LonamiWebs/Telethon
1
1
Fork 0
mirror of https://github.com/LonamiWebs/Telethon.git synced 2025-09-19 02:12:40 +03:00
Code Issues Packages Projects Releases Wiki Activity

feat: Support <blockquote expandable> info: https://core.telegram.org/bots/api#html-style

Browse Source
This commit is contained in:
HBcao233 2024-10-03 23:33:51 +08:00
parent f652f3f01a
commit a654ee4972
1 changed files with 56 additions and 40 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

96
telethon/extensions/html.py
View File

@ -1,6 +1,7 @@
""" """
Simple HTML -> Telegram entity parser. Simple HTML -> Telegram entity parser.
""" """
from collections import deque from collections import deque
from html import escape from html import escape
from html.parser import HTMLParser from html.parser import HTMLParser
@ -9,18 +10,25 @@ from typing import Iterable, Tuple, List
from ..helpers import add_surrogate, del_surrogate, within_surrogate, strip_text from ..helpers import add_surrogate, del_surrogate, within_surrogate, strip_text
from ..tl import TLObject from ..tl import TLObject
from ..tl.types import ( from ..tl.types import (
MessageEntityBold, MessageEntityItalic, MessageEntityCode, MessageEntityBold,
MessageEntityPre, MessageEntityEmail, MessageEntityUrl, MessageEntityItalic,
MessageEntityTextUrl, MessageEntityMentionName, MessageEntityCode,
MessageEntityUnderline, MessageEntityStrike, MessageEntityBlockquote, MessageEntityPre,
TypeMessageEntity MessageEntityEmail,
MessageEntityUrl,
MessageEntityTextUrl,
MessageEntityMentionName,
MessageEntityUnderline,
MessageEntityStrike,
MessageEntityBlockquote,
TypeMessageEntity,
) )
class HTMLToTelegramParser(HTMLParser): class HTMLToTelegramParser(HTMLParser):
def __init__(self): def __init__(self):
super().__init__() super().__init__()
self.text = '' self.text = ""
self.entities = [] self.entities = []
self._building_entities = {} self._building_entities = {}
self._open_tags = deque() self._open_tags = deque()
@ -33,17 +41,19 @@ class HTMLToTelegramParser(HTMLParser):
attrs = dict(attrs) attrs = dict(attrs)
EntityType = None EntityType = None
args = {} args = {}
if tag == 'strong' or tag == 'b': if tag == "strong" or tag == "b":
EntityType = MessageEntityBold EntityType = MessageEntityBold
elif tag == 'em' or tag == 'i': elif tag == "em" or tag == "i":
EntityType = MessageEntityItalic EntityType = MessageEntityItalic
elif tag == 'u': elif tag == "u":
EntityType = MessageEntityUnderline EntityType = MessageEntityUnderline
elif tag == 'del' or tag == 's': elif tag == "del" or tag == "s":
EntityType = MessageEntityStrike EntityType = MessageEntityStrike
elif tag == 'blockquote': elif tag == "blockquote":
EntityType = MessageEntityBlockquote EntityType = MessageEntityBlockquote
elif tag == 'code': if "expandable" in attrs.keys():
args["collapsed"] = True
elif tag == "code":
try: try:
# If we're in the middle of a <pre> tag, this <code> tag is # If we're in the middle of a <pre> tag, this <code> tag is
# probably intended for syntax highlighting. # probably intended for syntax highlighting.
@ -51,30 +61,30 @@ class HTMLToTelegramParser(HTMLParser):
# Syntax highlighting is set with # Syntax highlighting is set with
# <code class='language-...'>codeblock</code> # <code class='language-...'>codeblock</code>
# inside <pre> tags # inside <pre> tags
pre = self._building_entities['pre'] pre = self._building_entities["pre"]
try: try:
pre.language = attrs['class'][len('language-'):] pre.language = attrs["class"][len("language-") :]
except KeyError: except KeyError:
pass pass
except KeyError: except KeyError:
EntityType = MessageEntityCode EntityType = MessageEntityCode
elif tag == 'pre': elif tag == "pre":
EntityType = MessageEntityPre EntityType = MessageEntityPre
args['language'] = '' args["language"] = ""
elif tag == 'a': elif tag == "a":
try: try:
url = attrs['href'] url = attrs["href"]
except KeyError: except KeyError:
return return
if url.startswith('mailto:'): if url.startswith("mailto:"):
url = url[len('mailto:'):] url = url[len("mailto:") :]
EntityType = MessageEntityEmail EntityType = MessageEntityEmail
else: else:
if self.get_starttag_text() == url: if self.get_starttag_text() == url:
EntityType = MessageEntityUrl EntityType = MessageEntityUrl
else: else:
EntityType = MessageEntityTextUrl EntityType = MessageEntityTextUrl
args['url'] = del_surrogate(url) args["url"] = del_surrogate(url)
url = None url = None
self._open_tags_meta.popleft() self._open_tags_meta.popleft()
self._open_tags_meta.appendleft(url) self._open_tags_meta.appendleft(url)
@ -84,11 +94,12 @@ class HTMLToTelegramParser(HTMLParser):
offset=len(self.text), offset=len(self.text),
# The length will be determined when closing the tag. # The length will be determined when closing the tag.
length=0, length=0,
**args) **args,
)
def handle_data(self, text): def handle_data(self, text):
previous_tag = self._open_tags[0] if len(self._open_tags) > 0 else '' previous_tag = self._open_tags[0] if len(self._open_tags) > 0 else ""
if previous_tag == 'a': if previous_tag == "a":
url = self._open_tags_meta[0] url = self._open_tags_meta[0]
if url: if url:
text = url text = url
@ -129,23 +140,23 @@ def parse(html: str) -> Tuple[str, List[TypeMessageEntity]]:
ENTITY_TO_FORMATTER = { ENTITY_TO_FORMATTER = {
MessageEntityBold: ('<strong>', '</strong>'), MessageEntityBold: ("<strong>", "</strong>"),
MessageEntityItalic: ('<em>', '</em>'), MessageEntityItalic: ("<em>", "</em>"),
MessageEntityCode: ('<code>', '</code>'), MessageEntityCode: ("<code>", "</code>"),
MessageEntityUnderline: ('<u>', '</u>'), MessageEntityUnderline: ("<u>", "</u>"),
MessageEntityStrike: ('<del>', '</del>'), MessageEntityStrike: ("<del>", "</del>"),
MessageEntityBlockquote: ('<blockquote>', '</blockquote>'), MessageEntityBlockquote: ("<blockquote>", "</blockquote>"),
MessageEntityPre: lambda e, _: ( MessageEntityPre: lambda e, _: (
"<pre>\n" "<pre>\n" " <code class='language-{}'>\n" " ".format(e.language),
" <code class='language-{}'>\n" "{}\n" " </code>\n" "</pre>",
" ".format(e.language), "{}\n" ),
" </code>\n" MessageEntityEmail: lambda _, t: ('<a href="mailto:{}">'.format(t), "</a>"),
"</pre>" MessageEntityUrl: lambda _, t: ('<a href="{}">'.format(t), "</a>"),
MessageEntityTextUrl: lambda e, _: ('<a href="{}">'.format(escape(e.url)), "</a>"),
MessageEntityMentionName: lambda e, _: (
'<a href="tg://user?id={}">'.format(e.user_id),
"</a>",
), ),
MessageEntityEmail: lambda _, t: ('<a href="mailto:{}">'.format(t), '</a>'),
MessageEntityUrl: lambda _, t: ('<a href="{}">'.format(t), '</a>'),
MessageEntityTextUrl: lambda e, _: ('<a href="{}">'.format(escape(e.url)), '</a>'),
MessageEntityMentionName: lambda e, _: ('<a href="tg://user?id={}">'.format(e.user_id), '</a>'),
} }
@ -186,7 +197,12 @@ def unparse(text: str, entities: Iterable[TypeMessageEntity]) -> str:
while within_surrogate(text, at): while within_surrogate(text, at):
at += 1 at += 1
text = text[:at] + what + escape(text[at:next_escape_bound]) + text[next_escape_bound:] text = (
text[:at]
+ what
+ escape(text[at:next_escape_bound])
+ text[next_escape_bound:]
)
next_escape_bound = at next_escape_bound = at
text = escape(text[:next_escape_bound]) + text[next_escape_bound:] text = escape(text[:next_escape_bound]) + text[next_escape_bound:]