下载知乎指定问题的答案并保存图片

最新推荐文章于 2024-09-27 10:11:28 发布

weixin_30298497

最新推荐文章于 2024-09-27 10:11:28 发布

阅读量203

点赞数

文章标签： python

原文链接：http://www.cnblogs.com/shubin/p/7511737.html

版权

代码如下：

from zhihu_oauth import ZhihuClient

from zhihu_oauth.exception import NeedCaptchaException
from docx import Document
from docx.shared import Inches
from w3lib.html import remove_tags
import urllib.request
from io import StringIO
import subprocess
import re
document = Document()
client = ZhihuClient()



try:
    client.login('username', 'pass')
except NeedCaptchaException:
    # 保存验证码并提示输入，重新登录
    with open('a.gif', 'wb') as f:
        f.write(client.get_captcha())
    captcha = input('please input captcha:')
    client.login('898311543@qq.com', '1818039565', captcha)

p = re.compile('<img.*>')
num = input('请输入问题序号：')
question = client.question(int(num))
i = 0;
file = open(question.title+'.html','w')
file.write('<html><head></head><body>')
# document.add_heading(question.title, 0)
file.write('<h1>'+question.title+'</h1>')
for answer in question.answers:
#    print(question.answers[0].content.replace('<br>','\n'))
#    print(question.answers[0].voteup_count)
    print(answer.author.name)
    # document.add_paragraph("回答者："+answer.author.name+'\t'+'赞数：'+str(answer.voteup_count), style='IntenseQuote')
    # document.add_paragraph(remove_tags(answer.content, keep=('img',)))
    # document.add_page_break()
    file.write('<br><br>'+"回答者："+answer.author.name+'&nbsp;&nbsp;'+'赞数：'+str(answer.voteup_count))
    file.write('<p>'+answer.content+'</p>')
    i=i+1
    if(i>50):
        break
#document.save(str(question.title)+'.docx')
file.write('</body></html>')
file.close()
subprocess.call(['pandoc',question.title+'.html','-o',question.title+'.docx'])
subprocess.call(['rm','-rf',question.title+'.html'])