修改错误

prefectgou · Jul 13, 2017 · eb38bab · eb38bab
1 parent 27db113
commit eb38bab
Show file tree

Hide file tree

Showing 12 changed files with 122 additions and 86 deletions.
diff --git a/P113.jpg b/P113.jpg
diff --git a/P137.jpg b/P137.jpg
diff --git a/P145.jpg b/P145.jpg
diff --git a/P21.jpg b/P21.jpg
diff --git a/P29.jpg b/P29.jpg
diff --git a/P58.jpg b/P58.jpg
diff --git a/ch01/1.4.4.py b/ch01/1.4.4.py
@@ -74,17 +74,17 @@ class QueueManager(BaseManager):
 
 '''
 taskManager.py程序(Windows版)
+'''
 
-#coding:utf-8
 # taskManager.py for windows
 import Queue
 from multiprocessing.managers import BaseManager
 from multiprocessing import freeze_support
 #任务个数
 task_number = 10
 #定义收发队列
-task_queue = Queue.Queue(task_number);
-result_queue = Queue.Queue(task_number);
+task_queue = Queue.Queue(task_number)
+result_queue = Queue.Queue(task_number)
 def get_task():
     return task_queue
 def get_result():
@@ -97,7 +97,7 @@ def win_run():
     QueueManager.register('get_task_queue',callable = get_task)
     QueueManager.register('get_result_queue',callable = get_result)
     #绑定端口并设置验证口令，windows下需要填写ip地址，linux下不填默认为本地
-    manager = QueueManager(address = ('127.0.0.1',8001),authkey = 'qiye')
+    manager = QueueManager(address = ('127.0.0.1',8001),authkey = b'qiye')
     #启动
     manager.start()
     try:
@@ -122,4 +122,3 @@ def win_run():
     freeze_support()
     win_run()
 
-'''
diff --git a/ch06/DataOutput.py b/ch06/DataOutput.py
@@ -13,6 +13,7 @@ def store_data(self,data):
     def output_html(self):
         fout=codecs.open('baike.html','w',encoding='utf-8')
         fout.write("<html>")
+        fout.write("<head><meta charset='utf-8'/></head>")
         fout.write("<body>")
         fout.write("<table>")
         for data in self.datas:

diff --git a/ch06/baike.html b/ch06/baike.html
diff --git a/ch12/cnblogSpider/cnblogSpider/spiders/cnblogs_spider.py b/ch12/cnblogSpider/cnblogSpider/spiders/cnblogs_spider.py
@@ -22,7 +22,7 @@ def parse(self, response):
             url = paper.xpath(".//*[@class='postTitle']/a/@href").extract()[0]
             title = paper.xpath(".//*[@class='postTitle']/a/text()").extract()[0]
             time = paper.xpath(".//*[@class='dayTitle']/a/text()").extract()[0]
-            content = paper.xpath(".//*[@class='postTitle']/a/text()").extract()[0]
+            content = paper.xpath(".//*[@class='postCon']/a/text()").extract()[0]
             item = CnblogspiderItem(url=url, title=title, time=time, content=content)
             request = scrapy.Request(url=url, callback=self.parse_body)
             request.meta['item'] = item  # 将item暂存

diff --git a/ch14/zhihuCrawl/zhihuCrawl/spiders/zhihu_com.py b/ch14/zhihuCrawl/zhihuCrawl/spiders/zhihu_com.py
@@ -57,8 +57,8 @@ def start_login(self,response):
             meta={'cookiejar': response.meta['cookiejar']},
             formdata={
                 '_xsrf': self.xsrf,
-                'phone_num': '15109209327',
-                'password': '$waqxr123789',
+                'phone_num': 'xxxxxxxx',
+                'password': 'xxxxxxxx',
                 'captcha_type': 'cn'},
             callback=self.after_login
         )]

diff --git a/勘误表.md b/勘误表.md
@@ -5,7 +5,7 @@
 ```python
 for url in ["ImageUrl_"+str(i) for i in range(10)]:
 ```
-感谢 @jsqlzy
+感谢 [@jsqlzy](@jsqlzy)
 
 #### 2. 书籍182页出现问题
 原因: 笔误
@@ -14,7 +14,7 @@ for url in ["ImageUrl_"+str(i) for i in range(10)]:
 <br>
 将sqlite3改成MySQLdb
 
-感谢 @lg-Cat73
+感谢 [@lg-Cat73](@lg-Cat73)
 
 #### 3. 书籍P122-P123 CSS选择器表达式多出空格
 原因:印刷错误
@@ -23,15 +23,15 @@ for url in ["ImageUrl_"+str(i) for i in range(10)]:
 <br>
 ![](123页.png)
 <br>
-感谢 @Judy0513
+感谢 [@Judy0513](@Judy0513)
 
 #### 4. 书籍P144和P156 soup.find_all('a', href = re.compile(r'/view/\d+.htm'))正则表达式有误
 原因：百度词条的链接链接结构发生改变，不属于程序错误。
 修改如下：
 ```python
 links = soup.find_all('a', href=re.compile(r'/item/.*'))
 ```
-感谢 @Judy0513
+感谢 [@Judy0513](@Judy0513)
 #### 5.书籍P138页代码有误,多出空格
 原因:笔误
 <br>
@@ -40,4 +40,60 @@ links = soup.find_all('a', href=re.compile(r'/item/.*'))
 修改如下：
 ```python
 smtp_server = 'smtp.163.com'
-```
+```
+感谢 [@shaodamao](@shaodamao)
+
+#### 6.P58 --表2-4 实现效果第6行，应该是"这些元素拥有值为en的lang属性"
+原因:笔误
+<br>
+![](P58.jpg)
+<br>
+感谢 [@Judy0513](@Judy0513)
+
+#### 7.P305 def parse_item(self, response), def parse_body(self, response)两个函数排版
+原因:排版问题
+<br>
+感谢 [@Judy0513 ](@Judy0513 ) 
+
+#### 8.P29，上面那块代码后的文字，任务进程已经编写完成（应该为服务进程）
+原因：笔误
+<br>
+![](P29.jpg)
+<br>
+感谢 [@wushicanASL](@wushicanASL) 
+
+#### 9.P113,倒数第5行 Tag 的content属性 应为Tag的contents属性
+原因：笔误
+<br>
+![](P113.jpg)
+<br>
+感谢 [@wushicanASL](@wushicanASL) 
+
+#### 10. P137 5.3节Email提醒 开始 第三行，发送邮件的协议是STMP（应该为SMTP）
+原因：笔误
+<br>
+![](P137.jpg)
+<br>
+感谢 [@wushicanASL](@wushicanASL) 
+
+#### 11.P145和P152 存储成html,火狐打开出现乱码(其实可以使用火狐可以选择不同的编码)
+解决添加如下代码:
+<br>
+```python
+fout.write("<head><meta charset='utf-8'/></head>")
+```
+![](P145.jpg)
+<br>
+感谢 [@jsqlzy](@jsqlzy) 
+
+
+#### 12.P21 代码有误
+修改为：
+```python
+p2.terminate()
+```
+<br>
+
+![](P21.jpg)
+<br>
+感谢 [@Judy0513 ](@Judy0513 )