# 每次请求一次，然后写文件，这样可以规避多次请求触发反爬虫

r = requests.get('https://www.pearvideo.com/video_1522192')

html = r.content.decode("utf-8")

print(html)

with open("./test.html","w") as f:

    f.write(html.encode("gbk","ignore").decode("gbk","ignore"))   #再次编码，解码

#读取文件

with open('test.html', encoding='gbk') as file_obj:

    contents = file_obj.read()

#正则匹配视频地址

regex = re.compile('srcUrl="(.+?)"')

print(regex.findall(contents))