189. Advanced Regular Expressions with re

1. Positive Lookahead

Copy

import re

# Match 'Python' only if followed by 'Rocks'
pattern = r"Python(?= Rocks)"
text = "Python Rocks is amazing!"
matches = re.findall(pattern, text)
print(matches)  # Output: ['Python']

---

2. Negative Lookahead

Copy

import re

# Match 'Python' only if not followed by 'Rocks'
pattern = r"Python(?! Rocks)"
text = "Python is fun, but Python Rocks too!"
matches = re.findall(pattern, text)
print(matches)  # Output: ['Python']

---

3. Positive Lookbehind

Copy

import re

# Match 'Rocks' only if preceded by 'Python'
pattern = r"(?<=Python )Rocks"
text = "Python Rocks is amazing!"
matches = re.findall(pattern, text)
print(matches)  # Output: ['Rocks']

---

4. Negative Lookbehind

Copy

import re

# Match 'Rocks' only if not preceded by 'Python'
pattern = r"(?<!Python )Rocks"
text = "Python Rocks or just Rocks!"
matches = re.findall(pattern, text)
print(matches)  # Output: ['Rocks']

---

5. Named Groups

Copy

import re

# Match and capture groups with names
pattern = r"(?P<first>\w+) (?P<last>\w+)"
text = "John Doe"
match = re.search(pattern, text)
if match:
    print(match.group("first"))  # Output: John
    print(match.group("last"))   # Output: Doe

---

6. Flags: Ignore Case

Copy

import re

# Match ignoring case
pattern = r"python"
text = "Python is powerful."
matches = re.findall(pattern, text, flags=re.IGNORECASE)
print(matches)  # Output: ['Python']

---

7. Flags: Multiline Mode

Copy

import re

# Match '^Hello' in each line using multiline mode
pattern = r"^Hello"
text = "Hello World\nHello Python\nGoodbye World"
matches = re.findall(pattern, text, flags=re.MULTILINE)
print(matches)  # Output: ['Hello', 'Hello']

---

8. Non-Capturing Groups

Copy

import re

# Use non-capturing groups for better performance
pattern = r"(?:Python|Java) is (\w+)"
text = "Python is fun. Java is great."
matches = re.findall(pattern, text)
print(matches)  # Output: ['fun', 'great']

---

9. Match with Unicode Characters

Copy

import re

# Match Unicode words
pattern = r"\w+"
text = "Café München"
matches = re.findall(pattern, text, flags=re.UNICODE)
print(matches)  # Output: ['Café', 'München']

---

10. Combining Multiple Flags

Copy

import re

# Combine re.IGNORECASE and re.DOTALL
pattern = r"python.*"
text = "Python is powerful.\npython spans lines!"
matches = re.findall(pattern, text, flags=re.IGNORECASE | re.DOTALL)
print(matches)  # Output: ['Python is powerful.\npython spans lines!']

---