1212logger = logging .getLogger ("uvicorn.error" )
1313
1414
15- async def single_page (headers : dict , url : str , file , session : aiohttp .ClientSession ) -> tuple [bytes , dict ]:
16- async with session .put (url , data = file , headers = headers ) as response :
17- headers = response .headers
18- text = await response .read ()
19- return (text , headers )
15+ async def single_page (headers , url , file_name : str , session ):
16+
17+ with open (file_name , "rb" ) as file :
18+ async with session .put (url , data = file , headers = headers ) as response :
19+ headers = response .headers
20+ text = await response .read ()
21+ return (text , headers )
2022
2123
2224async def page_requests (headers , url , file ):
@@ -33,8 +35,7 @@ async def page_requests(headers, url, file):
3335 pdf_writer = PdfWriter ()
3436 pdf_writer .add_page (pdf .pages [page ])
3537
36- out_file_name = os .path .abspath (
37- os .path .join (temp_dir , f"page-{ page :05d} .pdf" ))
38+ out_file_name = os .path .abspath (os .path .join (temp_dir , f"page-{ page :05d} .pdf" ))
3839
3940 if out_file_name .startswith (temp_dir ):
4041 with open (out_file_name , 'wb' ) as out :
@@ -53,11 +54,8 @@ async def page_requests(headers, url, file):
5354
5455 logger .info (f"Process page: { page } of { pages } " )
5556
56- file_name = pdf_pages [page ]
57- if file_name .startswith (temp_dir ):
58- with open (file_name , "rb" ) as file :
59- tasks .append (single_page (
60- headers , url , file , session ))
57+ tasks .append (single_page (
58+ headers , url , pdf_pages [page ], session ))
6159
6260 if len (tasks ) < CHUNK :
6361 continue
@@ -69,4 +67,4 @@ async def page_requests(headers, url, file):
6967 await data .async_collect (tasks )
7068 tasks .clear ()
7169
72- return data .get_request ()
70+ return data .get_request ()
0 commit comments