1. import  requests
    2. from bs4 import  BeautifulSoup
    4. headers={
    5.     'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36 QIHU 360S'
    6. }
    7. url='https://www.shicimingju.com/book/sanguoyanyi.html'
    8. page_text=requests.get(url=url,headers=headers).text
    9. #encode编码，将ISO-8859-1编码成unicode
    10. page_text=page_text.encode("ISO-8859-1")
    11. #decode解码,将unicode解码成utf-8
    12. page_text=page_text.decode("utf-8")
    13. #print(page_text)
    15. soup=BeautifulSoup(page_text,'lxml')
    16. li_list=soup.select('.book-mulu > ul > li')
    17. fp=open('./sanguo.txt','w',encoding='utf-8')
    18. for li in li_list:
    19.     title=li.a.string
    20.     detail_url='https://www.shicimingju.com'+li.a['href']
    21.     detail_page_text=requests.get(url=detail_url,headers=headers).text
    22.     # encode编码，将ISO-8859-1编码成unicode
    23.     detail_page_text = detail_page_text.encode("ISO-8859-1").decode("utf-8")
    24.     detail_soup=BeautifulSoup(detail_page_text,'lxml')
    25.     div_tag=detail_soup.find('div',class_='chapter_content')
    26.     content=div_tag.getText()
    27.     fp.write(title+':'+content+'\n')
    28.     print(title+' 爬取成功')