Merge pull request #631 from lededev/parallel-mapdown

parallel map download

ADC_function.py

@@ -15,6 +15,7 @@ import mechanicalsoup
 from requests.adapters import HTTPAdapter
 from urllib3.util.retry import Retry
 from cloudscraper import create_scraper
+from concurrent.futures import ThreadPoolExecutor
 
 
 def getXpathSingle(htmlcode, xpath):
@@ -490,9 +491,40 @@ def download_file_with_filename(url, filename, path):
     raise ValueError('[-]Connect Failed! Please check your Proxy or Network!')
     return
 
+def download_one_file(args):
+    def _inner(url: str, save_path: Path):
+        filebytes = get_html(url, return_type='content')
+        if isinstance(filebytes, bytes) and len(filebytes):
+            if len(filebytes) == save_path.open('wb').write(filebytes):
+                return str(save_path)
+    return _inner(*args)
+
+'''用法示例: 2线程同时下载两个不同文件，并保存到不同路径，路径目录可未创建，但需要具备对目标目录和文件的写权限
+parallel_download_files([
+    ('https://site1/img/p1.jpg', 'C:/temp/img/p1.jpg'),
+    ('https://site2/cover/n1.xml', 'C:/tmp/cover/n1.xml')
+    ])
+'''
+# dn_list 可以是 tuple或者list: ((url1, save_fullpath1),(url2, save_fullpath2),)
+# parallel: 并行下载的线程池线程数，为0则由函数自己决定
+def parallel_download_files(dn_list, parallel: int = 0):
+    mp_args = []
+    for url, fullpath in dn_list:
+        if url and isinstance(url, str) and url.startswith('http') and fullpath and isinstance(fullpath, (str, Path)) and len(str(fullpath)):
+            fullpath = Path(fullpath)
+            fullpath.parent.mkdir(parents=True, exist_ok=True)
+            mp_args.append((url, fullpath))
+    if not len(mp_args):
+        return []
+    if not isinstance(parallel, int) or parallel not in range(1,200):
+        parallel = min(5, len(mp_args))
+    with ThreadPoolExecutor(parallel) as pool:
+        results = list(pool.map(download_one_file, mp_args))
+    return results
+
 def delete_all_elements_in_list(string,lists):
     new_lists = []
     for i in lists:
         if i != string:
             new_lists.append(i)
-    return new_lists
+    return new_lists

AV_Data_Capture.py

@@ -14,7 +14,7 @@ import config
 from datetime import datetime, timedelta
 import time
 from pathlib import Path
-from ADC_function import  file_modification_days, get_html
+from ADC_function import  file_modification_days, get_html, parallel_download_files
 from number_parser import get_number
 from core import core_main, moveFailedFolder
 
@@ -473,18 +473,24 @@ def main():
     if conf.update_check():
         check_update(version)
 
-    # Download Mapping Table
-    if not os.path.exists(str(Path.home() / '.local' / 'share' / 'avdc' / 'mapping_actor.xml')):
-        ADC_function.download_file_with_filename(
+    # Download Mapping Table, parallel version
+    down_map_tab = []
+    actor_xml = Path.home() / '.local' / 'share' / 'avdc' / 'mapping_actor.xml'
+    if not actor_xml.exists():
+        down_map_tab.append((
             "https://raw.githubusercontent.com/yoshiko2/AV_Data_Capture/master/MappingTable/mapping_actor.xml",
-            "mapping_actor.xml", str(Path.home() / '.local' / 'share' / 'avdc'))
-        print("[+] [1/2] Mapping Table Downloaded")
-
-    if not os.path.exists(str(Path.home() / '.local' / 'share' / 'avdc' / 'mapping_info.xml')):
-        ADC_function.download_file_with_filename(
+            actor_xml))
+    info_xml = Path.home() / '.local' / 'share' / 'avdc' / 'mapping_info.xml'
+    if not info_xml.exists():
+        down_map_tab.append((
             "https://raw.githubusercontent.com/yoshiko2/AV_Data_Capture/master/MappingTable/mapping_info.xml",
-            "mapping_info.xml", str(Path.home() / '.local' / 'share' / 'avdc'))
-        print("[+] [2/2] Mapping Table Downloaded")
+            info_xml))
+    res = parallel_download_files(down_map_tab)
+    for i, fp in enumerate(res, start=1):
+        if fp and len(fp):
+            print(f"[+] [{i}/{len(res)}] Mapping Table Downloaded to {fp}")
+        else:
+            print(f"[-] [{i}/{len(res)}] Mapping Table Download failed")
 
     print(f"[+]Load Config file '{conf.ini_path}'.")
     if conf.debug():

core.py

@@ -9,7 +9,6 @@ from PIL import Image
 from io import BytesIO
 from pathlib import Path
 from datetime import datetime
-from concurrent.futures import ThreadPoolExecutor
 
 from ADC_function import *
 from WebCrawler import get_data_from_json
@@ -216,33 +215,24 @@ def extrafanart_download_one_by_one(data, path, filepath):
     if conf.debug():
         print(f'[!]Extrafanart download one by one mode runtime {time.perf_counter() - tm_start:.3f}s')
 
-def download_one_file(args):
-    def _inner(url: str, save_path: Path):
-        filebytes = get_html(url, return_type='content')
-        if isinstance(filebytes, bytes) and len(filebytes):
-            if len(filebytes) == save_path.open('wb').write(filebytes):
-                return str(save_path)
-    return _inner(*args)
 
 def extrafanart_download_threadpool(url_list, save_dir, number):
     tm_start = time.perf_counter()
     conf = config.getInstance()
     extrafanart_dir = Path(save_dir) / conf.get_extrafanart()
     download_only_missing_images = conf.download_only_missing_images()
-    mp_args = []
+    dn_list = []
     for i, url in enumerate(url_list, start=1):
         jpg_fullpath = extrafanart_dir /  f'extrafanart-{i}.jpg'
         if download_only_missing_images and not file_not_exist_or_empty(jpg_fullpath):
             continue
-        mp_args.append((url, jpg_fullpath))
-    if not len(mp_args):
+        dn_list.append((url, jpg_fullpath))
+    if not len(dn_list):
         return
-    extrafanart_dir.mkdir(parents=True, exist_ok=True)
-    parallel = min(len(mp_args), conf.extrafanart_thread_pool_download())
+    parallel = min(len(dn_list), conf.extrafanart_thread_pool_download())
     if parallel > 100:
         print('[!]Warrning: Parallel download thread too large may cause website ban IP!')
-    with ThreadPoolExecutor(parallel) as pool:
-        result = list(pool.map(download_one_file, mp_args))
+    result = parallel_download_files(dn_list, parallel)
     failed = 0
     for i, r in enumerate(result, start=1):
         if not r:
@@ -255,6 +245,7 @@ def extrafanart_download_threadpool(url_list, save_dir, number):
     if conf.debug():
         print(f'[!]Extrafanart download ThreadPool mode runtime {time.perf_counter() - tm_start:.3f}s')
 
+
 # 封面是否下载成功，否则移动到failed
 def image_download(cover, number, leak_word, c_word, path, filepath):
     filename = f"{number}{leak_word}{c_word}-fanart.jpg"