python爬虫類-筆趣閣

from urllib.request import quote, unquote
import requests
from bs4 import BeautifulSoup
import sys
import time

content = input('            ：')
initial_content = content
keyword = quote(initial_content,encoding='gb2312')
url = 'http://www.biquge.com.tw/modules/article/soshu.php?searchkey='+keyword
print(url)
re = requests.get(url)   #     url
retype=re.apparent_encoding
re.encoding = retype
print(re.status_code)
html = re.text
soup = BeautifulSoup(html, 'html.parser')
fileName = '/Users/john/Desktop/  /'+initial_content+'.txt'
print(fileName)
file = open(fileName, 'a', encoding='utf-8')

chapters = soup.find_all(id='list')
info = soup.find_all(id='info')
for link in info:
    file.write(link.get_text())#      
download_soup = BeautifulSoup(str(chapters), 'html.parser')

arr = []
for child in download_soup.dl.children:    #dl      
    if hasattr(child, 'href') and child.a != None:
        arr.append(child.get_text())
numbel = len(arr)
print(numbel)
index= 1
time1 = time.time ()#      （ ）
for child in download_soup.dl.children:     #dl      
    if hasattr(child, 'href') and child.a != None:
        file.write(child.get_text() + '
' + '-----------------------------------------------' + '
')
        url = 'http://www.biquge.com.tw/' + child.a['href']
        # print(url)
        reponse_dl = requests.get(url)
        type_dl = reponse_dl.apparent_encoding
        reponse_dl.encoding = type_dl
        html_dl = reponse_dl.text
        soup_dl = BeautifulSoup(html_dl, 'html.parser')
        contents = soup_dl.find_all(id='content')   #  

        for link in contents:
            #print(link.get_text())
            file.write(link.get_text() + '

')
        print("   :%.3f%%" % float(index / numbel*100))#    
        index += 1
time2 = time.time()
tt = (time2 - time1)
print('    ：' + str(tt) + ' ')
file.close()
     ，                ，   macox  ，window                  。        BeautifulSoup,           ，    。