From d84757673cac4ae89c4e9639c776031f731ded17 Mon Sep 17 00:00:00 2001
From: test123456654321 <16307130148@fudan.edu.cn>
Date: Sat, 26 Oct 2024 14:47:00 +0800
Subject: [PATCH] dict
---
src/LunaTranslator/cishu/japandict.py | 37 +++++++++++++
src/LunaTranslator/cishu/jisho.py | 80 ++-------------------------
src/LunaTranslator/cishu/youdao.py | 16 ++++--
src/LunaTranslator/myutils/utils.py | 79 +++++++++++++++++++++++++-
src/files/defaultconfig/config.json | 4 ++
src/plugins/CMakeLists.txt | 2 +-
6 files changed, 136 insertions(+), 82 deletions(-)
create mode 100644 src/LunaTranslator/cishu/japandict.py
diff --git a/src/LunaTranslator/cishu/japandict.py b/src/LunaTranslator/cishu/japandict.py
new file mode 100644
index 00000000..b87b7f26
--- /dev/null
+++ b/src/LunaTranslator/cishu/japandict.py
@@ -0,0 +1,37 @@
+import requests
+from urllib.parse import quote
+from cishu.cishubase import cishubase
+from myutils.utils import get_element_by
+import threading, base64, re
+
+
+class japandict(cishubase):
+ def makelinkbase64(self, link, saver):
+ html = requests.get(
+ link,
+ proxies=self.proxy,
+ ).content
+ base64_content = base64.b64encode(html).decode("utf-8")
+ saver[link] = f"data:application/octet-stream;base64,{base64_content}"
+
+ def search(self, word):
+ url = "https://www.japandict.com/?s={}&lang=eng&list=1".format(quote(word))
+ html = requests.get(
+ url,
+ proxies=self.proxy,
+ ).text
+
+ res = get_element_by("class", "list-group list-group-flush", html)
+ if res is None:
+ return
+ ts = []
+ saver = {}
+ styles = ''
+ for link in re.findall('href="(.*?)"', styles):
+ ts.append(threading.Thread(target=self.makelinkbase64, args=(link, saver)))
+ ts[-1].start()
+ for t in ts:
+ t.join()
+ for link in saver:
+ styles = styles.replace(link, saver[link])
+ return res + styles
diff --git a/src/LunaTranslator/cishu/jisho.py b/src/LunaTranslator/cishu/jisho.py
index 7ff9c66a..322ddbe1 100644
--- a/src/LunaTranslator/cishu/jisho.py
+++ b/src/LunaTranslator/cishu/jisho.py
@@ -2,90 +2,21 @@ import requests
from urllib.parse import quote
import re
from cishu.cishubase import cishubase
-
-from html.parser import HTMLParser
-
-
-class IDParser(HTMLParser):
- """Modified HTMLParser that isolates a tag with the specified id"""
-
- def __init__(self, id):
- self.id = id
- self.result = None
- self.started = False
- self.depth = {}
- self.html = None
- self.watch_startpos = False
- HTMLParser.__init__(self)
-
- def loads(self, html):
- self.html = html
- self.feed(html)
- self.close()
-
- def handle_starttag(self, tag, attrs):
- attrs = dict(attrs)
- if self.started:
- self.find_startpos(None)
- if "id" in attrs and attrs["id"] == self.id:
- self.result = [tag]
- self.started = True
- self.watch_startpos = True
- if self.started:
- if not tag in self.depth:
- self.depth[tag] = 0
- self.depth[tag] += 1
-
- def handle_endtag(self, tag):
- if self.started:
- if tag in self.depth:
- self.depth[tag] -= 1
- if self.depth[self.result[0]] == 0:
- self.started = False
- self.result.append(self.getpos())
-
- def find_startpos(self, x):
- """Needed to put the start position of the result (self.result[1])
- after the opening tag with the requested id"""
- if self.watch_startpos:
- self.watch_startpos = False
- self.result.append(self.getpos())
-
- handle_entityref = handle_charref = handle_data = handle_comment = handle_decl = (
- handle_pi
- ) = unknown_decl = find_startpos
-
- def get_result(self):
- if self.result == None:
- return None
- if len(self.result) != 3:
- return None
- lines = self.html.split("\n")
- lines = lines[self.result[1][0] - 1 : self.result[2][0]]
- lines[0] = lines[0][self.result[1][1] :]
- if len(lines) == 1:
- lines[-1] = lines[-1][: self.result[2][1] - self.result[1][1]]
- lines[-1] = lines[-1][: self.result[2][1]]
- return "\n".join(lines).strip()
-
-
-def get_element_by_id(id, html):
- """Return the content of the tag with the specified id in the passed HTML document"""
- parser = IDParser(id)
- parser.loads(html)
- return parser.get_result()
+from myutils.utils import get_element_by
class jisho(cishubase):
def search(self, word):
- url = "https://jisho.org/word/{}".format(quote(word))
+ url = "https://jisho.org/search/{}".format(quote(word))
html = requests.get(
url,
proxies=self.proxy,
).text
- res = get_element_by_id("page_container", html)
+ if get_element_by("id", "no-matches", html):
+ return
+ res = get_element_by("id", "page_container", html)
if res is None:
return
res = (
@@ -94,6 +25,7 @@ class jisho(cishubase):
.replace(
'Log in to talk about this word.', ""
)
+ .replace(get_element_by("id", "other_dictionaries", html), "")
)
ss = re.search('href="https://assets.jisho.org/assets/application(.*)"', html)
diff --git a/src/LunaTranslator/cishu/youdao.py b/src/LunaTranslator/cishu/youdao.py
index 624a01c7..bf1dd163 100644
--- a/src/LunaTranslator/cishu/youdao.py
+++ b/src/LunaTranslator/cishu/youdao.py
@@ -4,16 +4,22 @@ from urllib.parse import quote
import re, os
from cishu.cishubase import cishubase
from myutils.utils import simplehtmlparser
+from myutils.utils import get_element_by
class youdao(cishubase):
- def search(self, word):
- url = "https://dict.youdao.com/result?word={}&lang={}".format(
- quote(word), getlangsrc()
- )
+ def search(self, word: str):
+ lang = getlangsrc()
+ if lang == "auto":
+ if word.isascii():
+ lang = "en"
+ else:
+ lang = "ja"
+ url = "https://dict.youdao.com/result?word={}&lang={}".format(quote(word), lang)
text = requests.get(url, proxies=self.proxy).text
-
+ if not get_element_by("class", "word-head", text):
+ return
text = re.sub("", "", text)
text = re.sub("", "", text)
diff --git a/src/LunaTranslator/myutils/utils.py b/src/LunaTranslator/myutils/utils.py
index 5f9d7405..8f76a8ac 100644
--- a/src/LunaTranslator/myutils/utils.py
+++ b/src/LunaTranslator/myutils/utils.py
@@ -21,6 +21,7 @@ from myutils.config import (
import threading, winreg
import re, heapq, winsharedutils
from myutils.wrapper import tryprint, threader
+from html.parser import HTMLParser
def qimage2binary(qimage: QImage, fmt="BMP"):
@@ -95,8 +96,12 @@ def getlanguagespace(lang=None):
def findenclose(text, tag):
i = 0
- tags = f"<{tag}"
- tage = f""
+ if tag == "link":
+ tags = ""
collect = ""
__ = 0
while True:
@@ -947,3 +952,73 @@ def createenglishlangmap():
)
mp.update({"auto": ""})
return mp
+
+
+class IDParser(HTMLParser):
+ """Modified HTMLParser that isolates a tag with the specified id"""
+
+ def __init__(self, attr, attrv):
+ self.id = attr, attrv
+ self.result = None
+ self.started = False
+ self.depth = {}
+ self.html = None
+ self.watch_startpos = False
+ HTMLParser.__init__(self)
+
+ def loads(self, html):
+ self.html = html
+ self.feed(html)
+ self.close()
+
+ def handle_starttag(self, tag, attrs):
+ attrs = dict(attrs)
+ if self.started:
+ self.find_startpos(None)
+ if self.id[0] in attrs and attrs[self.id[0]] == self.id[1]:
+ self.result = [tag]
+ self.started = True
+ self.watch_startpos = True
+ if self.started:
+ if not tag in self.depth:
+ self.depth[tag] = 0
+ self.depth[tag] += 1
+
+ def handle_endtag(self, tag):
+ if self.started:
+ if tag in self.depth:
+ self.depth[tag] -= 1
+ if self.depth[self.result[0]] == 0:
+ self.started = False
+ self.result.append(self.getpos())
+
+ def find_startpos(self, x):
+ """Needed to put the start position of the result (self.result[1])
+ after the opening tag with the requested id"""
+ if self.watch_startpos:
+ self.watch_startpos = False
+ self.result.append(self.getpos())
+
+ handle_entityref = handle_charref = handle_data = handle_comment = handle_decl = (
+ handle_pi
+ ) = unknown_decl = find_startpos
+
+ def get_result(self):
+ if self.result == None:
+ return None
+ if len(self.result) != 3:
+ return None
+ lines = self.html.split("\n")
+ lines = lines[self.result[1][0] - 1 : self.result[2][0]]
+ lines[0] = lines[0][self.result[1][1] :]
+ if len(lines) == 1:
+ lines[-1] = lines[-1][: self.result[2][1] - self.result[1][1]]
+ lines[-1] = lines[-1][: self.result[2][1]]
+ return "\n".join(lines).strip()
+
+
+def get_element_by(attr, attrv, html):
+ """Return the content of the tag with the specified id in the passed HTML document"""
+ parser = IDParser(attr, attrv)
+ parser.loads(html)
+ return parser.get_result()
diff --git a/src/files/defaultconfig/config.json b/src/files/defaultconfig/config.json
index 1c967a17..445537ea 100644
--- a/src/files/defaultconfig/config.json
+++ b/src/files/defaultconfig/config.json
@@ -1378,6 +1378,10 @@
"use": false,
"name": "jisho"
},
+ "japandict": {
+ "use": false,
+ "name": "JapanDict"
+ },
"weblio": {
"use": false,
"name": "weblio"
diff --git a/src/plugins/CMakeLists.txt b/src/plugins/CMakeLists.txt
index 419a5516..a0e9ad8c 100644
--- a/src/plugins/CMakeLists.txt
+++ b/src/plugins/CMakeLists.txt
@@ -29,7 +29,7 @@ include(generate_product_version)
set(VERSION_MAJOR 5)
set(VERSION_MINOR 50)
-set(VERSION_PATCH 1)
+set(VERSION_PATCH 2)
add_library(pch pch.cpp)
target_precompile_headers(pch PUBLIC pch.h)