add some picture crawler

Author: CodeOver2015

51_job_bs.py

@@ -77,8 +77,8 @@ def getData(self, work='Python'):
                         #存在p节点
                         for p in ps:
                             p_data.append(p.string)
-                        else:
-                            p_data.append(div.get_text().strip())
+                    else:
+                        p_data.append(div.get_text().strip())
                 except Exception as e:
                     print(str(e))
                     p_data.append("暂无")

README.md

@@ -1,2 +1,4 @@
 #### 2018-3-9
-##### *This is a warehouse with python crawlers and data processing, with examples inside.*   
+##### *This is a warehouse with python crawlers and data processing, with examples inside.*  
+
+>>[code introduce by csdn](http://blog.csdn.net/tenderness4/article/details/79504086) or [blog](http://wirjx.top/Python3.6%E7%88%AC%E8%99%AB%E6%80%BB%E7%BB%93)

mm_req_html_pic.py

@@ -0,0 +1,58 @@
+#coding=utf-8
+"""
+@author:JianxiongRao
+@data:2018/3/12
+@version:Python3.6
+"""
+from requests_html import HTMLSession
+import os
+import time
+
+class MM(object):
+    def __init__(self):
+        self.__page = 1
+        self.__url = "http://www.mm131.com/qingchun/list_1_{}.html"
+        self.__session = HTMLSession()
+        self.__headers = {
+            'Referer':'http://www.mm131.com/qingchun/',
+            'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.140 Safari/537.36'
+        }
+        self.__imagePath = r'D:/Photo/MM'
+        self.__confirmPath()
+
+    def __confirmPath(self):
+        if not os.path.exists(self.__imagePath):
+            os.makedirs(self.__imagePath)
+            
+    def download(self,link,fileName):
+        try:
+            with open(self.__imagePath+'/'+fileName+'.jpg','wb') as f:
+                f.write(self.__session.request('get',link,headers = self.__headers,allow_redirects=False).content)
+        except Exception as e:
+            print(str(e))
+
+    def parseData(self):
+        start = time.time()
+        while self.__page < 12:
+            if self.__page == 1:
+                self.__url = "http://www.mm131.com/qingchun/"
+            else:
+                self.__url = 'http://www.mm131.com/qingchun/list_1_{}.html'.format(self.__page)
+            r = self.__session.get(self.__url)
+            main = r.html.find(".main",first=True)
+            dl = main.find('dl')[0]
+            dds = dl.find('dd')
+            for dd in dds[:-1]:
+                attr = dd.find('img')[0].attrs
+                imageLink = attr['src']
+                title = attr['alt']
+                self.download(imageLink,title)
+            self.__page += 1
+        end = time.time() - start
+        print("爬取时间:",end)
+
+if __name__=="__main__":
+    mm = MM()
+    mm.parseData()
+
+