES.pid} property). Check the input series and season IDs for correctness."
            )
        actual_series_id = str(
            season.claims[wp.PART_OF_THE_SERIES.pid][0].getTarget().getID())
        if actual_series_id != series_id:
            raise ValueError(
                f"The season {season_id} has PART_OF_THE_SERIES={actual_series_id} but expected={series_id}. Check the input series and season IDs for correctness."
            )

        episode = ItemPage(repoutil.repo)

        episode.editLabels({"en": title}, summary="Setting label")
        print(f"Created a new Item: {episode.getID()}")

    print(f"{dry_str}Setting {wp.INSTANCE_OF}={wp.TELEVISION_SERIES_EPISODE}")
    if not dry:
        instance_claim = repoutil.new_claim(wp.INSTANCE_OF.pid)
        instance_claim.setTarget(
            ItemPage(repoutil.repo, wp.TELEVISION_SERIES_EPISODE))
        episode.addClaim(instance_claim,
                         summary=f"Setting {wp.INSTANCE_OF.pid}")

    print(
        f"{dry_str}Setting {wp.PART_OF_THE_SERIES}={series_id}, with {wp.SERIES_ORDINAL}={series_ordinal}"
    )
    if not dry:
        series_claim = repoutil.new_claim(wp.PART_OF_THE_SERIES.pid)
        series_claim.setTarget(ItemPage(repoutil.repo, series_id))

        series_ordinal_claim = repoutil.new_claim(wp.SERIES_ORDINAL.pid)
        series_ordinal_claim.setTarget(series_ordinal)
        series_claim.addQualifier(series_ordinal_claim)

        episode.addClaim(series_claim,
                         summary=f"Setting {wp.PART_OF_THE_SERIES.pid}")

    print(
        f"{dry_str}Setting {wp.SEASON}={season_id}, with {wp.SERIES_ORDINAL}={season_ordinal}"
    )
    if not dry:
        season_claim = repoutil.new_claim(wp.SEASON.pid)
        season_claim.setTarget(ItemPage(repoutil.repo, season_id))

        season_ordinal_claim = repoutil.new_claim(wp.SERIES_ORDINAL.pid)
        season_ordinal_claim.setTarget(season_ordinal)
        season_claim.addQualifier(season_ordinal_claim)

        episode.addClaim(season_claim, summary=f"Setting {wp.SEASON.pid}")

    return episode.getID() if episode is not None else "Q-1"