变更

python爬虫/beautiful_soup库.py

@@ -0,0 +1,50 @@
+from bs4 import BeautifulSoup
+import requests
+
+url = "https://python123.io/ws/demo.html"
+try:
+    r = requests.get(url, timeout=20)
+    r.raise_for_status()
+    r.encoding = r.apparent_encoding
+except:
+    print("出现异常")
+
+demo = r.text
+
+soup = BeautifulSoup(demo, "html.parser")
+
+# 标签
+print(soup.title)  # 获取title标签的内容
+
+# 标签的名字
+tag = soup.a
+print(tag)  # 获得了第一个a标签的内容
+print(soup.a.name)
+print(soup.a.parent.name)  # 查询a标签父标签名字
+print(soup.a.parent.parent.name)  # 查询p标签父标签名字
+
+# 标签的属性
+print(tag.attrs)  # 查询标签的属性
+# 结果{'href': 'http://www.icourse163.org/course/BIT-268001', 'class': ['py1'], 'id': 'link1'}
+print(tag.attrs['class'])  # 查询class属性内容
+# 结果['py1']
+print(type(tag.attrs))  # <class 'dict'>
+print(type(tag))  # <class 'bs4.element.Tag'>
+
+# 标签内非属性字符串
+print(soup.a)  # 查询a标签内容
+# <a class="py1" href="http://www.icourse163.org/course/BIT-268001" id="link1">Basic Python</a>
+print(soup.a.string)  # 查询a标签内非属性字符产
+# Basic Python
+print(soup.b)  # <b>The demo python introduces several python courses.</b>
+print(soup.b.string)  # The demo python introduces several python courses.
+# 由于b.string没有<b></b>
+# 所以Navigable String 可以跨越多个标签属性的
+print(type(soup.a.string))  # <class 'bs4.element.NavigableString'>
+
+# 标签注释
+newsoup = BeautifulSoup("<b><!-- This is a comment--></b><p>This is not a comment</p>", "html.parser")
+print(newsoup.b.string)
+print(newsoup.p.string)# 注释并未表明，因此区分注释需要用type（）来区分
+print(type(newsoup.b.string))
+print(type(newsoup.p.string))