update re code

Author: CodeOver2015

51_job.re.py

@@ -14,7 +14,9 @@ def __init__(self):
         self.__job = 'Python'
         self.__url = 'http://search.51job.com/list/000000,000000,0000,00,9,99,{},2,{}.html?lang=c&stype=1&postchannel=0000&workyear=99&cotype=99&degreefrom=99&jobterm=99&companysize=99&lonlat=0%2C0&radius=-1&ord_field=0&confirmdate=9&fromType=&dibiaoid=0&address=&line=&specialarea=00&from=&welfare='
         self.__count = 1
-        self.__page = 672
+        #总共672页
+        self.__page = 1
+        #总共672页
         self.__createSheet()
 
     def __createSheet(self):
@@ -46,13 +48,17 @@ def __getDetails(self, site):
         headers = {
             'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2785.143 Safari/537.36'
         }
-        res = requests.get(site, headers=headers)
-        res.encoding = 'gbk'
-        pattern2 = re.compile('<div class.*?"bmsg job_msg inbox">(.*?)<div>', re.S)
-        details = re.findall(pattern2, res.text)
-        if details is not None and len(details) != 0:
-            details = re.sub(re.compile(r'<[^>]+>', re.S), '', details)
-        else:
+        try:
+            res = requests.get(site, headers=headers,timeout=1)
+            res.encoding = 'gbk'
+            pattern2 = re.compile('<div class.*?bmsg.*?job.*?msg.*?inbox">(.*?)</div>', re.S)
+            details = re.findall(pattern2, res.text)
+            print(details)
+            if details is not None and len(details) != 0:
+                details = re.sub(re.compile(r'<[^>]+>', re.S), '', details[0])
+            else:
+                details = "暂无数据"
+        except:
             details = "暂无数据"
         return details
 
@@ -64,11 +70,15 @@ def getData(self, work='Python'):
             }
             while self.__page <= 672:
                 url = self.__url.format(self.__job, self.__page)
-                response = requests.get(url, headers=headers,timeout=3)
+                response = requests.get(url, headers=headers,timeout=1)
                 response.encoding = 'gbk'
                 content = response.text
-                pattern = re.compile('<div class.*?el.*?<a.*?title="(.*?)".*?href.*?"(.*?)".*?<a.*?title.*?"(.*?)".*?class.*?"t3">(.*?)</span>.*?class.*?"t4">(.*?)</span>',re.S)
+                print(content)
+                print("Start")
+                pattern = re.compile('<div class="el">.*?<a.*?title="(.*?)".*?href="(.*?)".*?<a.*?title="(.*?)".*?class.*?"t3">(.*?)</span>.*?class.*?"t4">(.*?)</span>.*?</div>',re.S)
+                print("go on")
                 datas = re.findall(pattern,content)
+                print("end")
                 for each in datas:
                     title = ""
                     address = ""
@@ -84,14 +94,12 @@ def getData(self, work='Python'):
                         name = each[2]
                         salary = each[4]
                         site = each[1]
-                        print(site)
                         details = self.__getDetails(site)
 
                     self.__saveDataToExcel(title, address, name, salary, details, site)
                 self.__page += 1
         except Exception as e:
             print(str(e))
-            raise e
 
 
 if __name__ == '__main__':