From d53837451873cd9f71fec86823f2e81ecf7c93a3 Mon Sep 17 00:00:00 2001
From: MorrisLCY <33283279+MorrisLCY@users.noreply.github.com>
Date: Sun, 11 Nov 2018 16:39:41 +0800
Subject: [PATCH] Add files via upload

---
 main.py | 73 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 73 insertions(+)
 create mode 100644 main.py

diff --git a/main.py b/main.py
new file mode 100644
index 0000000..2f184c5
--- /dev/null
+++ b/main.py
@@ -0,0 +1,73 @@
+
+#-------------------------------------------
+# 匯入必要模組
+#-------------------------------------------
+from selenium import webdriver
+from html.parser import HTMLParser
+
+
+#-------------------------------------------
+# 定義一個HTML解譯類別
+#-------------------------------------------
+class MyHTMLParser(HTMLParser):
+    content=''
+    print=False
+
+    def handle_data(self, data):
+        if data.strip()=='驚奇4超人':
+            self.print=True
+
+        if '期待度' in data.strip():
+            self.print=False
+        if data.strip()=='劇情介紹':
+            self.print=True
+
+        if '展開劇情簡介' in data.strip():
+            self.print=False
+
+        if self.print:
+            self.content+=data
+
+    def get_content(self):
+        return self.content
+
+#-------------------------------------------
+# 載入Chrome驅動程式
+#-------------------------------------------
+driver = webdriver.Chrome("chromedriver.exe")
+
+
+#-------------------------------------------
+# 待拜訪的網址
+#-------------------------------------------
+urls=[
+	'https://movies.yahoo.com.tw/movieinfo_main.html/id=5644'
+	]
+
+
+#-------------------------------------------
+# 依序將範例網址交給瀏覽器
+#-------------------------------------------
+for url in urls:
+    driver.get(url)
+
+    # 取得網頁原始碼
+    with open('out.txt', 'w', encoding='utf-8') as outfile:
+        pageSource = driver.page_source
+
+        #-------------------------------------------
+        # 取出沒有標籤的內容
+        #-------------------------------------------
+        parser = MyHTMLParser()
+        parser.feed(pageSource)
+
+        content=parser.get_content()
+        print(content)
+
+        outfile.write(content)
+
+
+#-------------------------------------------
+# 關閉Chrome驅動程式
+#-------------------------------------------
+driver.close()