PYTHON>>爬虫爬取小说

import requests
from bs4 import BeautifulSoup
import re
import time

# https://wwcom/28_28714/19953985.html
# https://wwwrg/83_83488/28981145.html

def URL00(a):
    url = 'https://wwworg/83_83488/'+ str(a) +'.html'
    return url

def DOWN00(a):
    strhtml=requests.get(URL00(a))
    strhtml.encoding = "UTF-8"
    soup = BeautifulSoup(strhtml.text,'lxml')

# 正文
# 选择“Copy”➔“Copy Selector”命令
    data02 = soup.select('#read > div.container > div:nth-child(3) > div > div.panel.panel-default > div.panel-body.content-body.content-ext')
    data02 = str(data02)
    data02 = re.findall(r'>(.*?)</div>', data02, re.S)
    data02 = ''.join(data02) + "\n"

# 标题、章节
    data01 = soup.select('#read > div.container > div:nth-child(3) > div > div.panel.panel-default > div.panel-heading')
    data01 = str(data01)
    data01 = re.findall(r'">(.*?)</div>', data01, re.S)
    data01 = ''.join(data01) + "\n\n"

    data = data01 + data02 + "=" * 40 + "\n\n"
    data = data.replace('<br/>','')
    data = data + "\n"
    return data

def SAVE00(data0):
    try:
        f = open(r"TXT0XZ.txt", 'a+',encoding='utf-8')
        f.write(data0)
        f.close()
    except IOError:
        f = open(r"TXT0XZ.txt", 'w',encoding='utf-8')
        f.write(data0)
        f.close()

def JINDU00(n):
    n = int(n)
    print('\r' + '#' * n + '=' * (100-n),end="")
    time.sleep(2)

if __name__ == "__main__":
    # for i in range(28981145,28981146):
    for i in range(28981145,28981337):
        n = (i - 28981145)/(28981337 - 28981145)*100
        JINDU00(n)
        TXT0 = DOWN00(i)
        SAVE00(TXT0)
    print("\n完成！")