Merge pull request egrcc#4 from Eureka22/master

add cookies support

Author: egrcc

README.rst

@@ -53,6 +53,12 @@ zhihu-python 采用 python2.7 编写，用来方便地获取知乎上各种内
     $ pip install beautifulsoup4
     $ pip install html2text
 
+或者使用
+
+.. code-block:: bash
+
+    $ pip install -r requirements.txt
+
 **注意** ：如果同时安装了 python3 和 python2 ， pip 命令可能默认安装的是 python3 版本的包，故需将上述命令中的 pip 换成pip2 （比如在我的Ubuntu上）。
 
 快速开始

config.ini

@@ -1,3 +1,14 @@
 [info]
 email = 
 password = 
+
+[cookies]
+z_c0 =  
+q_c1 =  
+c_c =   
+_xsrf = 
+__utmz =
+__utmv =
+__utmc =
+__utmb =
+__utma =

markdown/现实可以有多美好？--田浩的回答.md

@@ -0,0 +1,12 @@
+# 现实可以有多美好？
+## 作者: 田浩  赞同: 11000
+一个制毒者，凌晨被我们抓到，家里全是「制毒原料」，还有一台蒸馏机，几个塑料桶，我们进去的时候他还拿着棍子在桶里搅。被抓到当时情绪就崩溃了，说自己只是个木匠，
+一时鬼迷心窍才去缅甸买了这些机器和原料，并表示认罪，愿意积极配合，问我们能不能不死。说实话，按他的数量，少说几十公斤，虽然嘴上应承着，但心里觉得他死定了。  
+  
+我们把人和东西抓回去之后，化验毒品，神转折是，发现他的制毒的原料和机器全是假的。去境外被人骗了。  
+  
+最后是算预备犯罪还是犯罪未遂我忘记了，反正关了不到一年就放出来了。  
+  
+对他来说，这现实简直太美好啦。
+
+#### 原链接: http://www.zhihu.com/question/24269892/answer/29960616

requirements.txt

@@ -0,0 +1,3 @@
+requests
+beautifulsoup4
+html2text

text/现实可以有多美好？--田浩的回答.txt

@@ -0,0 +1,15 @@
+现实可以有多美好？
+
+作者: 田浩  赞同: 11000
+
+一个制毒者，凌晨被我们抓到，家里全是「制毒原料」，还有一台蒸馏机，几个塑料桶，我们进去的时候他还拿着棍子在桶里搅。被抓到当时情绪就崩溃了，说自己只是个木匠，一时鬼迷心窍才去缅甸买了这些机器和原料，并表示认罪，愿意积极配合，问我们能不能不死。说实话，按他的数量，少说几十公斤，虽然嘴上应承着，但心里觉得他死定了。我们把人和东西抓回去之后，化验毒品，神转折是，发现他的制毒的原料和机器全是假的。去境外被人骗了。最后是算预备犯罪还是犯罪未遂我忘记了，反正关了不到一年就放出来了。对他来说，这现实简直太美好啦。
+
+
+
+
+
+
+
+
+
+原链接: http://www.zhihu.com/question/24269892/answer/29960616

zhihu.py

@@ -9,17 +9,30 @@
 import html2text
 import ConfigParser
 from bs4 import BeautifulSoup
+import sys  
 
+reload(sys)  
+sys.setdefaultencoding('utf8')
 session = None
 
+cookies = {}
+
 def create_session():
 
     global session
-
+    global cookies
     cf = ConfigParser.ConfigParser()
     cf.read("config.ini")
+    
+    cookies = cf._sections['cookies']
+    
     email = cf.get("info", "email")
     password = cf.get("info", "password")
+    
+    
+    cookies = dict(cookies)
+    print cookies
+    
     s = requests.session()
     login_data = {"email": email, "password": password}
     header = {
@@ -28,9 +41,12 @@ def create_session():
         'Referer': "http://www.zhihu.com/",
         'X-Requested-With': "XMLHttpRequest"
     }
+    
     r = s.post('http://www.zhihu.com/login', data = login_data, headers = header)
     if r.json()["r"] == 1:
-        raise Exception("login failed.")
+        print "Login Failed, reason is:"
+        print r.text
+        print "Use cookies"
     session = s
 
 
@@ -67,7 +83,7 @@ def parser(self):
         if session == None:
             create_session()
         s = session
-        r = s.get(self.url)
+        r = s.get(self.url,cookies = cookies)
         soup = BeautifulSoup(r.content)
         self.soup = soup
 
@@ -239,7 +255,7 @@ def get_all_answers(self):
                         'Host': "www.zhihu.com",
                         'Referer': self.url
                     }
-                    r = s.post(post_url, data = data, headers = header)
+                    r = s.post(post_url, data = data, headers = header, cookies = cookies)
                     answer_list = r.json()["msg"]
                     for j in range(min(answers_num - i * 50, 50)):
                         soup = BeautifulSoup(self.soup.encode("utf-8"))
@@ -332,7 +348,7 @@ def parser(self):
         if session == None:
             create_session()
         s = session
-        r = s.get(self.user_url)
+        r = s.get(self.user_url,cookies = cookies)
         soup = BeautifulSoup(r.content)
         self.soup = soup
 
@@ -458,7 +474,7 @@ def get_followees(self):
                     create_session()
                 s = session
                 followee_url = self.user_url + "/followees"
-                r = s.get(followee_url)
+                r = s.get(followee_url,cookies = cookies)
                 soup = BeautifulSoup(r.content)
                 for i in range((followees_num - 1) / 20 + 1):
                     if i == 0:
@@ -481,7 +497,7 @@ def get_followees(self):
                             'Host': "www.zhihu.com",
                             'Referer': followee_url
                         }
-                        r_post = s.post(post_url, data = data, headers = header)
+                        r_post = s.post(post_url, data = data, headers = header, cookies = cookies)
                         followee_list = r_post.json()["msg"]
                         for j in range(min(followees_num - i * 20, 20)):
                             followee_soup = BeautifulSoup(followee_list[j])
@@ -506,7 +522,7 @@ def get_followers(self):
                     create_session()
                 s = session
                 follower_url = self.user_url + "/followers"
-                r = s.get(follower_url)
+                r = s.get(follower_url,cookies = cookies)
                 soup = BeautifulSoup(r.content)
                 for i in range((followers_num - 1) / 20 + 1):
                     if i == 0:
@@ -529,7 +545,7 @@ def get_followers(self):
                             'Host': "www.zhihu.com",
                             'Referer': follower_url
                         }
-                        r_post = s.post(post_url, data = data, headers = header)
+                        r_post = s.post(post_url, data = data, headers = header, cookies = cookies)
                         follower_list = r_post.json()["msg"]
                         for j in range(min(followers_num - i * 20, 20)):
                             follower_soup = BeautifulSoup(follower_list[j])
@@ -555,7 +571,7 @@ def get_asks(self):
             else:  
                 for i in range((asks_num - 1) / 20 + 1):
                     ask_url = self.user_url + "/asks?page=" + str(i + 1)
-                    r = s.get(ask_url)
+                    r = s.get(ask_url,cookies = cookies)
                     soup = BeautifulSoup(r.content)
                     for question in soup.find_all("a", class_ = "question_link"):
                         url = "http://www.zhihu.com" + question["href"]
@@ -581,7 +597,7 @@ def get_answers(self):
             else:
                 for i in range((answers_num - 1) / 20 + 1):
                     answer_url = self.user_url + "/answers?page=" + str(i + 1)
-                    r = s.get(answer_url)
+                    r = s.get(answer_url,cookies = cookies)
                     soup = BeautifulSoup(r.content)
                     for answer in soup.find_all("a", class_ = "question_link"):
                         question_url = "http://www.zhihu.com" + answer["href"][0:18]
@@ -608,7 +624,7 @@ def get_collections(self):
             else:
                 for i in range((collections_num - 1) / 20 + 1):
                     collection_url = self.user_url + "/collections?page=" + str(i + 1)
-                    r = s.get(collection_url)
+                    r = s.get(collection_url,cookies = cookies)
                     soup = BeautifulSoup(r.content)
                     for collection in soup.find_all("div", class_ = "zm-profile-section-item zg-clear"):
                         url = "http://www.zhihu.com" + \
@@ -652,7 +668,7 @@ def parser(self):
         if session == None:
             create_session()
         s = session
-        r = s.get(self.answer_url)
+        r = s.get(self.answer_url,cookies = cookies)
         soup = BeautifulSoup(r.content)
         self.soup = soup
 
@@ -905,7 +921,7 @@ def parser(self):
         if session == None:
             create_session()
         s = session
-        r = s.get(self.url)
+        r = s.get(self.url,cookies = cookies)
         soup = BeautifulSoup(r.content)
         self.soup = soup
 
@@ -972,7 +988,7 @@ def get_all_answers(self):
             i = 2
             s = session
             while True:
-                r = s.get(self.url + "?page=" + str(i))
+                r = s.get(self.url + "?page=" + str(i),cookies = cookies)
                 answer_soup = BeautifulSoup(r.content)
                 answer_list = answer_soup.find_all("div", class_ = "zm-item")
                 if len(answer_list) == 0: