add function to get answers' voter

lufo816 · lufo816 · commit 08f8e01b2d80 · 2015-04-19T21:55:19.000+08:00
diff --git a/test.py b/test.py
@@ -19,7 +19,7 @@ def question_test(url):
     # 获取该问题所属话题
     topics = question.get_topics()
     # 获取该问题被浏览次数
-    visit_times=question.get_visit_times()
+    visit_times = question.get_visit_times()
     # 获取排名第一的回答
     top_answer = question.get_top_answer()
     # 获取排名前十的十个回答
@@ -41,7 +41,7 @@ def question_test(url):
     print followers_num  # 输出：26910
     for topic in topics:
         print topic,  # 输出：情感克制 现实 社会 个人经历
-    print visit_times # 输出: 该问题当前被浏览的次数
+    print visit_times  # 输出: 该问题当前被浏览的次数
     print top_answer  # 输出：<zhihu.Answer instance at 0x7f8b6582d0e0>（Answer类对象）
     print top_answers  # 输出：<generator object get_top_i_answers at 0x7fed676eb320>（代表前十的Answer的生成器）
     print answers  # 输出：<generator object get_all_answer at 0x7f8b66ba30a0>（代表所有Answer的生成器）
@@ -57,6 +57,8 @@ def answer_test(answer_url):
     upvote = answer.get_upvote()
     # 获取改该答案所属问题被浏览次数
     visit_times = answer.get_visit_times()
+    # 获取所有给该答案点赞的用户信息
+    voters = answer.get_voters()
     # 把答案输出为txt文件
     answer.to_txt()
     # 把答案输出为markdown文件
@@ -69,9 +71,12 @@ def answer_test(answer_url):
     print author
     # <zhihu.User instance at 0x7f0b25425b90>
     # 一个User对象
+    for voter in voters:
+        print voter
+        # 一个 User 对象
     print author.get_user_id()  # 输出：田浩
     print upvote  # 输出：9320
-    print visit_times # 输出: 改答案所属问题被浏览次数
+    print visit_times  # 输出: 改答案所属问题被浏览次数
 
 
 def user_test(user_url):
@@ -207,4 +212,5 @@ def main():
 
 
 if __name__ == '__main__':
-    main()
+    main()
+
diff --git a/zhihu.py b/zhihu.py
@@ -23,14 +23,11 @@ def create_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}
@@ -824,9 +821,9 @@ def to_txt(self):
             print file_name
             # if platform.system() == 'Windows':
             # file_name = file_name.decode('utf-8').encode('gbk')
-            #     print file_name
+            # print file_name
             # else:
-            #     print file_name
+            # print file_name
             if os.path.exists(os.path.join(os.path.join(os.getcwd(), "text"), file_name)):
                 f = open(os.path.join(os.path.join(os.getcwd(), "text"), file_name), "a")
                 f.write("\n\n")
@@ -844,9 +841,9 @@ def to_txt(self):
             print file_name
             # if platform.system() == 'Windows':
             # file_name = file_name.decode('utf-8').encode('gbk')
-            #     print file_name
+            # print file_name
             # else:
-            #     print file_name
+            # print file_name
             f = open(os.path.join(os.path.join(os.getcwd(), "text"), file_name), "wt")
             f.write(self.get_question().get_title() + "\n\n")
         if platform.system() == 'Windows':
@@ -863,11 +860,11 @@ def to_txt(self):
 
     # def to_html(self):
     # content = self.get_content()
-    #     if self.get_author().get_user_id() == "匿名用户":
-    #         file_name = self.get_question().get_title() + "--" + self.get_author().get_user_id() + "的回答.html"
-    #         f = open(file_name, "wt")
-    #         print file_name
-    #     else:
+    # if self.get_author().get_user_id() == "匿名用户":
+    # file_name = self.get_question().get_title() + "--" + self.get_author().get_user_id() + "的回答.html"
+    # f = open(file_name, "wt")
+    # print file_name
+    # else:
     #         file_name = self.get_question().get_title() + "--" + self.get_author().get_user_id() + "的回答.html"
     #         f = open(file_name, "wt")
     #         print file_name
@@ -955,6 +952,24 @@ def get_visit_times(self):
             if "所属问题被浏览" in tag_p.contents[0].encode('utf-8'):
                 return int(tag_p.contents[1].contents[0])
 
+    def get_voters(self):
+        if self.soup == None:
+            self.parser()
+        soup = self.soup
+        data_aid = soup.find("div", class_="zm-item-answer ")["data-aid"]
+        request_url = 'http://www.zhihu.com/node/AnswerFullVoteInfoV2?params=%7B%22answer_id%22%3A%22' + str(
+            data_aid) + '%22%7D'
+        if session == None:
+            create_session()
+        s = session
+        r = s.get(request_url)
+        soup = BeautifulSoup(r.content)
+        voters_info = soup.find_all("span")[1:-1]
+        for voter_info in voters_info:
+            voter_url = "http://www.zhihu.com" + str(voter_info.a["href"])
+            voter_id = voter_info.a["title"].encode("utf-8")
+            yield User(voter_url, voter_id)
+
 
 class Collection:
     url = None
@@ -1000,7 +1015,7 @@ def parser(self):
         # print 'has_cookies', has_cookies
         if has_cookies == False:
             r = s.get(self.url)
-        #print 'r', r.content
+        # print 'r', r.content
         soup = BeautifulSoup(r.content)
         self.soup = soup
 
@@ -1057,8 +1072,8 @@ def get_all_answers(self):
                     question = Question(question_url, question_title)
                     answer_url = "http://www.zhihu.com" + answer.find("span", class_="answer-date-link-wrap").a["href"]
                     author = None
-                    #print 'answer url',answer_url
-                    #print 'answerfind',answer.find("h3", class_="zm-item-answer-author-wrap")
+                    # print 'answer url',answer_url
+                    # print 'answerfind',answer.find("h3", class_="zm-item-answer-author-wrap")
                     if answer.find("h3", class_="zm-item-answer-author-wrap").string == u"匿名用户":
                         author_url = None
                         author = User(author_url)
