def get_lemma_str_from_cat(self, category: str) -> List[str]:
page = Category(self.wiki, category)
cat_list = [
str(lemma).strip("[]")[2:]
for lemma in CategorizedPageGenerator(page)
]
return cat_list
def test_subpage_filter(self):
site = self.get_site()
test_cat = pywikibot.Category(site, 'Subpage testing')
gen = CategorizedPageGenerator(test_cat)
gen = pagegenerators.SubpageFilterGenerator(gen, 0)
expect_0 = ('/home/test', )
self.assertPagelistTitles(gen, titles=expect_0, site=site)
gen = CategorizedPageGenerator(test_cat)
gen = pagegenerators.SubpageFilterGenerator(gen, 3)
expect_3 = (
'/home/test',
'User:Sn1per/ProtectTest1/test',
'User:Sn1per/ProtectTest1/test/test',
'User:Sn1per/sandbox',
)
self.assertPagelistTitles(gen, titles=expect_3, site=site)
def load_files(categories, depth):
"""
Returns a list of unique files in categories
@param categories: List of Commons category names as strings
@type categories: list
@param depth: Category recursion depth
@type depth: int
@rtype: list
"""
files = set()
for cat in categories:
cat = Category(commons, cat)
generator = CategorizedPageGenerator(cat,
recurse=depth,
namespaces=Namespace.FILE)
for page in generator:
files.add(page.title(withNamespace=False))
return list(files)
import hashlib
import uuid
import json
site = Site('commons', 'commons')
cat = Category(site, 'Category:Media_contributed_by_the_Swedish_Performing_Arts_Agency:_2019-03')
translate = GoogleTranslate(input('google service account file:'))
def thumb_from_title(title):
safe_title = title.encode('utf-8')
md5_title = hashlib.md5(safe_title).hexdigest()
return 'https://upload.wikimedia.org/wikipedia/commons/thumb/{}/{}/{}/500px-{}.jpg'.format(md5_title[:1], md5_title[:2], title, title)
final_pages = list()
for page in CategorizedPageGenerator(cat, recurse=False, namespaces=6):
wikicode = mwparserfromhell.parse(page.text)
template_to_parse = False
for template in wikicode.filter_templates():
if template.name.matches('Musikverket-image'):
template_to_parse = template
if not template_to_parse:
print('failed to find given template')
continue
page_data = {}
page_data['media_id'] = '{}'.format(page.pageid)
page_data['local_id'] = mwparserfromhell.parse(template_to_parse).filter_templates()[0].get('ID').value.lstrip()