1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
|
from pathlib import PurePosixPath
from typing import Tuple
from urllib.error import HTTPError, URLError
from urllib.parse import urljoin, urlparse
from urllib.request import Request, urlopen
from epy_reader import __version__
from epy_reader.ebooks import Ebook
from epy_reader.lib import is_url
from epy_reader.models import BookMetadata
class URL(Ebook):
_header = {
"User-Agent": f"epy/v{__version__}",
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8",
"Accept-Language": "en-US,en;q=0.8",
}
def __init__(self, url: str):
self.path = url
self.file = url
self.contents = ("_",)
self.toc_entries = tuple()
def get_meta(self) -> BookMetadata:
return BookMetadata()
def initialize(self) -> None:
try:
with urlopen(Request(self.path, headers=URL._header)) as response:
self.html = response.read().decode()
except HTTPError as e:
raise e
except URLError as e:
raise e
def get_raw_text(self, _) -> str:
return self.html
def get_img_bytestr(self, src: str) -> Tuple[str, bytes]:
image_url = src if is_url(src) else urljoin(self.path, src)
# TODO: catch error on request
with urlopen(Request(image_url, headers=URL._header)) as response:
byte_str = response.read()
return PurePosixPath(urlparse(src).path).name, byte_str
def cleanup(self) -> None:
return
|
