43 |
44 |
45 |
51 | PhD student/Wizard/Swimmer
52 |
53 |
54 | 
74 | |
','\n', each_answer) 128 | self.save2file(filename, unicode(sub_answer)) 129 | k=k+1 130 | 131 | 132 | smtp_server = 'smtp.126.com' 133 | from_mail = 'your@126.com' 134 | password = 'yourpassword' 135 | to_mail = 'yourname@kindle.cn' 136 | 137 | # send_kindle=MailAtt(smtp_server,from_mail,password,to_mail) 138 | # send_kindle.send_txt(filename) 139 | 140 | # 调用发送邮件函数，把电子书发送到你的kindle用户的邮箱账号，这样你的kindle就可以收到电子书啦 141 | print filename 142 | 143 | 144 | 145 | class MailAtt(): 146 | def __init__(self, smtp_server, from_mail, password, to_mail): 147 | self.server = smtp_server 148 | self.username = from_mail.split("@")[0] 149 | self.from_mail = from_mail 150 | self.password = password 151 | self.to_mail = to_mail 152 | 153 | # 初始化邮箱设置 154 | 155 | def send_txt(self, filename): 156 | # 这里发送附件尤其要注意字符编码，当时调试了挺久的，因为收到的文件总是乱码 157 | self.smtp = smtplib.SMTP() 158 | self.smtp.connect(self.server) 159 | self.smtp.login(self.username, self.password) 160 | self.msg = MIMEMultipart() 161 | self.msg['to'] = self.to_mail 162 | self.msg['from'] = self.from_mail 163 | self.msg['Subject'] = "Convert" 164 | self.filename = filename + ".txt" 165 | self.msg['Date'] = Utils.formatdate(localtime=1) 166 | content = open(self.filename.decode('utf-8'), 'rb').read() 167 | # print content 168 | self.att = MIMEText(content, 'base64', 'utf-8') 169 | self.att['Content-Type'] = 'application/octet-stream' 170 | # self.att["Content-Disposition"] = "attachment;filename=\"%s\"" %(self.filename.encode('gb2312')) 171 | self.att["Content-Disposition"] = "attachment;filename=\"%s\"" % Header(self.filename, 'gb2312') 172 | # print self.att["Content-Disposition"] 173 | self.msg.attach(self.att) 174 | 175 | self.smtp.sendmail(self.msg['from'], self.msg['to'], self.msg.as_string()) 176 | self.smtp.quit() 177 | 178 | #Todo 179 | #add id list to database 180 | 181 | if __name__ == "__main__": 182 | 183 | sub_folder = os.path.join(os.getcwd(), "content") 184 | # 专门用于存放下载的电子书的目录 185 | 186 | if not os.path.exists(sub_folder): 187 | os.mkdir(sub_folder) 188 | 189 | os.chdir(sub_folder) 190 | 191 | id="20357585" 192 | #id = sys.argv[1] 193 | # 给出的第一个参数 就是你要下载的问题的id 194 | # 比如 想要下载的问题链接是 https://www.zhihu.com/question/29372574 195 | # 那么 就输入 python zhihu.py 29372574 196 | 197 | 198 | # id_link="/question/"+id 199 | obj = GetContent(id) 200 | # obj.getAnswer(id_link) 201 | 202 | # 调用获取函数 203 | 204 | print "Done" 205 | -------------------------------------------------------------------------------- /login_fetch.py: -------------------------------------------------------------------------------- 1 | # -*-coding=utf-8-*- 2 | ''' 3 | 在当前文件夹下创建data.cfg 4 | 第一行是用户名 5 | 第二行是用户密码 6 | 7 | 例如： 8 | zhangsan 9 | 123456 10 | ''' 11 | 12 | __author__ = 'Rocky' 13 | import requests 14 | import cookielib 15 | import re 16 | import json 17 | import time 18 | import os 19 | from getContent import GetContent 20 | import next_page 21 | 22 | agent = 'Mozilla/5.0 (Windows NT 5.1; rv:33.0) Gecko/20100101 Firefox/33.0' 23 | headers = {'Host': 'www.zhihu.com', 24 | 'Referer': 'https://www.zhihu.com', 25 | 'User-Agent': agent} 26 | 27 | # 全局变量 28 | session = requests.session() 29 | 30 | session.cookies = cookielib.LWPCookieJar(filename="cookies") 31 | 32 | try: 33 | session.cookies.load(ignore_discard=True) 34 | except: 35 | print "Cookie can't load" 36 | 37 | 38 | #读取文件 39 | def getUserData(configFile): 40 | f = open(configFile, 'r') 41 | 42 | #for i in f.readlines(): 43 | data=f.readlines() 44 | username=data[0].strip() 45 | pwd=data[1].strip() 46 | return username,pwd 47 | 48 | 49 | def isLogin(): 50 | url = 'https://www.zhihu.com/settings/profile' 51 | login_code = session.get(url, headers=headers, allow_redirects=False).status_code 52 | print login_code 53 | if login_code == 200: 54 | return True 55 | else: 56 | return False 57 | 58 | 59 | def get_xsrf(): 60 | url = 'https://www.zhihu.com' 61 | r = session.get(url, headers=headers, allow_redirects=False) 62 | txt = r.text 63 | print txt 64 | result = re.findall(r'', txt)[0] 65 | return result 66 | 67 | 68 | def getCaptcha(): 69 | #r=1471341285051 70 | r = (time.time() * 1000) 71 | url = 'http://www.zhihu.com/captcha.gif?r=' + str(r) + '&type=login' 72 | 73 | image = session.get(url, headers=headers) 74 | f = open("photo.jpg", 'wb') 75 | f.write(image.content) 76 | f.close() 77 | 78 | 79 | def Login(): 80 | username,pwd=getUserData("data.cfg") 81 | xsrf = get_xsrf() 82 | print xsrf 83 | print len(xsrf) 84 | login_url = 'https://www.zhihu.com/login/email' 85 | data = { 86 | '_xsrf': xsrf, 87 | 'password': pwd, 88 | 'remember_me': 'true', 89 | 'email': username 90 | } 91 | try: 92 | content = session.post(login_url, data=data, headers=headers) 93 | login_code = content.text 94 | d = json.loads(login_code) 95 | print d['msg'] 96 | print content.status_code 97 | #this line important ! if no status, if will fail and execute the except part 98 | #print content.status 99 | 100 | if content.status_code != requests.codes.ok: 101 | print "Need to verification code !" 102 | getCaptcha() 103 | #print "Please input the code of the captcha" 104 | code = raw_input("Please input the code of the captcha") 105 | data['captcha'] = code 106 | content = session.post(login_url, data=data, headers=headers) 107 | print content.status_code 108 | 109 | if content.status_code == requests.codes.ok: 110 | print "Login successful" 111 | session.cookies.save() 112 | #print login_code 113 | else: 114 | session.cookies.save() 115 | return True 116 | except: 117 | print "Error in login" 118 | return False 119 | 120 | 121 | def focus_question(): 122 | focus_id = [] 123 | url = 'https://www.zhihu.com/question/following' 124 | content = session.get(url, headers=headers) 125 | print content 126 | p = re.compile(r'') 129 | result = re.findall(pattern, content.text)[0] 130 | print result 131 | for i in id_list: 132 | print i 133 | focus_id.append(i) 134 | 135 | url_next = 'https://www.zhihu.com/node/ProfileFollowedQuestionsV2' 136 | page = 20 137 | offset = 20 138 | end_page = 500 139 | xsrf = re.findall(r'(\d+) 个回答') 52 | 53 | result=pattern.findall(content) 54 | if len(result)==0: 55 | return 0 56 | #print result 57 | new_result=result[0] 58 | offset=(int(new_result)/10) 59 | return offset 60 | 61 | def getAll_Answer(answerID): 62 | #answerID=50737023 63 | offset=getOffset(answerID) 64 | #print offset 65 | content=[] 66 | lists=[] 67 | p='0: 81 | lists.append(id_list[0]) 82 | ''' 83 | for k in id_list: 84 | print k 85 | #type(temp) 86 | #content.extend(id_list) 87 | ''' 88 | print lists 89 | all_answer=[] 90 | each_answer='https://www.zhihu.com/question/%s/answer/' % str(answerID) 91 | for x in lists: 92 | link=each_answer+x 93 | result=getAnswer(link) 94 | #print result 95 | all_answer.append(result) 96 | 97 | return all_answer 98 | 99 | #print id_list 100 | 101 | 102 | #getAll_Answer(123) 103 | ''' 104 | p='
67 |
68 |
69 |