变更

python爬虫/RE.py

@@ -0,0 +1,29 @@
+import re
+
+match = re.search(r'[1-9]\d{5}', 'bad116105sfa', flags=0)
+print(match.group(0))
+
+match1 = re.match(r'[1-9]\d{5}', 'bad116105sfa', flags=0)
+# print(match1.group())  # 返回类型为空变量，不用if判断会报错
+if match1:
+    print(match1.group())  # if 判断出match1为空，输出结果为空
+    # 原因为字符串开始为字母，match1匹配不到字符串
+
+match2 = re.match(r'[1-9]\d{5}', '116105sfa', flags=0)
+if match2:
+    print(match2.group())  # 去掉头部字母，则可以取出
+
+ls = re.findall(r'[1-9]\d{5}', '116105sfa116110sadf', flags=0)
+print(ls)  # 输出类型为列表
+
+ls1 = re.split(r'[1-9]\d{5}', 'sad116105ej116110')
+print(ls1)  # ['sad', 'ej', '']
+ls2 = re.split(r'[1-9]\d{5}', 'sad116105ej116110', maxsplit=1)
+print(ls2)  # ['sad', 'ej116110'],剩余部分不做匹配
+
+for m1 in re.finditer(r'[1-9]\d{5}', '116105sfa 116110sadf'):
+    if m1:
+        print(m1.group(0))
+
+match14 = re.sub(r'[1-9]\d{5}', 'helloworld', '116105sfa 116110sadf', count=1)
+print(match14)