Initial commit
This commit is contained in:
57
opf_parse.py
Normal file
57
opf_parse.py
Normal file
@@ -0,0 +1,57 @@
|
||||
|
||||
# parseopf.py
|
||||
# -----------------------------
|
||||
# 用于解析EPUB电子书的OPF文件,提取manifest部分所有id对应的html文件href。
|
||||
# 支持批量测试和通过id快速查找href。
|
||||
# 依赖:BeautifulSoup4
|
||||
# -----------------------------
|
||||
|
||||
from collections import defaultdict
|
||||
from bs4 import BeautifulSoup
|
||||
import pprint
|
||||
|
||||
|
||||
def parse_opf(filepath):
|
||||
"""
|
||||
解析OPF文件,返回{id: href}的defaultdict(dict)结构。
|
||||
仅保留href以.html结尾的项。
|
||||
|
||||
参数:
|
||||
filepath (str): OPF文件路径
|
||||
返回:
|
||||
defaultdict(dict): id到href的映射(仅html文件)
|
||||
"""
|
||||
result = defaultdict(dict)
|
||||
with open(filepath, 'r', encoding='utf-8') as f:
|
||||
soup = BeautifulSoup(f, 'xml')
|
||||
# 查找manifest部分,遍历所有item,筛选html结尾的href
|
||||
manifest = soup.find('manifest')
|
||||
if manifest:
|
||||
for item in manifest.find_all('item'):
|
||||
id_ = item.get('id')
|
||||
href = item.get('href')
|
||||
if id_ and href and href.strip().lower().endswith('html'):
|
||||
result[id_] = href
|
||||
return result
|
||||
|
||||
if __name__ == "__main__":
|
||||
test_files = [
|
||||
'./examples/epub_format_2/OEBPS/content.opf',
|
||||
'./examples/epub_format_4/item/standard.opf',
|
||||
'./examples/epub_format_3/OEBPS/content.opf',
|
||||
'./examples/epub_format_1/content.opf',
|
||||
]
|
||||
for file in test_files:
|
||||
print(f"\n==== 测试文件: {file} ====")
|
||||
try:
|
||||
result = parse_opf(file)
|
||||
pprint.pprint(result, indent=2, width=120, sort_dicts=False)
|
||||
|
||||
# 增加通过id快速打印href的测试
|
||||
test_ids = list(result.keys())[:3] # 取前三个id做演示
|
||||
for test_id in test_ids:
|
||||
print(f"id: {test_id} -> href: {result[test_id]}")
|
||||
|
||||
except Exception as e:
|
||||
print(f"解析失败: {e}")
|
||||
|
||||
Reference in New Issue
Block a user