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&＃xff1a;

源码&＃xff1a;

import re

from bs4 import BeautifulSoup

from urllib.request import urlopen

url &＃61; "你要解析的网页URL"

html &＃61; urlopen(url).read()

soup &＃61; BeautifulSoup(html,"html.parser")

titles &＃61; soup.select("body script") # CSS 选择器

i &＃61; 1

for title in titles:

if i &＃61;&＃61; 3:

#print(title.get_text())# 标签体、标签属性

str&＃61;title.get_text()

break

if i &＃61;&＃61; 2:

i &＃61; 3

if i &＃61;&＃61; 1:

i &＃61; 2

print(str)

str1 &＃61; "\"\"\""&＃43;""&＃43;"\"\"\""

soup &＃61; BeautifulSoup(str1, "html.parser")

pattern &＃61; re.compile(r"var _url &＃61; ‘(.*?)‘;$", re.MULTILINE | re.DOTALL)

script &＃61; soup.find("script", text&＃61;pattern)

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

s &＃61; pattern.search(script.text).string

print (s.split(‘\‘‘)[11])

原文&＃xff1a;https://www.cnblogs.com/mm20/p/10362963.html