python爬蟲之獲取頁面script里面的內容

這是網頁上的script 我要獲取的是00914這個數字  直接使用正則表達式即可

運行結果：

 

源碼：

 

import re
from bs4 import BeautifulSoup
from urllib.request import urlopen
url = "你要解析的網頁URL"
html = urlopen(url).read()
soup = BeautifulSoup(html,"html.parser")
titles = soup.select("body  script") # CSS 選擇器
i = 1
for title in titles:
    if i == 3:
     #print(title.get_text())# 標簽體、標簽屬性
     str=title.get_text()
     break
    if i == 2:
        i = 3
    if i == 1:
        i = 2

print(str)
str1 = "\"\"\""+"<script>"+str+"</script>"+"\"\"\""
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])