python爬取网页内容_python爬虫之获取页面script里面的内容

这是网页上的script 我要获取的是00914这个数字 直接使用正则表达式即可

运行结果：

源码：

import re

from bs4 import BeautifulSoup

from urllib.request import urlopen

url = "你要解析的网页URL"

html = urlopen(url).read()

soup = BeautifulSoup(html,"html.parser")

titles = soup.select("body script") # CSS 选择器

i = 1

for title in titles:

if i == 3:

#print(title.get_text())# 标签体、标签属性

str=title.get_text()

break

if i == 2:

i = 3

if i == 1:

i = 2

print(str)

str1 = "\"\"\""+""+"\"\"\""

soup = BeautifulSoup(str1, "html.parser")

pattern = re.compile(r"var _url = ‘(.*?)‘;$", re.MULTILINE | re.DOTALL)

script = soup.find("script", text=pattern)

#print (pattern.search(script.text).string)

s = pattern.search(script.text).string

print (s.split(‘\‘‘)[11])

原文：https://www.cnblogs.com/mm20/p/10362963.html