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

modify some scripts.

Browse Source
This commit is contained in:
oscar
2025-03-07 19:11:41 +08:00
parent 6cebf3f8ac
commit f5929811c7
27 changed files with 778 additions and 2724974 deletions
Download Patch File Download Diff File Expand all files Collapse all files

34867
scripts/iafd/result/astro.csv
View File

File diff suppressed because it is too large Load Diff

209198
scripts/iafd/result/astro.json
View File

File diff suppressed because it is too large Load Diff

34867
scripts/iafd/result/birth.csv
View File

File diff suppressed because it is too large Load Diff

209198
scripts/iafd/result/birth.json
View File

File diff suppressed because it is too large Load Diff

1
scripts/iafd/result/detail.csv
View File

@ -1 +0,0 @@
/root/hostdir/scripts_data/detail_birth_astro.csv
1 /root/hostdir/scripts_data/detail_birth_astro.csv

1
scripts/iafd/result/detail.json
View File

@ -1 +0,0 @@
/root/hostdir/scripts_data/detail_birth_astro.json

166437
scripts/iafd/result/ethnic.csv
View File

File diff suppressed because it is too large Load Diff

832182
scripts/iafd/result/ethnic.json
View File

File diff suppressed because it is too large Load Diff

34797
scripts/iafd/result/iafd_meta.csv
View File

File diff suppressed because it is too large Load Diff

208778
scripts/iafd/result/iafd_meta.json
View File

File diff suppressed because it is too large Load Diff

1
scripts/iafd/result/merged.json
View File

@ -1 +0,0 @@
merged_birth_astro.json

34867
scripts/iafd/result/merged_birth_astro.csv
View File

File diff suppressed because it is too large Load Diff

139466
scripts/iafd/result/merged_birth_astro.json
View File

File diff suppressed because it is too large Load Diff

163999
scripts/iafd/result/merged_birth_astro_ethnic.csv
View File

File diff suppressed because it is too large Load Diff

655994
scripts/iafd/result/merged_birth_astro_ethnic.json
View File

File diff suppressed because it is too large Load Diff

1
scripts/iafd/result/movie_list.json
View File

@ -1 +0,0 @@
distributors.json

235
scripts/iafd/src/fetch.py
View File

@ -21,13 +21,13 @@ def fetch_performers_by_astro():
url = scraper.astr_base_url + astro
logging.info(f"Fetching data for {astro}, url {url} ...")
soup = scraper.fetch_page(url, partial(scraper.generic_validator, tag="div", identifier="astro", attr_type="id"))
soup, status_code = scraper.fetch_page(url, partial(scraper.generic_validator, tag="div", identifier="astro", attr_type="id"))
if soup:
list_data, next_url = scraper.parse_page_astro(soup, astro)
if list_data:
for row in list_data :
# 写入演员数据表
perfomer_id = db_tools.insert_performer_index(name=row['person'], href=row['href'].lower() if row['href'] else '')
perfomer_id = db_tools.insert_performer_index(name=row['person'], href=row.get('href', '').lower(), from_astro_list=1)
if perfomer_id:
logging.debug(f'insert performer index to db. performer_id:{perfomer_id}, name: {row['person']}, href:{row['href']}')
else:
@ -35,6 +35,8 @@ def fetch_performers_by_astro():
else:
logging.warning(f'fetch astro error. {url} ...')
elif status_code and status_code == 404:
logging.warning(f'fetch page error. httpcode: {status_code}, url: {url}, Skiping...')
else:
logging.warning(f'fetch astro error. {url} ...')
@ -49,19 +51,21 @@ def fetch_performers_by_birth():
for day in range(1, 32): # 遍历1到31天
url = scraper.birth_base_url.format(month=month, day=day)
logging.info(f"Fetching data for birth, url {url}")
soup = scraper.fetch_page(url, partial(scraper.generic_validator, tag="div", identifier="col-sm-12 col-lg-9", attr_type="class"))
soup, status_code = scraper.fetch_page(url, partial(scraper.generic_validator, tag="div", identifier="col-sm-12 col-lg-9", attr_type="class"))
if soup:
list_data, next_url = scraper.parse_page_birth(soup, month, day)
if list_data:
for row in list_data :
# 写入演员数据表
perfomer_id = db_tools.insert_performer_index(name=row['person'], href=row['href'].lower() if row['href'] else '')
perfomer_id = db_tools.insert_performer_index(name=row['person'], href=row.get('href', '').lower(), from_birth_list=1)
if perfomer_id:
logging.debug(f'insert performer index to db. performer_id:{perfomer_id}, name: {row['person']}, href:{row['href']}')
else:
logging.warning(f'insert performer index failed. name: {row['person']}, href:{row['href']}')
else:
logging.warning(f'fetch astro error. {url} ...')
elif status_code and status_code == 404:
logging.warning(f'fetch page error. httpcode: {status_code}, url: {url}, Skiping...')
else:
logging.warning(f'fetch astro error. {url} ...')
@ -69,32 +73,56 @@ def fetch_performers_by_birth():
if debug:
return True
# 处理带空格的种族名
def format_ethnic(ethnic):
return ethnic.replace(' ', '+')
# 更新人种列表
def fetch_ethic_list():
url = scraper.ethnic_list_url
logging.info(f"Fetching data for performer's ethnic list, url {url} ...")
soup, status_code = scraper.fetch_page(url, partial(scraper.generic_validator, tag="select", identifier="ethnicity1", attr_type="id"))
if soup:
list_data = scraper.parse_page_ethnic_list(soup, url)
if list_data:
for row in list_data :
dist_id = db_tools.insert_or_update_ethnic({'name': row['name'], 'href': row.get('href', '')})
if dist_id:
logging.debug(f'insert one record into ethnic table. id:{dist_id}, name: {row['name']}, href:{row.get('href', '')}')
else:
logging.warning(f'fetch ethnic error. {url} ...')
elif status_code and status_code == 404:
logging.warning(f'fetch page error. httpcode: {status_code}, url: {url}, Skiping...')
else:
logging.warning(f'fetch page error. {url} ...')
# 按人种获取演员列表，有翻页
def fetch_performers_by_ethnic():
for ethnic in scraper.ethnic_list:
url = scraper.ethnic_url + format_ethnic(ethnic)
# 先刷新列表
fetch_ethic_list()
ethnic_list = db_tools.query_ethnic_hrefs()
for row in ethnic_list:
url = row['href']
ethnic = row['name']
next_url = url
while next_url:
logging.info(f"Fetching data for {ethnic}, url {url} ...")
soup = scraper.fetch_page(url, partial(scraper.generic_validator, tag="div", identifier="row headshotrow", attr_type="class"),
soup, status_code = scraper.fetch_page(url, partial(scraper.generic_validator, tag="div", identifier="row headshotrow", attr_type="class"),
parser="lxml", preprocessor=scraper.preprocess_html)
if soup:
list_data, next_url = scraper.parse_page_ethnic(soup, ethnic)
if list_data:
for row in list_data :
# 写入演员数据表
perfomer_id = db_tools.insert_performer_index(name=row['person'], href=row['href'].lower() if row['href'] else '')
perfomer_id = db_tools.insert_performer_index(name=row['person'], href=row.get('href', '').lower(), from_ethnic_list=1)
if perfomer_id:
logging.debug(f'insert performer index to db. performer_id:{perfomer_id}, name: {row['person']}, href:{row['href']}')
else:
logging.warning(f'insert performer index failed. name: {row['person']}, href:{row['href']}')
else:
logging.warning(f'fetch astro error. {url} ...')
elif status_code and status_code == 404:
logging.warning(f'fetch page error. httpcode: {status_code}, url: {next_url}, Skiping...')
break
else:
logging.warning(f'fetch astro error. {url} ...')
@ -106,7 +134,7 @@ def fetch_performers_by_ethnic():
def fetch_distributors_list():
url = scraper.distributors_list_url
logging.info(f"Fetching data for distributors list, url {url} ...")
soup = scraper.fetch_page(url, partial(scraper.generic_validator, tag="select", identifier="Distrib", attr_type="name"))
soup, status_code = scraper.fetch_page(url, partial(scraper.generic_validator, tag="select", identifier="Distrib", attr_type="name"))
if soup:
list_data, next_url = scraper.parse_page_dist_stu_list(soup, "Distrib")
if list_data:
@ -117,6 +145,8 @@ def fetch_distributors_list():
logging.debug(f'insert one record into distributors table. id:{dist_id}, name: {row['name']}, href:{dis_url}')
else:
logging.warning(f'fetch astro error. {url} ...')
elif status_code and status_code == 404:
logging.warning(f'fetch page error. httpcode: {status_code}, url: {url}, Skiping...')
else:
logging.warning(f'fetch astro error. {url} ...')
@ -124,7 +154,7 @@ def fetch_distributors_list():
def fetch_studios_list():
url = scraper.studios_list_url
logging.info(f"Fetching data for studios list, url {url} ...")
soup = scraper.fetch_page(url, partial(scraper.generic_validator, tag="select", identifier="Studio", attr_type="name"))
soup, status_code = scraper.fetch_page(url, partial(scraper.generic_validator, tag="select", identifier="Studio", attr_type="name"))
if soup:
list_data, next_url = scraper.parse_page_dist_stu_list(soup, "Studio")
if list_data:
@ -135,52 +165,68 @@ def fetch_studios_list():
logging.debug(f'insert one record into studios table. id:{stu_id}, name: {row['name']}, href:{stu_url}')
else:
logging.warning(f'fetch astro error. {url} ...')
elif status_code and status_code == 404:
logging.warning(f'fetch page error. httpcode: {status_code}, url: {url}, Skiping...')
else:
logging.warning(f'fetch astro error. {url} ...')
# 更新distributors列表中的影片信息
def fetch_movies_by_dist():
# 先刷新一下列表
fetch_distributors_list()
url_list = db_tools.query_studio_hrefs()
if debug:
url_list = db_tools.query_distributor_hrefs(name='vixen.com')
for url in url_list:
logging.info(f"Fetching data for distributor url {url} ...")
soup = scraper.fetch_page(url, partial(scraper.generic_validator, tag="table", identifier="distable", attr_type="id"))
soup, status_code = scraper.fetch_page(url, partial(scraper.generic_validator, tag="table", identifier="distable", attr_type="id"))
if soup:
list_data, next_url = scraper.parse_page_dist_stu(soup, 'distable')
if list_data:
for movie in list_data:
tmp_id = db_tools.insert_movie_index(title=movie['title'], href=movie['href'], release_year=utils.to_number(movie['year']))
tmp_id = db_tools.insert_movie_index(title=movie['title'], href=movie['href'], release_year=utils.to_number(movie['year']), from_dist_list=1)
if tmp_id:
logging.debug(f'insert one movie index to db. movie_id: {tmp_id}, title: {movie['title']}, href: {movie['href']}')
else:
logging.warning(f'insert movie index failed. title: {movie['title']}, href: {movie['href']}')
else :
logging.warning(f'parse_page_movie error. url: {url}')
elif status_code and status_code == 404:
logging.warning(f'fetch page error. httpcode: {status_code}, url: {url}, Skiping...')
else:
logging.warning(f'fetching page error. {url}')
# 调试增加brak
if debug:
break
# 更新distributors列表中的影片信息
def fetch_movies_by_stu():
# 先刷新一下列表
fetch_studios_list()
url_list = db_tools.query_studio_hrefs()
if debug:
url_list = db_tools.query_studio_hrefs(name='vixen.com')
for url in url_list:
logging.info(f"Fetching data for studio url {url} ...")
soup = scraper.fetch_page(url, partial(scraper.generic_validator, tag="table", identifier="studio", attr_type="id"))
soup, status_code = scraper.fetch_page(url, partial(scraper.generic_validator, tag="table", identifier="studio", attr_type="id"))
if soup:
list_data, next_url = scraper.parse_page_dist_stu(soup, 'studio')
if list_data:
for movie in list_data:
tmp_id = db_tools.insert_movie_index(title=movie['title'], href=movie['href'], release_year=utils.to_number(movie['year']))
tmp_id = db_tools.insert_movie_index(title=movie['title'], href=movie['href'], release_year=utils.to_number(movie['year']), from_stu_list=1)
if tmp_id:
logging.debug(f'insert one movie index to db. movie_id: {tmp_id}, title: {movie['title']}, href: {movie['href']}')
else:
logging.warning(f'insert movie index failed. title: {movie['title']}, href: {movie['href']}')
else :
logging.warning(f'parse_page_movie error. url: {url}')
elif status_code and status_code == 404:
logging.warning(f'fetch page error. httpcode: {status_code}, url: {url}, Skiping...')
else:
logging.warning(f'fetching page error. {url}')
# 调试增加brak
if debug:
break
@ -198,7 +244,7 @@ def fetch_performers_detail():
url = performer['href']
person = performer['name']
logging.info(f"Fetching data for performer ({person}), url {url} ...")
soup = scraper.fetch_page(url, partial(scraper.generic_validator, tag="div", identifier="headshot", attr_type="id"))
soup, status_code = scraper.fetch_page(url, partial(scraper.generic_validator, tag="div", identifier="headshot", attr_type="id"))
if soup:
data = scraper.parse_page_performer(soup)
if data:
@ -220,6 +266,8 @@ def fetch_performers_detail():
})
else:
logging.warning(f'parse_page_performer error. person: ({person}), url: {url}')
elif status_code and status_code == 404:
logging.warning(f'fetch page error. httpcode: {status_code}, url: {url}, Skiping...')
else:
logging.warning(f'fetch_page error. person: ({person}), url: {url}')
# 调试break
@ -238,7 +286,7 @@ def fetch_movies_detail():
url = movie['href']
title = movie['title']
logging.info(f"Fetching data for movie ({title}), url {url} ...")
soup = scraper.fetch_page(url, partial(scraper.generic_validator, tag="div", identifier="col-xs-12 col-sm-3", attr_type="class"))
soup, status_code = scraper.fetch_page(url, partial(scraper.generic_validator, tag="div", identifier="col-xs-12 col-sm-3", attr_type="class"))
if soup:
movie_data = scraper.parse_page_movie(soup, url, title)
if movie_data :
@ -257,54 +305,59 @@ def fetch_movies_detail():
utils.write_movie_json(url, movie_data)
else:
logging.warning(f'parse_page_movie error. url: {url}')
elif status_code and status_code == 404:
logging.warning(f'fetch page error. httpcode: {status_code}, url: {url}, Skiping...')
else:
logging.warning(f'fetch_page error. url: {url}')
# 调试增加break
if debug:
return True
# 获取更新
def check_update():
# 建立缩写到函数的映射
function_map = {
"astro": fetch_performers_by_astro,
"birth": fetch_performers_by_birth,
"ethnic": fetch_performers_by_ethnic,
"dist" : fetch_movies_by_dist,
"stu" : fetch_movies_by_stu,
"performers": fetch_performers_detail,
"movies" : fetch_movies_detail,
}
# 主函数
def main(cmd, args_debug, args_force):
global debug
debug = args_debug
global force
force = args_force
# 开启任务
task_id = db_tools.insert_task_log()
if task_id is None:
logging.warning(f'insert task log error.')
return None
logging.info(f'running task. id: {task_id}, debug: {debug}, force: {force}, cmd: {cmd}')
# 刷新星座演员列表
db_tools.update_task_log(task_id, task_status='fetching astro list')
fetch_performers_by_astro()
# 刷新生日演员列表
db_tools.update_task_log(task_id, task_status='fetching birth list')
fetch_performers_by_birth()
# 刷新人种演员列表
db_tools.update_task_log(task_id, task_status='fetching ethnic list')
fetch_performers_by_ethnic()
# 刷新distributors列表
db_tools.update_task_log(task_id, task_status='fetching distributor list')
fetch_distributors_list()
# 刷新studios列表
db_tools.update_task_log(task_id, task_status='fetching studio list')
fetch_studios_list()
# 刷新影片列表
db_tools.update_task_log(task_id, task_status='fetching movie list by dist')
fetch_movies_by_dist()
db_tools.update_task_log(task_id, task_status='fetching movie list by stu')
fetch_movies_by_stu()
# 更新演员信息
db_tools.update_task_log(task_id, task_status='fetching performers')
fetch_performers_detail()
# 更新影片信息
db_tools.update_task_log(task_id, task_status='fetching movies')
fetch_movies_detail()
# 执行指定的函数
if cmd:
function_names = args.cmd.split(",") # 拆分输入
for short_name in function_names:
func = function_map.get(short_name.strip()) # 从映射中获取对应的函数
if callable(func):
db_tools.update_task_log(task_id, task_status=f'Running {func}')
func()
else:
print(f"Warning: {short_name} is not a valid function shortcut.")
else: # 全量执行
for name, func in function_map.items():
if callable(func):
db_tools.update_task_log(task_id, task_status=f'Running {func}')
func()
else:
print(f"Warning: {name} is not a valid function shortcut.")
logging.info(f'all process completed!')
db_tools.finalize_task_log(task_id)
@ -314,80 +367,14 @@ def check_update():
# 2, distributors 和 studios 对movie列表的互相检验
# 3, 数据不规范问题，可以先手动导入所有 performers 和 movies ，然后用本程序增量获取新的
# 处理本地数据
def load_data():
# 导入已经在本地的 performers 数据
perfomers_file = '../result/detail.json'
performers_data = utils.read_json(perfomers_file)
if performers_data is None:
print(f'read file error.')
performers_data = []
# 读取数据库中的演员列表
existed_performer_hrefs = db_tools.query_performer_hrefs()
if not existed_performer_hrefs:
logging.warning(f'get existed performers from db error.')
return None
for person in performers_data:
# 非强制更新下，跳过已有数据
if not force and person['href'] in existed_performer_hrefs:
continue
performer_id = db_tools.insert_or_update_performer(person)
if performer_id:
logging.info(f'insert one person, id: {performer_id}, person: {person['person']}, url: {person['href']}')
else:
logging.warning(f'insert person: {person['person']}, {person['href']} failed.')
logging.info(f'all performers loaded in database.')
# 导入已经在本地的 movies 数据
movies_file = '../result/movie_details.json'
movies_data = utils.read_json(movies_file)
if movies_data is None:
print(f'read file error.')
movies_data = []
for movie in movies_data:
# 修复url不规范的问题
if movie['DistributorHref']:
movie['DistributorHref'] = utils.dist_stu_href_rewrite(movie['DistributorHref'].lower())
if movie['StudioHref']:
movie['StudioHref'] = utils.dist_stu_href_rewrite(movie['StudioHref'].lower())
movie_id = db_tools.insert_or_update_movie(movie)
if movie_id:
logging.info(f'insert one movie, id: {movie_id}, title: {movie['title']} url: {movie['href']}')
else:
logging.warning(f'insert movie {movie['title']}, {movie['href']} failed.')
logging.info('task completed.')
# 主函数
def main(task, args_debug, args_force):
global debug
debug = args_debug
if debug:
logging.info('Debug mode enabled.')
global force
force = args_force
if force:
logging.info('force update for all data.')
if task == 'fetch':
check_update()
elif task == 'load':
load_data()
else:
print(f'unkown command. see --help.')
if __name__ == "__main__":
# 命令行参数处理
keys_str = ",".join(function_map.keys())
parser = argparse.ArgumentParser(description='fetch iafd data.')
parser.add_argument('--task', type=str, default='fetch', help='fetch from iafd.com or load from local data ... (fetch , load)')
parser.add_argument("--cmd", type=str, help=f"Comma-separated list of function shortcuts: {keys_str}")
parser.add_argument('--debug', action='store_true', help='Enable debug mode (limit records)')
parser.add_argument('--force', action='store_true', help='force update (true for rewrite all)')
args = parser.parse_args()
main(args.task, args.debug, args.force)
main(args.cmd, args.debug, args.force)

42
scripts/iafd/src/iafd_scraper.py
View File

@ -21,15 +21,14 @@ astro_list = ['Aries', 'Taurus', 'Gemini', 'Cancer', 'Leo', 'Virgo', 'Libra', 'S
birth_base_url = "https://www.iafd.com/calendar.asp?calmonth={month}&calday={day}"
ethnic_url = f"{host_url}/lookupethnic.rme/ethnic="
ethnic_list = ['caucasian', 'black', 'asian', 'latin', 'native american', 'middle eastern', 'mediteranean', 'indian', 'polynesian', 'multi-ethnic', 'ethnic', 'romani', 'eurasian', 'north african', 'south asian']
distributors_list_url = f'{host_url}/distrib.asp'
distributors_base_url = f"{host_url}/distrib.rme/distrib="
studios_list_url = f"{host_url}/studio.asp"
studios_base_url = f"{host_url}/studio.rme/studio="
ethnic_list_url = f'{host_url}/advsearch.asp'
# 设置 headers 和 scraper
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36'
@ -42,9 +41,15 @@ def fetch_page(url, validator, max_retries=3, parser="html.parser", preprocessor
try:
if host_url not in url.lower():
logging.error(f'wrong url format: {url}')
return None
return None, None
response = scraper.get(url, headers=headers)
# 处理 HTTP 状态码
if response.status_code == 404:
logging.warning(f"Page not found (404): {url}")
return None, 404 # 直接返回 404，调用方可以跳过
response.raise_for_status() # 处理 HTTP 错误
# 预处理 HTML（如果提供了 preprocessor）
@ -52,7 +57,7 @@ def fetch_page(url, validator, max_retries=3, parser="html.parser", preprocessor
soup = BeautifulSoup(html_text, parser)
if validator(soup): # 进行自定义页面检查
return soup
return soup, response.status_code
logging.warning(f"Validation failed on attempt {attempt + 1} for {url}")
except cloudscraper.exceptions.CloudflareChallengeError as e:
@ -63,7 +68,7 @@ def fetch_page(url, validator, max_retries=3, parser="html.parser", preprocessor
logging.error(f"Unexpected error on {url}: {e}, Retring...")
logging.error(f'Fetching failed after max retries. {url}')
return None # 达到最大重试次数仍然失败
return None, None # 达到最大重试次数仍然失败
# 修复 HTML 结构，去除多余标签并修正 <a> 标签，在获取人种的时候需要
def preprocess_html(html):
@ -83,6 +88,31 @@ def generic_validator(soup, tag, identifier, attr_type="id"):
def movie_validator(soup, table_id):
return soup.find("table", id=table_id) is not None
# 解析 HTML 内容，提取需要的数据
def parse_page_ethnic_list(soup, href):
div_root = soup.find("select", id="ethnicity1")
if not div_root:
logging.warning(f"Warning: No 'ethnicity1' select found in {href}")
return None, None
list_data = []
# 提取所有的 <option> 标签
options = div_root.find_all('option')
if options:
# 解析并输出 value 和文本内容
for option in options:
href = option.get('value', None)
text = option.text.strip()
if href and href.lower() == 'none':
continue
list_data.append({
"name": text,
"href": host_url + href if href else ''
})
return list_data
# 解析 HTML 内容，提取需要的数据
def parse_page_astro(soup, astro):
astro_div = soup.find("div", id="astro")

107
scripts/iafd/src/load.py Normal file
View File

@ -0,0 +1,107 @@
import json
import time
import csv
import argparse
import logging
from functools import partial
import config
import sqlite_utils as db_tools
import iafd_scraper as scraper
import utils
config.setup_logging()
res_dir = '/root/hostdir/scripts_data/iafd_202503'
# 演员列表
def load_performer_list(file, **from_fields):
json_data = utils.read_json(file)
if json_data is None:
json_data = []
total_rows = len(json_data)
loaded_rows = 0
succ = 0
for row in json_data:
row_id = db_tools.insert_performer_index(name=row.get('person', ''),
href=row.get('href', ''),
**from_fields
)
if row_id:
logging.debug(f'insert one person, id: {row_id}, person: {row['person']}, url: {row['href']}')
succ += 1
else:
logging.warning(f'insert person failed. {row['person']}, {row['href']} failed.')
loaded_rows += 1
if loaded_rows % 10000 == 0:
logging.info(f'loading file: {file}, total rows: {total_rows}, loaded rows: {loaded_rows}, succ rows: {succ}')
logging.info(f'load data succ. file: {file}, rows: {total_rows}, succ rows: {succ}')
# movie 列表
def load_movie_list(file, **from_fields):
json_data = utils.read_json(file)
if json_data is None:
json_data = []
total_rows = len(json_data)
loaded_rows = 0
succ = 0
for row in json_data:
row_id = db_tools.insert_movie_index(title=row.get('title', ''),
href=row.get('href', ''),
release_year=utils.to_number(row['year']),
**from_fields
)
if row_id:
logging.debug(f'insert one movie, id: {row_id}, title: {row['title']}, url: {row['href']}')
succ += 1
else:
logging.warning(f'insert movie failed: {row['title']}, {row['href']} failed.')
loaded_rows += 1
if loaded_rows % 10000 == 0:
logging.info(f'loading file: {file}, total rows: {total_rows}, loaded rows: {loaded_rows}, succ rows: {succ}')
logging.info(f'load data succ. file: {file}, rows: {len(json_data)}, succ rows: {succ}')
# 演员详情
def load_performers(file):
json_data = utils.read_json(file)
if json_data is None:
json_data = []
total_rows = len(json_data)
loaded_rows = 0
succ = 0
for row in json_data:
performer_id = db_tools.insert_or_update_performer(row)
if performer_id:
logging.debug(f'insert one person, id: {performer_id}, person: {row['person']}, url: {row['href']}')
succ += 1
else:
logging.warning(f'insert person failed. {row['person']}, {row['href']} failed.')
loaded_rows += 1
if loaded_rows % 10000 == 0:
logging.info(f'loading file: {file}, total rows: {total_rows}, loaded rows: {loaded_rows}, succ rows: {succ}')
logging.info(f'load data succ. file: {file}, rows: {len(json_data)}, succ rows: {succ}')
if __name__ == "__main__":
load_performer_list(f'{res_dir}/astro.json', from_astro_list=1)
time.sleep(3)
load_performer_list(f'{res_dir}/birth.json', from_birth_list=1)
time.sleep(3)
load_performer_list(f'{res_dir}/ethnic.json', from_ethnic_list=1)
time.sleep(3)
load_movie_list(f'{res_dir}/distributors.json', from_dist_list=1)
time.sleep(3)
load_movie_list(f'{res_dir}/studios.json', from_stu_list=1)
time.sleep(3)
load_performers(f'{res_dir}/performers.json')

162
scripts/iafd/src/sqlite_utils.py
View File

@ -25,20 +25,48 @@ def get_id_by_href(table: str, href: str) -> int:
return row[0] if row else None
# 插入演员索引，来自于列表数据
def insert_performer_index(name, href):
def insert_performer_index(name, href, from_astro_list=None, from_birth_list=None, from_ethnic_list=None, from_movie_list=None):
try:
# **查询是否已存在该演员**
cursor.execute("""
INSERT OR IGNORE INTO iafd_performers (href, name) VALUES (?, ?)
""", (
href, name
))
SELECT id, name, from_astro_list, from_birth_list, from_ethnic_list, from_movie_list
FROM iafd_performers WHERE href = ?
""", (href,))
existing_performer = cursor.fetchone()
if existing_performer: # **如果演员已存在**
performer_id, existing_name, existing_astro, existing_birth, existing_ethnic, existing_movie = existing_performer
# **如果没有传入值，则保持原有值**
from_astro_list = from_astro_list if from_astro_list is not None else existing_astro
from_birth_list = from_birth_list if from_birth_list is not None else existing_birth
from_ethnic_list = from_ethnic_list if from_ethnic_list is not None else existing_ethnic
from_movie_list = from_movie_list if from_movie_list is not None else existing_movie
cursor.execute("""
UPDATE iafd_performers
SET name = ?,
from_astro_list = ?,
from_birth_list = ?,
from_ethnic_list = ?,
from_movie_list = ?,
updated_at = datetime('now', 'localtime')
WHERE href = ?
""", (name, from_astro_list, from_birth_list, from_ethnic_list, from_movie_list, href))
else: # **如果演员不存在，插入**
cursor.execute("""
INSERT INTO iafd_performers (href, name, from_astro_list, from_birth_list, from_ethnic_list, from_movie_list)
VALUES (?, ?, COALESCE(?, 0), COALESCE(?, 0), COALESCE(?, 0), COALESCE(?, 0))
""", (href, name, from_astro_list, from_birth_list, from_ethnic_list, from_movie_list))
conn.commit()
performer_id = get_id_by_href('iafd_performers', href)
if performer_id:
logging.debug(f'insert one performer index, id: {performer_id}, name: {name}, href: {href}')
logging.debug(f'Inserted/Updated performer index, id: {performer_id}, name: {name}, href: {href}')
return performer_id
return performer_id
except sqlite3.Error as e:
conn.rollback()
logging.error(f"数据库错误: {e}")
@ -48,28 +76,58 @@ def insert_performer_index(name, href):
logging.error(f"未知错误: {e}")
return None
# """插入电影索引，来自于列表数据"""
def insert_movie_index(title, href, release_year=0):
# """插入电影索引，来自于列表数据"""
def insert_movie_index(title, href, release_year=0, from_performer_list=None, from_dist_list=None, from_stu_list=None):
try:
# 插入或更新电影信息
# **查询是否已存在该电影**
cursor.execute("""
INSERT OR IGNORE INTO iafd_movies (title, href, release_year) VALUES (?, ?, ?)
""",
(title, href, release_year)
)
SELECT id, title, release_year, from_performer_list, from_dist_list, from_stu_list
FROM iafd_movies WHERE href = ?
""", (href,))
existing_movie = cursor.fetchone()
if existing_movie: # **如果电影已存在**
movie_id, existing_title, existing_year, existing_performer, existing_dist, existing_stu = existing_movie
# **如果没有传入值，则保持原有值**
release_year = release_year if release_year != 0 else existing_year
from_performer_list = from_performer_list if from_performer_list is not None else existing_performer
from_dist_list = from_dist_list if from_dist_list is not None else existing_dist
from_stu_list = from_stu_list if from_stu_list is not None else existing_stu
cursor.execute("""
UPDATE iafd_movies
SET title = ?,
release_year = ?,
from_performer_list = ?,
from_dist_list = ?,
from_stu_list = ?,
updated_at = datetime('now', 'localtime')
WHERE href = ?
""", (title, release_year, from_performer_list, from_dist_list, from_stu_list, href))
else: # **如果电影不存在，插入**
cursor.execute("""
INSERT INTO iafd_movies (title, href, release_year, from_performer_list, from_dist_list, from_stu_list)
VALUES (?, ?, ?, COALESCE(?, 0), COALESCE(?, 0), COALESCE(?, 0))
""", (title, href, release_year, from_performer_list, from_dist_list, from_stu_list))
conn.commit()
movie_id = get_id_by_href('iafd_movies', href)
if movie_id:
logging.debug(f'insert one movie index, id: {movie_id}, title: {title}, href: {href}')
logging.debug(f'Inserted/Updated movie index, id: {movie_id}, title: {title}, href: {href}')
return movie_id
return movie_id
except sqlite3.Error as e:
conn.rollback()
logging.error(f"数据库错误: {e}")
return None
except Exception as e:
conn.rollback()
logging.error("Error inserting movie: %s", e)
logging.error(f"未知错误: {e}")
return None
# 插入演员和电影的关联数据
def insert_performer_movie(performer_id, movie_id, role, notes):
try:
@ -167,16 +225,14 @@ def insert_or_update_performer(data):
conn.commit()
# 插入影片列表，可能有 personal 和 director 两个身份
credits = data['credits']
if credits is None :
return performer_id
credits = data.get('credits', {})
for role, movies in credits.items():
if movies:
for movie in movies:
movie_id = get_id_by_href('iafd_movies', movie['href'])
# 影片不存在，先插入
if movie_id is None:
movie_id = insert_movie_index(movie['title'], movie['href'], utils.to_number(movie['year']))
movie_id = insert_movie_index(movie['title'], movie['href'], utils.to_number(movie['year']), from_performer_list=1)
if movie_id:
tmp_id = insert_performer_movie(performer_id, movie_id, role, movie['notes'])
if tmp_id :
@ -269,6 +325,54 @@ def query_performer_hrefs(**filters):
return None
# 插入或更新发行商 """
def insert_or_update_ethnic(data):
try:
cursor.execute("""
INSERT INTO iafd_meta_ethnic (name, href)
VALUES (?, ?)
ON CONFLICT(href) DO UPDATE SET
name = excluded.name
""", (data["name"], data["href"]))
conn.commit()
# 获取 performer_id
cursor.execute("SELECT id FROM iafd_meta_ethnic WHERE href = ?", (data["href"],))
dist_id = cursor.fetchone()[0]
if dist_id:
logging.debug(f"成功插入/更新ethnic: {data['name']}")
return dist_id
else:
return None
except sqlite3.Error as e:
conn.rollback()
logging.error(f"数据库错误: {e}")
return None
# 按条件查询 href 列表
def query_ethnic_hrefs(**filters):
try:
sql = "SELECT href, name FROM iafd_meta_ethnic WHERE 1=1"
params = []
if "id" in filters:
sql += " AND id = ?"
params.append(filters["id"])
if "url" in filters:
sql += " AND href = ?"
params.append(filters["href"])
if "name" in filters:
sql += " AND name LIKE ?"
params.append(f"%{filters['name']}%")
cursor.execute(sql, params)
#return [row[0].lower() for row in cursor.fetchall()] # 链接使用小写
return [{'href': row[0], 'name': row[1]} for row in cursor.fetchall()]
except sqlite3.Error as e:
logging.error(f"查询 href 失败: {e}")
return None
# 插入或更新发行商 """
def insert_or_update_distributor(data):
try:
@ -436,7 +540,7 @@ def insert_or_update_movie(movie_data):
director_id = get_id_by_href('iafd_performers', movie_data['DirectorHref'])
# 导演不存在的话，插入一条
if director_id is None:
director_id = insert_performer_index( movie_data['Director'], movie_data['DirectorHref'])
director_id = insert_performer_index( movie_data['Director'], movie_data['DirectorHref'], from_movie_list=1)
# 插入或更新电影信息
cursor.execute(
@ -469,7 +573,7 @@ def insert_or_update_movie(movie_data):
performer_id = get_id_by_href('iafd_performers', performer['href'])
# 如果演员不存在，先插入
if performer_id is None:
performer_id = insert_performer_index(performer['name'], performer['href'])
performer_id = insert_performer_index(performer['name'], performer['href'], from_movie_list=1)
if performer_id:
notes = '|'.join(tag for tag in performer['tags'] if tag != performer['name'])
tmp_id = insert_performer_movie(performer_id, movie_id, 'personal', notes)
@ -581,7 +685,13 @@ def insert_task_log():
INSERT INTO iafd_task_log (task_status) VALUES ('Start')
""")
conn.commit()
return cursor.lastrowid # 获取插入的 task_id
task_id = cursor.lastrowid
if task_id is None:
return None
update_task_log(task_id=task_id, task_status='Start')
return task_id # 获取插入的 task_id
except sqlite3.Error as e:
logging.error(f"插入任务失败: {e}")
return None

170
scripts/javdb/src/fetch.py
View File

@ -20,26 +20,29 @@ def fetch_actor_list():
next_url = scraper.actors_uncensored_base_url
while next_url:
logging.info(f'fetching page {next_url}')
soup = scraper.fetch_page(next_url, partial(scraper.generic_validator, tag="div", identifier="actors", attr_type="id"))
soup, status_code = scraper.fetch_page(next_url, partial(scraper.generic_validator, tag="div", identifier="actors", attr_type="id"))
if soup:
list_data, next_url = scraper.parse_actors_uncensored(soup, next_url)
if list_data :
# 写入数据库
for row in list_data:
actor_id = db_tools.insert_actor_index(name=row['name'], href=row['href'] if row['href'] else '')
actor_id = db_tools.insert_actor_index(name=row['name'], href=row.get('href', ''), from_actor_list=1)
if actor_id:
logging.debug(f'insert performer index to db. performer_id:{actor_id}, name: {row['name']}, href:{row['href']}')
else:
logging.warning(f'insert performer index failed. name: {row['name']}, href:{row['href']}')
else:
logging.warning(f'fetch actor error. {next_url} ...')
elif status_code and status_code == 404:
logging.warning(f'fetch page error. httpcode: {status_code}, url: {next_url}')
break
# 获取makers列表
def fetch_makers_list():
next_url = scraper.makers_uncensored_base_url
while next_url:
logging.info(f'fetching page {next_url}')
soup = scraper.fetch_page(next_url, partial(scraper.generic_validator, tag="div", identifier="makers", attr_type="id"))
soup, status_code = scraper.fetch_page(next_url, partial(scraper.generic_validator, tag="div", identifier="makers", attr_type="id"))
if soup:
list_data, next_url = scraper.parse_makers_uncensored(soup, next_url)
if list_data :
@ -53,12 +56,16 @@ def fetch_makers_list():
else:
logging.warning(f'fetch actor error. {next_url} ...')
elif status_code and status_code == 404:
logging.warning(f'fetch page error. httpcode: {status_code}, url: {next_url}')
break
# 获取series列表
def fetch_series_list():
next_url = scraper.series_uncensored_base_url
while next_url:
logging.info(f'fetching page {next_url}')
soup = scraper.fetch_page(next_url, partial(scraper.generic_validator, tag="div", identifier="series", attr_type="id"))
soup, status_code = scraper.fetch_page(next_url, partial(scraper.generic_validator, tag="div", identifier="series", attr_type="id"))
if soup:
list_data, next_url = scraper.parse_series_uncensored(soup, next_url)
if list_data :
@ -72,6 +79,10 @@ def fetch_series_list():
else:
logging.warning(f'fetch actor error. {next_url} ...')
elif status_code and status_code == 404:
logging.warning(f'fetch page error. httpcode: {status_code}, url: {next_url}')
break
# 更新makers列表中的影片信息
def fetch_movies_by_maker():
@ -79,21 +90,27 @@ def fetch_movies_by_maker():
if debug:
url_list = db_tools.query_maker_hrefs(name='muramura')
for url in url_list:
next_url = url
while True:
# 去掉可下载的标志（如果有）
next_url = utils.remove_url_query(url)
while next_url:
logging.info(f"Fetching data for maker url {next_url} ...")
soup = scraper.fetch_page(next_url, partial(scraper.generic_validator, tag="div", identifier="movie-list h cols-4 vcols-5", attr_type="class"))
soup, status_code = scraper.fetch_page(next_url, partial(scraper.generic_validator, tag="div", identifier="column section-title", attr_type="class"))
if soup:
list_data, next_url = scraper.parse_maker_detail(soup, next_url)
if list_data:
for movie in list_data:
tmp_id = db_tools.insert_movie_index(title=movie['title'], href=movie['href'])
tmp_id = db_tools.insert_movie_index(title=movie['title'], href=movie['href'], from_movie_makers=1)
if tmp_id:
logging.debug(f'insert one movie index to db. movie_id: {tmp_id}, title: {movie['title']}, href: {movie['href']}')
else:
logging.warning(f'insert movie index failed. title: {movie['title']}, href: {movie['href']}')
else :
logging.warning(f'parse_page_movie error. url: {next_url}')
elif status_code and status_code == 404:
logging.warning(f'fetch page error. httpcode: {status_code}, url: {next_url}')
break
# 调试增加brak
if debug:
return True
@ -104,21 +121,26 @@ def fetch_movies_by_series():
if debug:
url_list = db_tools.query_series_hrefs(name='10musume')
for url in url_list:
next_url = url
while True:
# 去掉可下载的标志（如果有）
next_url = utils.remove_url_query(url)
while next_url:
logging.info(f"Fetching data for series url {next_url} ...")
soup = scraper.fetch_page(next_url, partial(scraper.generic_validator, tag="div", identifier="movie-list h cols-4 vcols-5", attr_type="class"))
soup, status_code = scraper.fetch_page(next_url, partial(scraper.generic_validator, tag="div", identifier="column section-title", attr_type="class"))
if soup:
list_data, next_url = scraper.parse_series_detail(soup, next_url)
if list_data:
for movie in list_data:
tmp_id = db_tools.insert_movie_index(title=movie['title'], href=movie['href'])
tmp_id = db_tools.insert_movie_index(title=movie['title'], href=movie['href'], from_movie_series=1)
if tmp_id:
logging.debug(f'insert one movie index to db. movie_id: {tmp_id}, title: {movie['title']}, href: {movie['href']}')
else:
logging.warning(f'insert movie index failed. title: {movie['title']}, href: {movie['href']}')
else :
logging.warning(f'parse_page_movie error. url: {next_url}')
elif status_code and status_code == 404:
logging.warning(f'fetch page error. httpcode: {status_code}, url: {next_url}')
break
# 调试增加brak
if debug:
return True
@ -129,23 +151,31 @@ def fetch_performers_detail():
perfomers_list = []
while True:
# 每次从数据库中取一部分，避免一次全量获取
perfomers_list = db_tools.query_actors(is_full_data=0, limit=10)
perfomers_list = db_tools.query_actors(is_full_data=0, limit=100)
if len(perfomers_list) < 1:
logging.info(f'all performers fetched.')
break
for performer in perfomers_list:
url = performer['href']
person = performer['name']
pic = ''
alias = []
next_url = url
all_movies = []
while next_url:
logging.info(f"Fetching data for actor ({person}), url {next_url} ...")
soup = scraper.fetch_page(next_url, partial(scraper.generic_validator, tag="div", identifier="movie-list h cols-4 vcols-5", attr_type="class"))
soup, status_code = scraper.fetch_page(next_url, partial(scraper.generic_validator, tag="div", identifier="movie-list h cols-4 vcols-5", attr_type="class"))
if soup:
data, next_url = scraper.parse_actor_detail(soup, next_url)
if data:
all_movies.extend(data)
pic = data.get('pic', '')
alias = data.get('alias', [])
all_movies.extend(data.get('movies', []))
elif status_code and status_code == 404:
logging.warning(f'fetch page error. httpcode: {status_code}, url: {next_url}, Skiping...')
break
else:
logging.warning(f'fetch_page error. person: ({person}), url: {url}')
@ -153,8 +183,8 @@ def fetch_performers_detail():
performer_id = db_tools.insert_or_update_actor({
'href': url,
'name': person,
'pic' : '',
'alias' : [],
'pic' : pic,
'alias' : alias,
'credits':all_movies
})
if performer_id:
@ -169,7 +199,7 @@ def fetch_performers_detail():
def fetch_movies_detail():
movies_list = []
while True:
movies_list = db_tools.query_movie_hrefs(is_full_data=0, limit=10)
movies_list = db_tools.query_movie_hrefs(is_full_data=0, limit=100)
if len(movies_list) < 1:
logging.info(f'all movies fetched.')
break
@ -177,7 +207,7 @@ def fetch_movies_detail():
url = movie['href']
title = movie['title']
logging.info(f"Fetching data for movie ({title}), url {url} ...")
soup = scraper.fetch_page(url, partial(scraper.generic_validator, tag="div", identifier="video-meta-panel", attr_type="class"))
soup, status_code = scraper.fetch_page(url, partial(scraper.generic_validator, tag="div", identifier="video-meta-panel", attr_type="class"))
if soup:
movie_data = scraper.parse_movie_detail(soup, url, title)
if movie_data :
@ -188,84 +218,76 @@ def fetch_movies_detail():
logging.warning(f'insert movie {url} failed.')
else:
logging.warning(f'parse_page_movie error. url: {url}')
elif status_code and status_code == 404:
logging.warning(f'fetch page error. httpcode: {status_code}, url: {next_url}')
break
else:
logging.warning(f'fetch_page error. url: {url}')
# 调试增加break
if debug:
return True
# 获取更新
def check_update():
# 建立缩写到函数的映射
function_map = {
"actor_list": fetch_actor_list,
"maker_list": fetch_makers_list,
"series_list": fetch_series_list,
"makers": fetch_movies_by_maker,
"series" : fetch_movies_by_series,
"movies" : fetch_movies_detail,
"actors" : fetch_performers_detail,
}
# 主函数
def main(cmd, args_debug, args_force):
global debug
debug = args_debug
global force
force = args_force
# 开启任务
task_id = db_tools.insert_task_log()
if task_id is None:
logging.warning(f'insert task log error.')
return None
logging.info(f'running task. id: {task_id}, debug: {debug}, force: {force}, cmd: {cmd}')
if False:
# 刷新演员列表
db_tools.update_task_log(task_id, task_status='fetching actor list')
fetch_actor_list()
# 刷新makers列表
db_tools.update_task_log(task_id, task_status='fetching maker list')
fetch_makers_list()
# 刷新series列表
db_tools.update_task_log(task_id, task_status='fetching series list')
fetch_series_list()
# 刷新影片列表
db_tools.update_task_log(task_id, task_status='fetching movie list by maker')
fetch_movies_by_maker()
db_tools.update_task_log(task_id, task_status='fetching movie list by series')
fetch_movies_by_series()
# 更新演员信息
db_tools.update_task_log(task_id, task_status='fetching performers')
fetch_performers_detail()
# 更新影片信息
db_tools.update_task_log(task_id, task_status='fetching movies')
fetch_movies_detail()
# 执行指定的函数
if cmd:
function_names = args.cmd.split(",") # 拆分输入
for short_name in function_names:
func = function_map.get(short_name.strip()) # 从映射中获取对应的函数
if callable(func):
db_tools.update_task_log(task_id, task_status=f'Running {func}')
func()
else:
logging.warning(f" {short_name} is not a valid function shortcut.")
else: # 全量执行
for name, func in function_map.items():
if callable(func):
db_tools.update_task_log(task_id, task_status=f'Running {func}')
func()
else:
logging.warning(f" {short_name} is not a valid function shortcut.")
logging.info(f'all process completed!')
db_tools.finalize_task_log(task_id)
# TODO:
# 1,
# 处理本地数据
def load_data():
return True
# 主函数
def main(task, args_debug, args_force):
global debug
debug = args_debug
if debug:
logging.info('Debug mode enabled.')
global force
force = args_force
if force:
logging.info('force update for all data.')
if task == 'fetch':
check_update()
elif task == 'load':
load_data()
else:
print(f'unkown command. see --help.')
if __name__ == "__main__":
# 命令行参数处理
parser = argparse.ArgumentParser(description='fetch iafd data.')
parser.add_argument('--task', type=str, default='fetch', help='fetch from iafd.com or load from local data ... (fetch , load)')
keys_str = ",".join(function_map.keys())
parser = argparse.ArgumentParser(description='fetch javdb data.')
parser.add_argument("--cmd", type=str, help=f"Comma-separated list of function shortcuts: {keys_str}")
parser.add_argument('--debug', action='store_true', help='Enable debug mode (limit records)')
parser.add_argument('--force', action='store_true', help='force update (true for rewrite all)')
args = parser.parse_args()
main(args.task, args.debug, args.force)
main(args.cmd, args.debug, args.force)

62
scripts/javdb/src/scraper.py
View File

@ -30,9 +30,15 @@ def fetch_page(url, validator, max_retries=3, parser="html.parser", preprocessor
try:
if 'javdb.com' not in url.lower():
logging.error(f'wrong url format: {url}')
return None
return None, None
response = scraper.get(url, headers=headers)
# 处理 HTTP 状态码
if response.status_code == 404:
logging.warning(f"Page not found (404): {url}")
return None, 404 # 直接返回 404，调用方可以跳过
response.raise_for_status() # 处理 HTTP 错误
# 预处理 HTML（如果提供了 preprocessor）
@ -40,7 +46,7 @@ def fetch_page(url, validator, max_retries=3, parser="html.parser", preprocessor
soup = BeautifulSoup(html_text, parser)
if validator(soup): # 进行自定义页面检查
return soup
return soup, response.status_code
logging.warning(f"Validation failed on attempt {attempt + 1} for {url}")
except cloudscraper.exceptions.CloudflareChallengeError as e:
@ -51,7 +57,7 @@ def fetch_page(url, validator, max_retries=3, parser="html.parser", preprocessor
logging.error(f"Unexpected error on {url}: {e}, Retring...")
logging.error(f'Fetching failed after max retries. {url}')
return None # 达到最大重试次数仍然失败
return None, None # 达到最大重试次数仍然失败
# 修复 HTML 结构，去除多余标签并修正 <a> 标签，在获取人种的时候需要
def preprocess_html(html):
@ -78,6 +84,21 @@ def url_page_num(href):
else:
return None
# <span class="avatar" style="background-image: url(https://c0.jdbstatic.com/avatars/md/mdRn.jpg)"></span>
def parse_avatar_image(soup):
try:
span = soup.find("span", class_="avatar")
if not span:
return "" # 没有找到 <span> 元素，返回空字符串
style = span.get("style", "")
match = re.search(r'url\(["\']?(.*?)["\']?\)', style)
return match.group(1) if match else "" # 解析成功返回 URL，否则返回空字符串
except Exception as e:
return "" # 发生异常时，返回空字符串
# 解析 HTML 内容，提取需要的数据
def parse_actors_uncensored(soup, href):
div_actors = soup.find("div", id='actors')
@ -123,6 +144,29 @@ def parse_actors_uncensored(soup, href):
# 解析 HTML 内容，提取需要的数据
def parse_actor_detail(soup, href):
# 先找一下别名
alias_list = []
div_meta = soup.find('span', class_='actor-section-name')
if not div_meta:
logging.warning(f'warning: no meta data found in page {href}')
return None, None
alias_div = soup.find('div', class_='column section-title')
if alias_div:
meta_list = alias_div.find_all('span', class_='section-meta')
if len(meta_list) > 1:
alias_list = meta_list[0].text.strip().split(", ")
# 头像
pic = ''
avatar = soup.find("div", class_="column actor-avatar")
if avatar:
pic = parse_avatar_image(avatar)
# 返回数据
actor = {}
div_movies = soup.find("div", class_='movie-list h cols-4 vcols-5')
if not div_movies:
logging.warning(f"Warning: No movies div found ")
@ -157,7 +201,13 @@ def parse_actor_detail(soup, href):
if next_page_number and next_page_number > current_page_number :
next_url = host_url + next_page_url
return list_data, next_url
actor = {
'pic' : pic,
'alias' : alias_list,
'movies' : list_data
}
return actor, next_url
# 解析 HTML 内容，提取需要的数据
@ -257,7 +307,7 @@ def parse_series_detail(soup, href):
div_movies = soup.find("div", class_='movie-list h cols-4 vcols-5')
if not div_movies:
logging.warning(f"Warning: No movies div found ")
return None, None
return [], None
# 解析元素
rows = div_movies.find_all('div', class_='item')
@ -337,7 +387,7 @@ def parse_maker_detail(soup, href):
div_movies = soup.find("div", class_='movie-list h cols-4 vcols-5')
if not div_movies:
logging.warning(f"Warning: No movies div found ")
return None, None
return [], None
# 解析元素
rows = div_movies.find_all('div', class_='item')

98
scripts/javdb/src/sqlite_utils.py
View File

@ -17,21 +17,42 @@ def get_id_by_href(table: str, href: str) -> int:
row = cursor.fetchone()
return row[0] if row else None
# 插入演员索引，来自于列表数据
def insert_actor_index(name, href):
def insert_actor_index(name, href, from_actor_list=None, from_movie_list=None):
try:
cursor.execute("""
INSERT OR IGNORE INTO javdb_actors (href, name) VALUES (?, ?)
""", (
href, name
))
# **查询是否已存在该演员**
cursor.execute("SELECT id, name, from_actor_list, from_movie_list FROM javdb_actors WHERE href = ?", (href,))
existing_actor = cursor.fetchone()
if existing_actor: # **如果演员已存在**
actor_id, existing_name, existing_actor_list, existing_movie_list = existing_actor
# **如果没有传入值，则保持原有值**
from_actor_list = from_actor_list if from_actor_list is not None else existing_actor_list
from_movie_list = from_movie_list if from_movie_list is not None else existing_movie_list
cursor.execute("""
UPDATE javdb_actors
SET name = ?,
from_actor_list = ?,
from_movie_list = ?,
updated_at = datetime('now', 'localtime')
WHERE href = ?
""", (name, from_actor_list, from_movie_list, href))
else: # **如果演员不存在，插入**
cursor.execute("""
INSERT INTO javdb_actors (href, name, from_actor_list, from_movie_list)
VALUES (?, ?, COALESCE(?, 0), COALESCE(?, 0))
""", (href, name, from_actor_list, from_movie_list))
conn.commit()
performer_id = get_id_by_href('javdb_actors', href)
if performer_id:
logging.debug(f'insert one actor index, id: {performer_id}, name: {name}, href: {href}')
logging.debug(f'Inserted/Updated actor index, id: {performer_id}, name: {name}, href: {href}')
return performer_id
return performer_id
except sqlite3.Error as e:
conn.rollback()
logging.error(f"数据库错误: {e}")
@ -41,28 +62,49 @@ def insert_actor_index(name, href):
logging.error(f"未知错误: {e}")
return None
# """插入电影索引，来自于列表数据"""
def insert_movie_index(title, href):
def insert_movie_index(title, href, from_actor_list=None, from_movie_makers=None, from_movie_series=None):
try:
# 插入或更新电影信息
cursor.execute("""
INSERT OR IGNORE INTO javdb_movies (title, href) VALUES (?, ?)
""",
(title, href)
)
# **先检查数据库中是否已有该电影**
cursor.execute("SELECT id, from_actor_list, from_movie_makers, from_movie_series FROM javdb_movies WHERE href = ?", (href,))
existing_movie = cursor.fetchone()
if existing_movie: # **如果电影已存在**
movie_id, existing_actor, existing_maker, existing_series = existing_movie
# **如果没有传入值，就用原来的值**
from_actor_list = from_actor_list if from_actor_list is not None else existing_actor
from_movie_makers = from_movie_makers if from_movie_makers is not None else existing_maker
from_movie_series = from_movie_series if from_movie_series is not None else existing_series
cursor.execute("""
UPDATE javdb_movies
SET title = ?,
from_actor_list = ?,
from_movie_makers = ?,
from_movie_series = ?,
updated_at = datetime('now', 'localtime')
WHERE href = ?
""", (title, from_actor_list, from_movie_makers, from_movie_series, href))
else: # **如果电影不存在，插入**
cursor.execute("""
INSERT INTO javdb_movies (title, href, from_actor_list, from_movie_makers, from_movie_series)
VALUES (?, ?, COALESCE(?, 0), COALESCE(?, 0), COALESCE(?, 0))
""", (title, href, from_actor_list, from_movie_makers, from_movie_series))
conn.commit()
movie_id = get_id_by_href('javdb_movies', href)
if movie_id:
logging.debug(f'insert one movie index, id: {movie_id}, title: {title}, href: {href}')
logging.debug(f'Inserted/Updated movie index, id: {movie_id}, title: {title}, href: {href}')
return movie_id
return movie_id
except Exception as e:
conn.rollback()
logging.error("Error inserting movie: %s", e)
logging.error(f"Error inserting/updating movie: {e}")
return None
# 插入演员和电影的关联数据
def insert_actor_movie(performer_id, movie_id, tags=''):
try:
@ -117,7 +159,7 @@ def insert_or_update_actor(actor):
movie_id = get_id_by_href('javdb_movies', movie['href'])
# 影片不存在，先插入
if movie_id is None:
movie_id = insert_movie_index(movie['title'], movie['href'])
movie_id = insert_movie_index(movie['title'], movie['href'], from_actor_list=1)
if movie_id:
tmp_id = insert_actor_movie(actor_id, movie_id)
if tmp_id :
@ -369,7 +411,7 @@ def insert_or_update_movie(movie):
performer_id = get_id_by_href('javdb_actors', performer['href'])
# 如果演员不存在，先插入
if performer_id is None:
performer_id = insert_actor_index(performer['name'], performer['href'])
performer_id = insert_actor_index(performer['name'], performer['href'], from_movie_list=1)
if performer_id:
tmp_id = insert_actor_movie(performer_id, movie_id)
if tmp_id:
@ -465,7 +507,13 @@ def insert_task_log():
INSERT INTO javdb_task_log (task_status) VALUES ('Start')
""")
conn.commit()
return cursor.lastrowid # 获取插入的 task_id
task_id = cursor.lastrowid
if task_id is None:
return None
update_task_log(task_id=task_id, task_status='Start')
return task_id # 获取插入的 task_id
except sqlite3.Error as e:
logging.error(f"插入任务失败: {e}")
return None

18
scripts/javdb/src/utils.py
View File

@ -0,0 +1,18 @@
import re
import os
import json
import time
import csv
from urllib.parse import urlparse
import logging
# 去掉 https://www.javdb.com/makers/16w?f=download 后面的参数
def remove_url_query(url: str) -> str:
try:
parsed_url = urlparse(url)
clean_url = f"{parsed_url.scheme}://{parsed_url.netloc}{parsed_url.path}"
return clean_url
except Exception as e:
print(f"解析 URL 失败: {e}")
return url

2
scripts/javhd/tools.py
View File

@ -93,7 +93,7 @@ def load_json(file_path):
return []
if __name__ == "__main__":
create_table()
#create_table()
json_data = load_json("./result/models_detail.json")
if json_data:
insert_data(json_data)

200
scripts/schema.sql
View File

@ -1,4 +1,3 @@
CREATE TABLE sqlite_sequence(name,seq);
CREATE TABLE IF NOT EXISTS "iafd_performers" (
id INTEGER PRIMARY KEY AUTOINCREMENT,
name TEXT NOT NULL,
@ -27,8 +26,15 @@ CREATE TABLE IF NOT EXISTS "iafd_performers" (
vixen_cnt INTEGER,
blacked_cnt INTEGER,
tushy_cnt INTEGER,
x_art_cnt INTEGER
);
x_art_cnt INTEGER,
is_full_data INTEGER DEFAULT (0) NOT NULL,
birth_year INTEGER DEFAULT (0) NOT NULL,
from_astro_list INTEGER DEFAULT (0) NOT NULL,
from_birth_list INTEGER DEFAULT (0) NOT NULL,
from_ethnic_list INTEGER DEFAULT (0) NOT NULL,
from_movie_list INTEGER DEFAULT (0) NOT NULL
);
CREATE TABLE sqlite_sequence(name,seq);
CREATE TABLE IF NOT EXISTS "iafd_performer_aliases" (
`performer_id` integer NOT NULL,
`alias` varchar(255) NOT NULL,
@ -44,59 +50,6 @@ CREATE TABLE IF NOT EXISTS "iafd_movies_appers_in" (
foreign key(`appears_in_id`) references "iafd_movies"(`id`) on delete CASCADE,
PRIMARY KEY (`movie_id`, `appears_in_id`)
);
CREATE TABLE IF NOT EXISTS "iafd_performer_urls" (
`performer_id` integer NOT NULL,
`position` varchar(255) NOT NULL,
`url` varchar(255) NOT NULL,
foreign key(`performer_id`) references "iafd_performers"(`id`) on delete CASCADE,
PRIMARY KEY(`performer_id`, `position`, `url`)
);
CREATE TABLE IF NOT EXISTS "iafd_distributors" (
`id` INTEGER NOT NULL PRIMARY KEY AUTOINCREMENT,
`name` VARCHAR(255) NOT NULL,
`href` VARCHAR(255) UNIQUE,
`parent_id` INTEGER DEFAULT NULL CHECK (`id` IS NOT `parent_id`) REFERENCES "iafd_distributors"(`id`) ON DELETE SET NULL,
`created_at` TEXT DEFAULT (datetime('now', 'localtime')),
`updated_at` TEXT DEFAULT (datetime('now', 'localtime')),
`details` TEXT
);
CREATE TABLE IF NOT EXISTS "iafd_studios" (
`id` INTEGER NOT NULL PRIMARY KEY AUTOINCREMENT,
`name` VARCHAR(255) NOT NULL,
`href` VARCHAR(255) UNIQUE,
`parent_id` INTEGER DEFAULT NULL CHECK (`id` IS NOT `parent_id`) REFERENCES "iafd_studios"(`id`) ON DELETE SET NULL,
`created_at` TEXT DEFAULT (datetime('now', 'localtime')),
`updated_at` TEXT DEFAULT (datetime('now', 'localtime')),
`details` TEXT
);
CREATE TABLE IF NOT EXISTS "iafd_performers_movies" (
`performer_id` integer,
`movie_id` integer,
`role` varchar(255),
`notes` varchar(255),
`created_at` TEXT DEFAULT (datetime('now', 'localtime')),
foreign key(`performer_id`) references "iafd_performers"(`id`) on delete CASCADE,
foreign key(`movie_id`) references "iafd_movies"(`id`) on delete CASCADE,
PRIMARY KEY (`movie_id`, `performer_id`)
);
CREATE TABLE IF NOT EXISTS "iafd_task_log" (
`task_id` integer not null primary key autoincrement,
`before_performers` integer,
`new_performers` integer,
`after_performers` integer,
`before_movies` integer,
`new_movies` integer,
`after_movies` integer,
`before_distributors` integer,
`new_distributors` integer,
`after_distributors` integer,
`before_studios` integer,
`new_studios` integer,
`after_studios` integer,
`task_status` varchar(255),
`created_at` TEXT DEFAULT (datetime('now', 'localtime')),
`updated_at` TEXT DEFAULT (datetime('now', 'localtime'))
);
CREATE TABLE IF NOT EXISTS "iafd_movies" (
`id` integer not null primary key autoincrement,
`title` varchar(255),
@ -112,10 +65,68 @@ CREATE TABLE IF NOT EXISTS "iafd_movies" (
`director_id` integer,
`href` varchar(255) UNIQUE,
`created_at` TEXT DEFAULT (datetime('now', 'localtime')),
`updated_at` TEXT DEFAULT (datetime('now', 'localtime')),
`updated_at` TEXT DEFAULT (datetime('now', 'localtime')),
is_full_data INTEGER DEFAULT (0) NOT NULL,
release_year INTEGER DEFAULT (0) NOT NULL,
from_performer_list INTEGER DEFAULT (0) NOT NULL,
from_dist_list INTEGER DEFAULT (0) NOT NULL,
from_stu_list INTEGER DEFAULT (0) NOT NULL,
foreign key(`studio_id`) references "iafd_studios"(`id`) on delete SET NULL,
foreign key(`distributor_id`) references "iafd_distributors"(`id`) on delete SET NULL
);
CREATE TABLE IF NOT EXISTS "iafd_performers_movies" (
`performer_id` integer,
`movie_id` integer,
`role` varchar(255),
`notes` varchar(255),
`created_at` TEXT DEFAULT (datetime('now', 'localtime')),
foreign key(`performer_id`) references "iafd_performers"(`id`) on delete CASCADE,
foreign key(`movie_id`) references "iafd_movies"(`id`) on delete CASCADE,
PRIMARY KEY (`movie_id`, `performer_id`)
);
CREATE TABLE IF NOT EXISTS "iafd_studios" (
`id` INTEGER NOT NULL PRIMARY KEY AUTOINCREMENT,
`name` VARCHAR(255) NOT NULL,
`href` VARCHAR(255) UNIQUE,
`parent_id` INTEGER DEFAULT NULL CHECK (`id` IS NOT `parent_id`) REFERENCES "iafd_studios"(`id`) ON DELETE SET NULL,
`created_at` TEXT DEFAULT (datetime('now', 'localtime')),
`updated_at` TEXT DEFAULT (datetime('now', 'localtime')),
`details` TEXT
);
CREATE TABLE IF NOT EXISTS "iafd_distributors" (
`id` INTEGER NOT NULL PRIMARY KEY AUTOINCREMENT,
`name` VARCHAR(255) NOT NULL,
`href` VARCHAR(255) UNIQUE,
`parent_id` INTEGER DEFAULT NULL CHECK (`id` IS NOT `parent_id`) REFERENCES "iafd_distributors"(`id`) ON DELETE SET NULL,
`created_at` TEXT DEFAULT (datetime('now', 'localtime')),
`updated_at` TEXT DEFAULT (datetime('now', 'localtime')),
`details` TEXT
);
CREATE TABLE IF NOT EXISTS "iafd_performer_urls" (
`performer_id` integer NOT NULL,
`position` varchar(255) NOT NULL,
`url` varchar(255) NOT NULL,
foreign key(`performer_id`) references "iafd_performers"(`id`) on delete CASCADE,
PRIMARY KEY(`performer_id`, `position`, `url`)
);
CREATE TABLE IF NOT EXISTS "iafd_task_log" (
`task_id` integer not null primary key autoincrement,
`full_data_performers` integer,
`total_performers` integer,
`full_data_movies` integer,
`total_movies` integer,
`total_distributors` integer,
`total_studios` integer,
`task_status` varchar(255),
`created_at` TEXT DEFAULT (datetime('now', 'localtime')),
`updated_at` TEXT DEFAULT (datetime('now', 'localtime'))
);
CREATE TABLE IF NOT EXISTS "iafd_meta_ethnic" (
`id` INTEGER NOT NULL PRIMARY KEY AUTOINCREMENT,
`name` VARCHAR(255) NOT NULL,
`href` VARCHAR(255) UNIQUE,
`created_at` TEXT DEFAULT (datetime('now', 'localtime'))
);
CREATE TABLE javhd_models (
id INTEGER PRIMARY KEY AUTOINCREMENT,
rank INTEGER,
@ -170,3 +181,78 @@ CREATE TABLE thelordofporn_alias (
FOREIGN KEY (actress_id) REFERENCES thelordofporn_actress(id) ON DELETE CASCADE,
PRIMARY KEY(`actress_id`, `alias`)
);
CREATE TABLE javdb_actors (
id INTEGER PRIMARY KEY AUTOINCREMENT,
name TEXT NOT NULL,
href TEXT UNIQUE NOT NULL,
pic TEXT,
created_at DATETIME DEFAULT (datetime('now', 'localtime')),
updated_at DATETIME DEFAULT (datetime('now', 'localtime')),
is_full_data INTEGER DEFAULT (0) NOT NULL,
from_actor_list INTEGER DEFAULT (0) NOT NULL,
from_movie_list INTEGER DEFAULT (0) NOT NULL
);
CREATE TABLE javdb_actors_alias (
actor_id INTEGER NOT NULL,
alias TEXT NOT NULL,
created_at DATETIME DEFAULT (datetime('now', 'localtime')),
updated_at DATETIME DEFAULT (datetime('now', 'localtime')),
PRIMARY KEY (actor_id, alias),
FOREIGN KEY (actor_id) REFERENCES javdb_actors(id) ON DELETE CASCADE
);
CREATE TABLE IF NOT EXISTS "javdb_makers" (
`id` INTEGER NOT NULL PRIMARY KEY AUTOINCREMENT,
`name` VARCHAR(255) NOT NULL,
`href` VARCHAR(255) UNIQUE,
`parent_id` INTEGER DEFAULT NULL CHECK (`id` IS NOT `parent_id`) REFERENCES "javdb_makers"(`id`) ON DELETE SET NULL,
`created_at` TEXT DEFAULT (datetime('now', 'localtime')),
`updated_at` TEXT DEFAULT (datetime('now', 'localtime')),
`details` TEXT
);
CREATE TABLE IF NOT EXISTS "javdb_series" (
`id` INTEGER NOT NULL PRIMARY KEY AUTOINCREMENT,
`name` VARCHAR(255) NOT NULL,
`href` VARCHAR(255) UNIQUE,
`parent_id` INTEGER DEFAULT NULL CHECK (`id` IS NOT `parent_id`) REFERENCES "javdb_series"(`id`) ON DELETE SET NULL,
`created_at` TEXT DEFAULT (datetime('now', 'localtime')),
`updated_at` TEXT DEFAULT (datetime('now', 'localtime')),
`details` TEXT
);
CREATE TABLE IF NOT EXISTS "javdb_movies" (
id INTEGER PRIMARY KEY AUTOINCREMENT,
href TEXT UNIQUE,
title TEXT,
cover_url TEXT,
serial_number TEXT,
release_date TEXT,
duration TEXT,
maker_id TEXT,
series_id TEXT,
is_full_data INTEGER DEFAULT (0) NOT NULL,
created_at TEXT DEFAULT (datetime('now', 'localtime')),
updated_at TEXT DEFAULT (datetime('now', 'localtime')),
from_actor_list INTEGER DEFAULT (0) NOT NULL,
from_movie_makers INTEGER DEFAULT (0) NOT NULL,
from_movie_series INTEGER DEFAULT (0) NOT NULL
);
CREATE TABLE IF NOT EXISTS "javdb_actors_movies" (
actor_id INTEGER,
movie_id INTEGER,
tags TEXT,
created_at TEXT DEFAULT (datetime('now', 'localtime')),
PRIMARY KEY (actor_id, movie_id),
FOREIGN KEY (actor_id) REFERENCES javdb_actors(id),
FOREIGN KEY (movie_id) REFERENCES "javdb_movies"(id)
);
CREATE TABLE IF NOT EXISTS "javdb_task_log" (
`task_id` integer not null primary key autoincrement,
`full_data_actors` integer,
`total_actors` integer,
`full_data_movies` integer,
`total_movies` integer,
`total_makers` integer,
`total_series` integer,
`task_status` varchar(255),
`created_at` TEXT DEFAULT (datetime('now', 'localtime')),
`updated_at` TEXT DEFAULT (datetime('now', 'localtime'))
);

2
scripts/thelordofporn/tools.py
View File

@ -147,7 +147,7 @@ def insert_actress(conn, actress):
def main():
setup_logging()
conn = connect_db()
create_tables(conn)
#create_tables(conn)
actresses = load_json("./result/actress_detail.json")
if actresses: