当我们使用正则表达式对字符串做处理的时候可能会有这样的需求:
需要从一大串字符串中找出所有符合我们匹配规则的字符。我们可能会写”*“,”+“这样的,但这样会匹配很多字符,甚至匹配到最后,把好几个符合条件的做成一个结果输出,我们需要对其做限制,比如第一次遇到某个字符时停止匹配。这里就要用到非贪婪限制字符?例如下面这段字符,我要匹配s='xxxxxx';这样的,我需要从这段字符中找出所有的格式为s='xxxxxxx';的字符。观察可以知道这个字符中包含5个这样的符合条件的字符
最开始我们可以这样写:(s='data:image.*';)这样你会发现他会一直匹配到最后一个字符,输出结果只有一个。碰到第一个,;后并不会停下来,因为.*的存在会继续往后匹配。这时候用上?就可以很好解决了 写成这样:(s='data:image.*?';),就能正确匹配出满足条件的5个了。
result = re.findall(r"(s='data:image.*?';)",content)
function(){var s='data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAGQAAABkCAMAAABHPGVmAAAAulBMVEUbGxv+AAD///8AAKOnoo8fXqFQKBQKhUKhUCgUin+XP9wiPMV6Xh9eAAAAAElFTkSuQmCC';var ii=['news-thumbnail-image-52780429785705'];_setImagesSrc(ii,s);})();(function(){var s='data:image/jpeg;base64,/9j/4AAQSkZJRgABAQAAAQABAAD/2wCEAAkGBwgHBgkIBwgKCgkLDRYPDQwMDRsUFRAWIB+OdQt5osxX2lh51zjLCTAPz4FEblcSKMUfInI8M6Tp/5Edv5g9rdKxJpfw1jja6/PBn//2Q\x3d\x3d';var ii=['news-thumbnail-image--4543338495812352792'];_setImagesSrc(ii,s);})();(function(){var s='data:image/jpeg;base64,/9j/4AAQSkZJRgABAQAAAQABAAD/2wCEAAkGBwgHBgkIBwgKCgkLDRYPDQwMDRsUFRAWIBUoyDBPrSwaKhQOY4tG1ChXHDLUw5wKFCuOGWiRjllBPvQoUKOsJ//2Q\x3d\x3d';var ii=['news-thumbnail-image-2184828388954396908'];_setImagesSrc(ii,s);})();(function(){var s='data:image/jpeg;base64,/9j/4AAQSkZJRgABAQAAAQABAAD/2wCEAAkGBwgHBgkIBwgKCgkLDRYPDQwMDRsUFRAWIB596ZDIclIY1Hsxn61vcOpxp2qUerOU4ksXTS6IgvGrRVCx0DDQShHP/2Q\x3d\x3d';var ii=['news-thumbnail-image-52780428761211'];_setImagesSrc(ii,s);})();(function(){var s='data:image/jpeg;base64,/9j/4AAQSkZJRgABAQAAAQABAAD/2wCEAAkGBwgHBgkIBwgKCgkLDRYPDQwMDRsUFRAWIBOAB4nFXRjCA9SKlSszQ7GwqxNz8K8qUrGRaSRXtSpQGP/9k\x3d';