7.4

Author: tompanxin

.idea/Python.iml

@@ -0,0 +1,38 @@
+# 请求json接口整体数据 抽取想要的 保存数据
+import requests
+import json
+response=requests.get("https://movie.douban.com/j/chart/top_list?type=11&interval_id=100%3A90&action=&start=0&limit=20")
+py_data=json.loads(response.text)
+for i in py_data:
+    items={'电影名称':i['title'],'上映地区':i['regions'],
+           '评分':i['score'],'上映时间':i['release_date']}
+    # print(items)
+    content=json.dumps(items,ensure_ascii=False)+".\n"
+    with open("douban.json" , "a" , encoding="utf-8") as f:
+        f.write(content)
+        print(content)
+
+
+
+
+
+
+
+
+
+
+
+
+# import requests
+# import json
+# response=requests.get("http://image.baidu.com/pv/pv.gif?dsp=pc&tn=result&hs=2&type=prerequire&t=1556545641129")
+# py_data=json.loads(response.text)
+# for i in py_data:
+#     print(i)
+#     # print(items)
+#     # content=json.dumps(items,ensure_ascii=False)+".\n"
+#     # with open("douban.json" , "a" , encoding="utf-8") as f:
+#     #     f.write(content)
+#     #     print(content)
+
+

.idea/encodings.xml

@@ -1,23 +1,54 @@
+
+# from time import sleep
+# from selenium import webdriver
+#
+# def getFile(url):
+#     #实例化一个浏览器驱动
+#     chrome = webdriver.Chrome()
+#
+#     #访问页面
+#     chrome.get(url)
+#     #捕获元素
+#
+#     texts = chrome.find_elements_by_xpath("//div[@class='content']/p")
+#     for t in texts:
+#         print(t.text)
+#     sleep(1)
+#     next_url = chrome.find_elements_by_xpath("//a[@class='nextchapter']")
+#     if next_url:
+#         next_urls = next_url[0].get_attribute("href")
+#         getFile(next_urls)
+#     else:
+#         chrome.close()
+#         return
+#     #关闭浏览器
+##################################################################
+
 from time import sleep
 from selenium import webdriver
 
-def getFile(url):
+def getFile(chrome, url):
     #实例化一个浏览器驱动
-    chrome = webdriver.Chrome()
-
     #访问页面
     chrome.get(url)
     #捕获元素
-
-    texts = chrome.find_elements_by_xpath("//div[@class='content']/p")
-    for t in texts:
-        print(t.text)
+    texts = chrome.find_elements_by_xpath("//div[@class='bg']/h1")
+    textcont = chrome.find_elements_by_xpath("//div[@class='content-body']/p")
+    # print(texts,textcont)
+    with open("1.txt","a") as f:
+        f.write(texts[0].text+"\n")
+        for i in textcont:
+            f.write(i.text + "\n")
     sleep(1)
-    next_url = chrome.find_elements_by_xpath("//a[@class='nextchapter']")
+    next_url = chrome.find_elements_by_xpath("//a[@id='xiayipian']")
     if next_url:
         next_urls = next_url[0].get_attribute("href")
-        getFile(next_urls)
+        # print(next_urls)
+        getFile(chrome,next_urls)
     else:
         chrome.close()
         return
     #关闭浏览器
+if __name__ == '__main__':
+    chrome = webdriver.Chrome()
+    getFile(chrome, "http://seputu.com/biji2/127.html")

.idea/misc.xml

@@ -1,16 +1,37 @@
+# from selenium import webdriver
+#
+# #实例化一个浏览器驱动
+# chrome = webdriver.Chrome()
+#
+# #访问页面
+# chrome.get("https://www.baidu.com/")
+# #捕获元素
+# inputs = chrome.find_element_by_id("kw")
+# #对元素进行操作
+# inputs.send_keys("老边饺子")
+# button = chrome.find_element_by_id("su")
+# button.click()
+# #关闭浏览器
+# chrome.close()
+##########################################################
 from selenium import webdriver
-
-#实例化一个浏览器驱动
+import time
 chrome = webdriver.Chrome()
-
-#访问页面
-chrome.get("https://www.baidu.com/")
-#捕获元素
-inputs = chrome.find_element_by_id("kw")
-#对元素进行操作
-inputs.send_keys("老边饺子")
-button = chrome.find_element_by_id("su")
-button.click()
+def qqzone():
+    #访问页面
+    chrome.get("https://xui.ptlogin2.qq.com/cgi-bin/xlogin?proxy_url=https%3A//qzs.qq.com/qzone/v6/portal/proxy.html&daid=5&&hide_title_bar=1&low_login=0&qlogin_auto_login=1&no_verifyimg=1&link_target=blank&appid=549000912&style=22&target=self&s_url=https%3A%2F%2Fqzs.qq.com%2Fqzone%2Fv5%2Floginsucc.html%3Fpara%3Dizone&pt_qr_app=手机QQ空间&pt_qr_link=https%3A//z.qzone.com/download.html&self_regurl=https%3A//qzs.qq.com/qzone/v6/reg/index.html&pt_qr_help_link=https%3A//z.qzone.com/download.html&pt_no_auth=0")
+    time.sleep(1)
+    #捕获元素
+    button = chrome.find_elements_by_class_name("face")
+    #对元素进行操作
+    button[0].click()
+    time.sleep(1)
+    button1 = chrome.find_element_by_id("aAppstore")
+    button1.click()
+    button2 = chrome.find_elements_by_class_name("my-app-list-item")
+    print(button2.text)
+qqzone()
+# nongchang()
+# time.sleep(100)
 #关闭浏览器
-chrome.close()
-
+# chrome.close()