research/resources
Archived
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

modify scripts

Browse Source
This commit is contained in:
oscarz
2025-06-26 09:48:55 +08:00
parent f0fdcf60a4
commit 6fce587aad
1 changed files with 4 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
src/javbus/fetch.py
View File

@ -95,6 +95,9 @@ def fetch_movies_common(tbl):
url = row['href'] url = row['href']
row_id = row['id'] row_id = row['id']
uncensored = row['uncensored'] if row['uncensored'] > 0 else None uncensored = row['uncensored'] if row['uncensored'] > 0 else None
# 增加一个判断：只有当url中包含uncensored时，才算无码
uncensored = 1 if 'uncensored' in url.lower() else 0
if not utils.is_valid_url(url): if not utils.is_valid_url(url):
logging.info(f'invalid url ({url}) in {tbl}, row id: {row_id}. skipping...') logging.info(f'invalid url ({url}) in {tbl}, row id: {row_id}. skipping...')
continue continue
@ -224,7 +227,7 @@ def update_multilang_tags():
langs_url = utils.generate_multilang_urls(url) langs_url = utils.generate_multilang_urls(url)
for lang, next_url in langs_url.items(): for lang, next_url in langs_url.items():
while next_url: while next_url:
logging.info(f"Fetching data for url {next_url} ..., raw url: {url}") logging.info(f"Fetching data for url {next_url} ...")
soup, status_code = scraper.fetch_page(next_url, partial(scraper.generic_validator, tag="div", identifier="waterfall", attr_type="id")) soup, status_code = scraper.fetch_page(next_url, partial(scraper.generic_validator, tag="div", identifier="waterfall", attr_type="id"))
if soup: if soup:
list_data, next_url = scraper.parse_studios_labels_series_detail(soup, next_url) list_data, next_url = scraper.parse_studios_labels_series_detail(soup, next_url)