Python杂谈（3）——BeautifulSoup库全面介绍

from bs4 import BeautifulSoup
import requests
r = requests.get("http://python123.io/ws/demo.html")
#print(r.text)
demo = r.text
soup = BeautifulSoup(demo,"html.parser")
#输出网页全部内容
#print(soup.prettify())
#截取网页中的title标签
print(soup.title)
#截取网页中的a标签
print(soup.a)
#看a标签的父标签
print(soup.a.parent.name)
#看a标签的父标签的父标签
print(soup.a.parent.parent.name)
tag = soup.a
print(tag)
#查看标签的各个属性信息
print(tag.attrs)
#如果获取某个属性的值
print(tag.attrs['class'])
#获取标签当中的文本信息
print(soup.a.string)
print(soup.p.string)

from bs4 import BeautifulSoup
import requests
r = requests.get("http://python123.io/ws/demo.html")
demo = r.text
soup = BeautifulSoup(demo,"html.parser")
#查看head的内容
print(soup.head)
#查看head的儿子节点
print(soup.head.contents)
#查看body的儿子节点
print(soup.body.contents)
#查看儿子节点的个数
print(len(soup.body.contents))
#查看某个儿子节点
print(soup.body.contents[1])
#标签树的下行儿子遍历
for child in soup.body.children:
    print(child)
#标签树的下行所有遍历
print("____________________")
for child in soup.body.descendants:
    print(child)

from bs4 import BeautifulSoup
import requests
r = requests.get("http://python123.io/ws/demo.html")
demo = r.text
soup = BeautifulSoup(demo,"html.parser")
print(soup.html.parent)
#标签树的上行遍历
for parent in soup.a.parents:
    if parent is None:
        print(parent)
    else:
        print(parent.name)

#平行遍历都必须发生在同一个父节点下个各个节点
from bs4 import BeautifulSoup
import requests
r = requests.get("http://python123.io/ws/demo.html")
demo = r.text
soup = BeautifulSoup(demo,"html.parser")
#a标签的下一个平行标签
print(soup.a.next_sibling)
#a标签的下一个平行标签的下一个平行标签
print(soup.a.next_sibling.next_sibling)
#a标签的前一个平行标签
print(soup.a.previous_sibling)
#检测a标签的父标签
print(soup.a.parent)
#遍历后续节点
print("===================")
for sibling in soup.a.next_siblings:
    print(sibling)
print("===================")
#遍历前续节点
for sibling in soup.a.previous_siblings:
    print(sibling)

from bs4 import BeautifulSoup
import requests
import re
r = requests.get("http://python123.io/ws/demo.html")
demo = r.text
soup = BeautifulSoup(demo,"html.parser")
#查找所有的a标签
print(soup.find_all('a'))
#可以在里面放列表类型
print(soup.find_all(['a','b']))
#如果里面放的是True，就是找所有的标签
for tag in soup.find_all(True):
    print(tag.name)
#如果想找所有b开头的标签
for tag in soup.find_all(re.compile('b')):
    print(tag.name)

from bs4 import BeautifulSoup
import requests
import re
r = requests.get("http://python123.io/ws/demo.html")
demo = r.text
soup = BeautifulSoup(demo,"html.parser")
#找到p标签中带有course值的标签
print(soup.find_all('p','course'))
#找到id='link1'  （查找标签域中）
print(soup.find_all(id='link1'))
#如果写id值中为link的 （赋值必须精确）
print(soup.find_all(id='link'))
#比如检索到所有id中包括link的
print(soup.find_all(id=re.compile('link')))
#recursise是否对子孙全部检索，默认为True
print(soup.find_all('a'))
print(soup.find_all('a',recursive=False))
#检索字符串(在字符串域)
print(soup.find_all(string = 'Basic Python'))
#检索到更多
print(soup.find_all(string = re.compile('Python')))

from bs4 import BeautifulSoup
import requests
r = requests.get("http://python123.io/ws/demo.html")
print(r.text)
demo = r.text
soup = BeautifulSoup(demo,"html.parser")
#输出网页全部内容（以一种更加友好的方式）
print(soup.prettify())
#对单个信息的处理(a标签)
print(soup.a.prettify())