学习爬虫中

deadlyedge · Apr 18, 2019 · 717c87a · 717c87a
1 parent 1f935b7
commit 717c87a
Show file tree

Hide file tree

Showing 3 changed files with 27 additions and 0 deletions.
diff --git a/bs4_practise.py b/bs4_practise.py
@@ -0,0 +1,12 @@
+from bs4 import BeautifulSoup
+import requests
+
+data = requests.get('https://www.google.com').content
+
+soup = BeautifulSoup(data, 'html.parser')
+#
+# links =soup.findAll('a')
+# for link in links:
+#     print(link)
+
+print(soup.body.div.attrs)
diff --git a/text.html b/text.html
@@ -0,0 +1,12 @@
+<!DOCTYPE html>
+<html lang="cn">
+<head>
+    <meta charset="UTF-8">
+    <title>This is our page</title>
+</head>
+<body>
+<h1>This is H1</h1>
+<p>something is here, love you guys!!!</p>
+
+</body>
+</html>
diff --git a/ximalaya_audio_grab.py b/ximalaya_audio_grab.py
@@ -0,0 +1,3 @@
+# -*- coding:utf-8 -*-
+
+#抓取解析喜马拉雅的音频信息  存储 mongodb数据库
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1,3 @@
		# -- coding:utf-8 --

		#抓取解析喜马拉雅的音频信息存储 mongodb数据库