python3+PyQt5 实现支持多线程的页面索引器应用程序

最新推荐文章于 2025-03-27 14:15:19 发布

basisworker

最新推荐文章于 2025-03-27 14:15:19 发布

阅读量2.1k

点赞数 1

分类专栏： PyQt5 python 文章标签： python pyqt

本文链接：https://blog.youkuaiyun.com/xiaoyangyang20/article/details/71375466

版权

本文介绍了一种使用Python3和PyQt5创建的多线程页面索引器应用程序。该程序展示了如何在Qt GUI中集成多线程技术，以实现高效地索引和处理网页内容。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

本文通过Python3+pyqt5实现了python Qt GUI 快速编程的19章的页面索引器应用程序例子。

/home/yrd/eric_workspace/chap19/walker_ans.py

#!/usr/bin/env python3

import codecs
import html.entities
import re
import sys
from PyQt5.QtCore import (QMutex, QThread,pyqtSignal,Qt)

class Walker(QThread):
    finished = pyqtSignal(bool,int)
    indexed = pyqtSignal(str,int)
    COMMON_WORDS_THRESHOLD = 250
    MIN_WORD_LEN = 3
    MAX_WORD_LEN = 25
    INVALID_FIRST_OR_LAST = frozenset("0123456789_")
    STRIPHTML_RE = re.compile(r"<[^>]*?>", re.IGNORECASE|re.MULTILINE)
    ENTITY_RE = re.compile(r"&(\w+?);|&#(\d+?);")
    SPLIT_RE = re.compile(r"\W+", re.IGNORECASE|re.MULTILINE)

    def __init__(self, index, lock, files, filenamesForWords,
                 commonWords, parent=None):
        super(Walker, self).__init__(parent)
        self.index = index
        self.lock = lock
        self.files = files
        self.filenamesForWords = filenamesForWords
        self.commonWords = commonWords
        self.stopped = False
        self.mutex = QMutex()
        self.completed = False


    def stop(self):
        try:
            self.mutex.lock()
            self.stopped = True
        finally:
            self.mutex.unlock()


    def isStopped(self):
        try:
            self.mutex.lock()
            return self.stopped
        finally:
            self.mutex.unlock()


    def run(self):
        self.processFiles()
        self.stop()
        self.finished.emit(self.completed,self.index)


    def processFiles(self):
        def unichrFromEntity(match):
            text = match.group(match.lastindex)
            if text.isdigit():
                return chr(int(text))
            u = html.entities.name2codepoint.get(text)
            return chr(u) if u is not None else ""

        for fname in self.files:
            if self.isStopped():
                return
            words = set()
            fh = None
            try:
                fh = codecs.open(fname, "r", "UTF8", "ignore")
                text = fh.read()
            except EnvironmentError as e:
                sys.stderr.write("Error: {0}\n".format(e))
                continue
            finally:
                if fh is not

最低0.47元/天解锁文章