Kris
432d5db970
完成Help Scout渠道的完整功能实现，包含API客户端、webhook处理、轮询同步、自动回复、工单标签分配、客户资料管理等核心能力，附带完整的配置Schema与插件元信息
145 lines
3.9 KiB
Python
145 lines
3.9 KiB
Python
from __future__ import annotations
|
|
|
|
import logging
|
|
import re
|
|
from html import unescape
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
try:
|
|
from bs4 import BeautifulSoup
|
|
|
|
HAS_BS4 = True
|
|
except ImportError:
|
|
HAS_BS4 = False
|
|
logger.warning("beautifulsoup4 not installed — Help Scout HTML parsing will use fallback regex")
|
|
|
|
_EMAIL_QUOTE_PATTERNS = [
|
|
re.compile(r"^On\s+.*wrote:\s*$", re.IGNORECASE | re.MULTILINE),
|
|
re.compile(r"^>{1,}\s?", re.MULTILINE),
|
|
re.compile(r"^-{2,}\s*Original Message\s*-{2,}", re.IGNORECASE),
|
|
re.compile(r"^From:\s+.*$", re.IGNORECASE | re.MULTILINE),
|
|
re.compile(r"^Sent:\s+.*$", re.IGNORECASE | re.MULTILINE),
|
|
re.compile(r"^To:\s+.*$", re.IGNORECASE | re.MULTILINE),
|
|
re.compile(r"^Subject:\s+.*$", re.IGNORECASE | re.MULTILINE),
|
|
re.compile(r"^Date:\s+.*$", re.IGNORECASE | re.MULTILINE),
|
|
]
|
|
|
|
|
|
def html_to_text(html_body: str) -> str:
|
|
if not html_body:
|
|
return ""
|
|
|
|
if HAS_BS4:
|
|
return _bs4_html_to_text(html_body)
|
|
return _regex_html_to_text(html_body)
|
|
|
|
|
|
def _bs4_html_to_text(html_body: str) -> str:
|
|
soup = BeautifulSoup(html_body, "html.parser")
|
|
|
|
for tag in soup(["style", "script", "head"]):
|
|
tag.decompose()
|
|
|
|
for a_tag in soup.find_all("a", href=True):
|
|
text = a_tag.get_text(strip=True)
|
|
url = a_tag["href"]
|
|
if text and url:
|
|
a_tag.replace_with(f"[{text}]({url})")
|
|
|
|
for br in soup.find_all("br"):
|
|
br.replace_with("\n")
|
|
|
|
for p in soup.find_all("p"):
|
|
p.insert_before("\n")
|
|
p.insert_after("\n")
|
|
p.unwrap()
|
|
|
|
for tag in soup.find_all(["strong", "b"]):
|
|
if tag.string:
|
|
tag.string.replace_with(f"**{tag.string}**")
|
|
tag.unwrap()
|
|
|
|
for tag in soup.find_all(["em", "i"]):
|
|
if tag.string:
|
|
tag.string.replace_with(f"*{tag.string}*")
|
|
tag.unwrap()
|
|
|
|
for li in soup.find_all("li"):
|
|
li.insert_before("- ")
|
|
li.insert_after("\n")
|
|
li.unwrap()
|
|
|
|
text = soup.get_text(separator="\n")
|
|
text = unescape(text)
|
|
text = strip_email_quote(text)
|
|
text = re.sub(r"\n{3,}", "\n\n", text)
|
|
|
|
return text.strip()
|
|
|
|
|
|
def _regex_html_to_text(html_body: str) -> str:
|
|
import html
|
|
|
|
text = html_body
|
|
|
|
for tag in ("style", "script", "head"):
|
|
text = re.sub(
|
|
f"<{tag}[^>]*>.*?</{tag}>",
|
|
"",
|
|
text,
|
|
flags=re.DOTALL | re.IGNORECASE,
|
|
)
|
|
|
|
text = re.sub(
|
|
r'<a\s[^>]*href=["\']([^"\']*)["\'][^>]*>(.*?)</a>',
|
|
r"[\2](\1)",
|
|
text,
|
|
flags=re.DOTALL,
|
|
)
|
|
text = re.sub(r"<br\s*/?>", "\n", text, flags=re.IGNORECASE)
|
|
text = re.sub(r"<p[^>]*>", "\n", text, flags=re.IGNORECASE)
|
|
text = re.sub(r"</p>", "\n", text, flags=re.IGNORECASE)
|
|
text = re.sub(
|
|
r"<(?:strong|b)[^>]*>(.*?)</(?:strong|b)>",
|
|
r"**\1**",
|
|
text,
|
|
flags=re.DOTALL,
|
|
)
|
|
text = re.sub(r"<(?:em|i)[^>]*>(.*?)</(?:em|i)>", r"*\1*", text, flags=re.DOTALL)
|
|
text = re.sub(r"<li[^>]*>(.*?)</li>", r"- \1\n", text, flags=re.DOTALL)
|
|
text = re.sub(r"<[^>]+>", "", text)
|
|
text = html.unescape(text)
|
|
text = strip_email_quote(text)
|
|
text = re.sub(r"\n{3,}", "\n\n", text)
|
|
text = re.sub(r"[ \t]{2,}", " ", text)
|
|
|
|
return text.strip()
|
|
|
|
|
|
def strip_email_quote(text: str) -> str:
|
|
lines = text.split("\n")
|
|
cleaned_lines = []
|
|
|
|
for line in lines:
|
|
is_quote = False
|
|
for pattern in _EMAIL_QUOTE_PATTERNS:
|
|
if pattern.match(line.strip()):
|
|
is_quote = True
|
|
break
|
|
|
|
if not is_quote:
|
|
cleaned_lines.append(line)
|
|
else:
|
|
break
|
|
|
|
return "\n".join(cleaned_lines)
|
|
|
|
|
|
def extract_plain_text(text: str, max_length: int = 500) -> str:
|
|
plain = re.sub(r"[#*_>\-\[\]\(\)]", "", text)
|
|
plain = re.sub(r"\s+", " ", plain).strip()
|
|
if len(plain) > max_length:
|
|
plain = plain[: max_length - 3] + "..."
|
|
return plain
|