python3基于pyttsx3实现文本转语音，附带request、webdriver爬取

背景：之前爬了好几本小说，但又没有时间看（上班期间也不能看啊），所以就想转成语音，这样不就能听了嘛(ˉ﹃ˉ)

python版本：3.7.4
最开始是用3.8.x的，但是pyttsx3里面有很多坑，有一些模块仅支持到3.7.4，不支持以上的版本，所以最好使用3.7.4以下版本。

啥，你也是跟我一样是高版本的？最容易的操作如下：

1. 安装Miniconda，打开powershell，输入conda install python==3.7.4
   
   
2. 如果你之前不是用miniconda装的python，那就出现两个，一个是你原来的，另外一个在miniconda文件夹里面，所以我们需要改一下项目里的python版本，也可以改系统环境。File --> setting --> project --> show all --> +

3. 开始文本转语音pip install pyttsx3

import pyttsx3


def main():
    # 创建对象，有就使用旧的，没有就创建，单一原则
    engine = pyttsx3.init()
    # 设置新的语音速率，默认200
    engine.setProperty('rate', 180)
    # 设置新的语音音量，音量最小为 0，最大为 1，默认1
    engine.setProperty('volume', 1.0)
    # 获取当前语音声音的详细信息，这个是获取你电脑上语音识别的语音列表
    # voices = engine.getProperty('voices')
    # 设置当前语音声音，根据自己的语音列表设置
    engine.setProperty('voice', voices[0].id)
    # 语音文本
    out_file = 'text2audio.mp3'
    in_file = '完美世界.txt'
    f = open(in_file, 'r', encoding='utf-8')
    my_text = f.read()
    f.close()
    # 将语音文本说出来
    # engine.say(my_text )
    # 将文本转换成音频，并输出到out_file
    engine.save_to_file(my_text , out_file)
    engine.runAndWait()
    engine.stop()


if __name__ == '__main__':
    main()

4. 附带小说爬取代码，request版

import datetime
import random
import time

import requests
from bs4 import BeautifulSoup


def get_html(url, headers):
    r = requests.get(url, headers=headers)
    r.encoding = r.apparent_encoding
    return r.text


def get_wanMeiShiJie(html, f):
    soup = BeautifulSoup(html, "html.parser")
    # 章节标题
    title = soup.find("div", class_="bookname").find("h1").string
    # 章节内容
    all_content = soup.find("div", id="content").text
    f.write(title + "\n\n")
    f.write(all_content + "\n\n")
    print(title + "  ----爬取完成")


def main():
    # 开始时间
    start_time = datetime.datetime.now()

    url = "https://www.xbiquge.la"
    start_url = "/26/26874/"
    headers = {"user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) "
                             "Chrome/96.0.4664.45 Safari/537.36"}

    temp_url = start_url

    f = open('沧元图.txt', 'w', encoding='utf-8')
    # 每max_size章 暂停sleep_time秒
    max_size = random.randint(50, 200)
    chapter_size = 0
    html = get_html(url + temp_url, headers)
    soup = BeautifulSoup(html, "html.parser")
    list_name = set()
    list_href = []
    list_a = soup.find('div', id="list").find_all('a')
    again_ = 1
    for _a in list_a:
        # if -1 < str(_a.text).find('第四千八百七十六章', 0, len(_a.text)):
        #     again_ = 1
        #     continue
        if again_ == 0 or _a.text in list_name:
            continue
        else:
            list_name.add(_a.text)
            list_href.append(_a['href'])

    print("【遍历所有章节，并进行章节去重】，完成")
    for href in list_href:
        html = get_html(url + href, headers)
        get_wanMeiShiJie(html, f)
        chapter_size += 1
        if max_size <= chapter_size:
            chapter_size = 0
            sleep_time = random.uniform(0.5, 5)
            print("----------已爬取" + str(max_size) + "章，休息" + str(sleep_time) + "秒----------")
            max_size = random.randint(50, 200)
            time.sleep(sleep_time)

    f.close()

    print("爬取结束，总耗时：")
    print(datetime.datetime.now() - start_time)


if __name__ == '__main__':
    main()

5. 附带小说爬取代码，webdriver版

from selenium import webdriver
from bs4 import BeautifulSoup
from selenium.webdriver.support.wait import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC


def get_html(url, driver, title):
    driver.get(url)
    # 显示等待，10秒内，直到title标签包含title字符串，才返回页面
    WebDriverWait(driver, 10).until(EC.title_contains(title))

    return driver.page_source


def main():
    urls = [
        "http://www.7pingtan.com/archives/3199",
        "http://www.7pingtan.com/archives/2987",
        "http://www.7pingtan.com/archives/2450"
    ]

    driver = None
    f = None
    try:
        driver = webdriver.Chrome()
        f = open('平潭蓝眼泪.txt', 'w', encoding='utf-8')
        for url in urls:
            html = get_html(url, driver, "平潭蓝眼泪")
            soup = BeautifulSoup(html, "html.parser")
            _main = soup.find("div", id="content").find("div", class_="main").find("div", class_="content")
            all_url = _main.find_all("a")
            for index, temp_url in enumerate(all_url):
                if 0 == index or 1 == index:
                    continue
                _url = temp_url["href"]
                _html = get_html(_url, driver, "平潭蓝眼泪")
                soup = BeautifulSoup(_html, "html.parser")
                # 内容
                _main = soup.find("div", id="content").find("div", class_="content")
                all_content = _main.find_all("p")
                for content in all_content:
                    str = content.text
                    if ("蓝眼泪" not in str) or ("（无）" in str):
                        break
                    strs = str.split("蓝眼泪实况：")
                    begin_time = strs[0].replace("夜光藻", "")
                    temp_strs = strs[1].split("。")
                    f.write(temp_strs[0] + begin_time + "\n")
    except Exception as e:
        print(e)
    finally:
        if None is not f:
            f.close()
        if None is not driver:
            driver.close()


if __name__ == '__main__':
    main()

总结：不要让生活难倒你，摸鱼的方法有很多。