selenium

Author: Snailclimb

PythonDemo/.spyproject/workspace.ini

@@ -6,5 +6,5 @@ save_non_project_files = False
 
 [main]
 version = 0.1.0
-recent_files = ['E:\\GitHubWorkplace\\Python\\PythonDemo\\Matplotlib\\demo19.py', 'E:\\GitHubWorkplace\\Python\\PythonDemo\\Matplotlib\\demo18.py', 'E:\\GitHubWorkplace\\Python\\PythonDemo\\spider\\weixinQianming.py', 'E:\\GitHubWorkplace\\Python\\PythonDemo\\spider\\weixin.py', 'E:\\GitHubWorkplace\\Python\\PythonDemo\\spider\\weixinchatRobotGroup.py', 'E:\\GitHubWorkplace\\Python\\PythonDemo\\spider\\weixinchatRobotSingle.py', 'E:\\GitHubWorkplace\\Python\\PythonDemo\\spider\\weixinItchatSexAs.py', 'E:\\GitHubWorkplace\\Python\\PythonDemo\\wordcloud\\examples\\a_new_hope.py', 'E:\\GitHubWorkplace\\Python\\PythonDemo\\wordcloud\\examples\\colored.py', 'E:\\GitHubWorkplace\\Python\\PythonDemo\\wordcloud\\examples\\masked.py', 'E:\\GitHubWorkplace\\Python\\PythonDemo\\spider\\weixinlocation.py', 'E:\\GitHubWorkplace\\Python\\PythonDemo\\SnowNLP\\test.py', 'E:\\GitHubWorkplace\\Python\\PythonDemo\\SnowNLP\\demo1.py']
+recent_files = ['C:\\Users\\Administrator\\.spyder-py3\\temp.py', 'E:\\GitHubWorkplace\\Python\\PythonDemo\\numpy\\arrayboolean.py', 'E:\\GitHubWorkplace\\Python\\PythonDemo\\numpy\\arraymethod.py']
 

PythonDemo/readme.txt

@@ -1 +1,3 @@
-wordcloud词云  jieba分词 itchat wxpy微信相关
+wordcloud词云  jieba分词 itchat wxpy微信相关
+Matplotlib第三库
+numpy第三库

PythonDemo/spider/qqbotRobot.py

@@ -6,5 +6,5 @@ save_non_project_files = False
 
 [main]
 version = 0.1.0
-recent_files = ['C:\\Users\\Administrator\\.spyder-py3\\temp.py']
+recent_files = ['C:\\Users\\Administrator\\.spyder-py3\\temp.py', 'E:\\GitHubWorkplace\\Python\\PythonSpider\\SimpleCrawler.py', 'E:\\GitHubWorkplace\\Python\\PythonSpider\\followers.json']
 

PythonDemo/spider/signatures.jpg PythonDemo/weixin/signatures.jpgPythonDemo/spider/signatures.jpg renamed to PythonDemo/weixin/signatures.jpg

@@ -0,0 +1,30 @@
+import json
+import requests 
+class SimpleCrawler: 
+    init_url = "https://zhuanlan.zhihu.com/api/columns/pythoneer/followers"
+    offset = 0 
+    def crawl(self, params = None): #必须指定UA， 否则知乎服务器会判定请求不合法 
+        headers = {
+                   "Host": "zhuanlan.zhihu.com",
+                   "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
+                   "AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.84 Safari/537.36",
+       }
+        response = requests.get(self.init_url, headers = headers, params = params) 
+        print(response.url) 
+        data = response.json()# 7000 表示所有关注量# 分页加载更多， 递归调用
+        while self.offset < 7000: 
+              self.parse(data) 
+              self.offset += 20 
+              params = {
+                      "limit": 20,
+                       "offset": self.offset
+                      }
+              self.crawl(params) 
+    def parse(self, data): 
+    #以json格式存储到文件 
+        with open("followers.json", "a", encoding = "utf-8") as f: 
+             for item in data:
+                 f.write(json.dumps(item)) 
+                 f.write('\n') 
+if __name__ == '__main__': 
+    SimpleCrawler().crawl();

PythonDemo/spider/signatures.txt PythonDemo/weixin/signatures.txtPythonDemo/spider/signatures.txt renamed to PythonDemo/weixin/signatures.txt

@@ -0,0 +1,17 @@
+# -*- coding: utf-8 -*-
+"""
+Created on Sat Mar 17 18:30:06 2018
+
+@author: Administrator
+"""
+
+from selenium import webdriver
+## 创建浏览器对象
+browser = webdriver.Firefox()
+## 打开小米社区网站
+browser.get('https://passport.csdn.net/account/login')
+browser.find_element_by_xpath("//*[@id='username']").clear()#清空输入框
+browser.find_element_by_xpath("//*[@id='username']").send_keys("1361583339@qq.com")#输入账号
+browser.find_element_by_xpath("//*[@id='password']").clear()#清空输入框
+browser.find_element_by_xpath("//*[@id='password']").send_keys("ks1996721kr")#输入密码
+browser.find_element_by_xpath("/html/body/div[4]/div/div/div[2]/div/div[1]/div/form/input[8]").click()#登录