python爬虫篇之正则表达式(二)

import repath = "/yuan/blog/2000/12/"path1 = "/www/yuan/blog/2000/12/"# 开头必须跟^后内容一样reg = "^/yuan/blog/[0-9]{4}/[0-9]{1,2}/"ret = re.findall(reg, path)ret1 = re.findall(reg, path1)print(f"path的输出结果：{ret}")print(f"path1的输出结果：{ret1}")

import repath = "/yuan/blog/2000/12/"path1 = "/yuan/blog/2000/12/aaa"# 结尾必须跟$前内容一样reg = "/yuan/blog/[0-9]{4}/[0-9]{1,2}/$"ret = re.findall(reg, path)ret1 = re.findall(reg, path1)print(f"path的输出结果：{ret}")print(f"path1的输出结果：{ret1}")

import res = "The cat sat on the caterpillar"reg = r"\bcat\b"  #只匹配完整的"cat"r = re.findall(reg, s)print(f"r的输出结果为：{r}")  # 输出：['cat']s1 = "encrypt JSencrypt AESencrypt encrypyData encrypt"r1 = re.findall(r"\bencrypt\b", s1)print(f"r1的输出结果为：{r1}")

import re# 取消特殊功能符号以普通化s = "https://wwwxxxbaidu.com/, https://www.ooaac.com/, https://www.youdao.com/"ret = re.findall(r"https?://www.[a-z]*?.com", s)ret1 = re.findall(r"https?://www\.[a-z]*?\.com", s)print(f"没加\的ret结果：{ret}")print(f"加\的ret1结果：{ret1}")

import retext = """Visit us at example.com for more information.You can also cheak out our partner site: partner-site.orgDon't forget about our blog at blog-example.com!For support, visit support.example.com"""# 正则表达式匹配以 .com 结尾的域名pattern = r'\b[a-zA-Z0-9._%+-]+\.com\b'# 查找所以匹配项matches = re.findall(pattern, text)#输出结果print(f"Matched .com domains: {matches}")

import retext = """Visit us at example.com for more information.You can also cheak ** out our partner site: partner-site.orgDon't forget about ****** our blog **** at blog-example.com!For support, ********* visit support.example.com"""ret = re.findall(r"\*+", text)print(ret)

import res = r"\user\yuan\apple.png,\user\yuan\banana.png,\user\yuan\peach.png,\user\rain\apple.png"ret = re.findall(r"\\user\\yuan\\\w+\.png", s)print(ret)