William/comic_book_downloader
William/comic_book_downloader
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

优化代码

Browse Source
This commit is contained in:
vincent 2023-07-21 16:59:38 +08:00
parent 4d2635fba8
commit ffd9e70346
1 changed files with 11 additions and 37 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

48
main.py
View File

@ -2,12 +2,8 @@ import os
import requests
from bs4 import BeautifulSoup
from concurrent.futures import ThreadPoolExecutor
from PIL import Image
import io
from reportlab.lib.pagesizes import letter
from reportlab.pdfgen import canvas
def get_html(url, max_retries=3):
@ -52,10 +48,11 @@ def get_img_urls(html_content):
return img_urls
def create_img_obj_list(img_url_list):
def create_img_obj_list(img_url_list, file_name):
img_obj_list = []
for url in img_url_list:
obj = dict()
obj["file_name"] = file_name
obj["url"] = url
obj["data"] = None
img_obj_list.append(obj)
@ -67,35 +64,11 @@ def set_img_obj_data(img_obj):
url = img_obj["url"]
data = download_image(url)
if data is None:
raise Exception("下载图片失败")
file_name = img_obj["file_name"]
raise Exception(f"{file_name}, 下载图片失败")
img_obj["data"] = data
def save_images_to_directory(img_obj_list, directory_path):
try:
# 创建保存图片的目录（如果不存在）
os.makedirs(directory_path, exist_ok=True)
for idx, img_obj in enumerate(img_obj_list):
url = img_obj["url"]
data = img_obj["data"]
# 获取图片的扩展名（假设url以图片扩展名结尾）
extension = os.path.splitext(url)[1]
# 图片文件名，这里用序号作为文件名
file_name = f"image_{idx}{extension}"
file_path = os.path.join(directory_path, file_name)
# 将图片数据写入本地文件
with open(file_path, "wb") as file:
file.write(data)
print("图片保存成功！")
except Exception as e:
print(f"图片保存失败：{e}")
def concatenate_images_vertically(img_obj_list, output_file):
try:
# 计算拼接后的长图宽度和总高度
@ -120,10 +93,10 @@ def concatenate_images_vertically(img_obj_list, output_file):
# 保存拼接后的长图到本地
long_image.save(output_file)
except Exception as e:
print(f"拼接图片失败：{e}")
file_name = img_obj_list[0]["file_name"]
print(f"{file_name}, 拼接图片失败：{e}")
return None
@ -135,24 +108,23 @@ def process_batch(lines):
file_name, _, url = line.partition(" - ")
html_content = get_html(url)
img_url_list = get_img_urls(html_content)
img_obj_list = create_img_obj_list(img_url_list)
img_obj_list = create_img_obj_list(img_url_list, file_name)
# 使用 ThreadPoolExecutor 创建线程池
with ThreadPoolExecutor() as executor:
# 多线程处理图片下载和替换
executor.map(set_img_obj_data, img_obj_list)
# save_images_to_directory(img_obj_list, directory_path="imgs")
concatenate_images_vertically(
img_obj_list, output_file=f"imgs/{file_name}.png"
)
if __name__ == "__main__":
file_name = "input.txt"
task_file = "input.txt"
batch_size = 3 # 每个线程处理的行数
with open(file_name, "r", encoding="utf-8") as file:
with open(task_file, "r", encoding="utf-8") as file:
lines = file.readlines()
# 使用 ThreadPoolExecutor 创建线程池
@ -161,3 +133,5 @@ if __name__ == "__main__":
for i in range(0, len(lines), batch_size):
batch_lines = lines[i : i + batch_size]
executor.submit(process_batch, batch_lines)
print("finish, 程序结束...")