Python爬去知乎上问题下所有图片

Posted 2020-12-28 守拙的瘦子

from zhihu_oauth import ZhihuClient
from zhihu_oauth.exception import NeedCaptchaException

client = ZhihuClient()

try:
    client.login(‘email_or_phone‘, ‘password‘)
    print(u"登陆成功!")
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(‘[phone]‘, ‘z289784552‘, captcha)
    print(u"登陆成功!")
client.save_token(‘token.pkl‘)

获取Token

from __future__ import print_function # 使用python3的print方法
from zhihu_oauth import ZhihuClient
import re
import os
import urllib.request

client = ZhihuClient()
# 登录
client.load_token(‘token.pkl‘)  # 加载token文件
id = 46508954 # https://www.zhihu.com/question/24400664(长得好看是一种怎么样的体验)
question = client.question(id)
print(u"问题:",question.title)
print(u"回答数量:",question.answer_count)
os.mkdir(question.title + u"(图片)")
path = question.title + u"(图片)"
index = 1 # 图片序号
for answer in question.answers:
    content = answer.content  # 回答内容
    re_compile = re.compile(r‘<img src="(https://picd.zhimg.com/.*?.(jpg|png))".*?>‘)
    img_lists = re.findall(re_compile, content)
    if (img_lists):
        for img in img_lists:
            img_url = img[0]  # 图片url
            urllib.request.urlretrieve(img_url, path + u"/%d.jpg" % index)
            print(u"成功保存第%d张图片" % index)
            index += 1

加载Token并读取数据