Python自动化操作，批量获取网页源码

明心@Seeker

于 2023-10-14 15:11:26 发布

阅读量117

点赞数

文章标签：自动化 python

本文链接：https://blog.csdn.net/beyondlhp/article/details/131436272

版权

import pyautogui as gui
import pyperclip as pc
import pandas.io.clipboard as cb
import os
import time

gui.PAUSE = 1  # 调用在执行动作后暂停的秒数，只能在执行一些pyautogui动作后才能使用，建议用time.sleep
gui.FAILSAFE = True  # 启用自动防故障功能，左上角的坐标为（0，0），将鼠标移到屏幕的左上角，来抛出failSafeException异常

#url地址定位坐标
URL_BAR_X = 300
URL_BAR_Y = 50

#html元素定位坐标
HTML_ELEMEMT_X = 1225
HTML_ELEMEMT_Y = 191

#保存文档目录
SAVE_DIR = "xiaoshuo"

#获取内容
def get_content(url):
    pc.copy(url)
    gui.click(URL_BAR_X,URL_BAR_Y)
    gui.hotkey('ctrl','a')
    gui.hotkey('ctrl','v')
    gui.keyDown('enter')
    time.sleep(1)
    gui.click(HTML_ELEMEMT_X,HTML_ELEMEMT_Y,button='right')
    gui.moveTo(HTML_ELEMEMT_X+60,HTML_ELEMEMT_Y+36)
    gui.mouseDown()
    gui.mouseUp()
    gui.hotkey('ctrl','a')
    gui.hotkey('ctrl','c')
    html =cb.paste()
    return html

#清理内容
def clean_content(html):
    title = html[html.index('<title>')+7:html.index('</title>')]
    str = html[:html.index('<main')]
    body = html.replace(str,'')
    body = body[:body.index('</main>')+7]
    html = "<html><head><title>"+title+"</title></head><body>"+body+"</body></html>"
    return html

#保存内容
def save_content(fname,html):
    if not os.path.exists(SAVE_DIR):
        os.mkdir(SAVE_DIR)
    file = open(SAVE_DIR+'\\'+fname+'.html', 'w', encoding="UTF-8")
    file.write(html)


file = open('urls.txt', encoding='utf-8')
url = file.readline()
i=1
while url:
    print(i)
    html = get_content(url)
    html = clean_content(html)
    save_content(str(i),html)
    url = file.readline()
    i += 1