PS.知乎可以通过手机号和邮箱号两种方式登陆，方法相同，这里模拟的是通过手机号的登陆。
主要用到了requests库等，用requests处理cookies更方便一点。requests.Session能够跨请求地保持cookies，同一个session实例发送的请求都保持同一个cookies，requests模块会自动处理。
PC端的验证码是选择倒立的汉字，处理起来比较麻烦，这里模拟了手机端登陆的过程，输入验证码即可。
import re import requests from bs4 import BeautifulSoup from PIL import Image import http.cookiejar import time import json session = requests.Session() session.cookies = http.cookiejar.LWPCookieJar(filename='cookies') try: session.cookies.load(ignore_discard=True) except: print("Cookie 未能加载") home_url = 'https://www.zhihu.com/' headers = { 'User-Agent':'Mozilla/5.0 (Linux; U; Android 2.3.7; en-us; Nexus One Build/FRF91) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1', 'Referer':'https://www.zhihu.com/', 'Host':'www.zhihu.com' } def islogin(): url = 'https://www.zhihu.com/settings/profile' status = session.get(url,headers = headers, allow_redirects=False ).status_code #注意禁止重定向 if status == 200: return True else: return False def get_xsrf(url = 'https://www.zhihu.com/explore'): html = session.get(url,headers = headers) _xsrf = re.search('_xsrf" value="(.*?)"/>',html.text,re.S).group(1) return _xsrf def get_captcha(): t = str(int(time.time() * 1000)) captcha_url = 'https://www.zhihu.com/captcha.gif?r=' + t + "&type=login" r = session.get(captcha_url, headers=headers) with open('captcha.jpg', 'wb') as f: #保存验证码到本地 f.write(r.content) f.close() im = Image.open('captcha.jpg') im.show() im.close() captcha = input('请输入验证码:') return captcha def login(user_name,password): _xsrf = get_xsrf() post_url = 'https://www.zhihu.com/login/phone_num' post_data = { '_xsrf' : _xsrf, 'password' : password, 'phone_num' : user_name, } result = session.post(post_url,data = post_data,headers = headers) #尝试不输入验证码登陆 if(json.loads(result.text))['r'] == 1 : #登陆失败，需要输入验证码 post_data['captcha'] = get_captcha() login_page = session.post(post_url,data = post_data,headers = headers) print((json.loads(login_page.text))['msg']) #登陆提示信息 session.cookies.save() #保存cookies，方便下次登陆 def show_mine(): mine_url = 'https://www.zhihu.com/collections/mine' html = session.get(mine_url,headers = headers) href = BeautifulSoup(html.text,'html5lib').find_all('h2',class_ = 'zm-item-title')[1].find('a')['href'] url = 'https://www.zhihu.com' + str(href) show_collection(url) def down_answer(url): answer_html = session.get(url,headers = headers) title = BeautifulSoup(answer_html.text,'html5lib').find('title').get_text() print(title) def get_collection(url): print(url) content = session.get(url,headers = headers) all_answer = BeautifulSoup(content.text,'html5lib').find_all('a',class_="toggle-expand") for answer in all_answer: answer_href = answer['href'] if(re.match('^https://zhuanlan',answer_href) == None): answer_url = 'https://www.zhihu.com' + answer_href else: answer_url = answer_href down_answer(answer_url) def show_collection(url): coll_html = session.get(url,headers = headers) page_num = BeautifulSoup(coll_html.text,'html5lib').find('div' ,class_ = 'zm-invite-pager').find_all('span')[-2].get_text() print(page_num) for page in range(1,int(page_num)): page_url = url + '?page=' + str(page) get_collection(page_url) if __name__ == '__main__': if islogin(): print('已登录') else: user_name = input('请输入用户名:') password = input('请输入密码:') login(user_name,password) show_mine()
