Python正则表达式re模块讲解以及其案例举例

>>> import re
>>> help(re.compile)
Help on function compile in module re:

compile(pattern, flags=0)
    Compile a regular expression pattern, returning a pattern object.

>>>

>>> help(re.findall)
Help on function findall in module re:

findall(pattern, string, flags=0)
    Return a list of all non-overlapping matches in the string.

    If one or more capturing groups are present in the pattern, return
    a list of groups; this will be a list of tuples if the pattern
    has more than one group.

    Empty matches are included in the result.

>>> help(re.finditer)
Help on function finditer in module re:

finditer(pattern, string, flags=0)
    Return an iterator over all non-overlapping matches in the
    string.  For each match, the iterator returns a match object.

    Empty matches are included in the result.

>>> help(re.search)
Help on function search in module re:

search(pattern, string, flags=0)
    Scan through string looking for a match to the pattern, returning
    a match object, or None if no match was found.

>>> help(re.match)
Help on function match in module re:

match(pattern, string, flags=0)
    Try to apply the pattern at the start of the string, returning
    a match object, or None if no match was found.

>>> help(re.sub)
Help on function sub in module re:

sub(pattern, repl, string, count=0, flags=0)
    Return the string obtained by replacing the leftmost
    non-overlapping occurrences of the pattern in string by the
    replacement repl.  repl can be either a string or a callable;
    if a string, backslash escapes in it are processed.  If it is
    a callable, it's passed the match object and must return
    a replacement string to be used.

>>> help(re.subn)
Help on function subn in module re:

subn(pattern, repl, string, count=0, flags=0)
    Return a 2-tuple containing (new_string, number).
    new_string is the string obtained by replacing the leftmost
    non-overlapping occurrences of the pattern in the source
    string by the replacement repl.  number is the number of
    substitutions that were made. repl can be either a string or a
    callable; if a string, backslash escapes in it are processed.
    If it is a callable, it's passed the match object and must
    return a replacement string to be used.

>>> help(re.split)
Help on function split in module re:

split(pattern, string, maxsplit=0, flags=0)
    Split the source string by the occurrences of the pattern,
    returning a list containing the resulting substrings.  If
    capturing parentheses are used in pattern, then the text of all
    groups in the pattern are also returned as part of the resulting
    list.  If maxsplit is nonzero, at most maxsplit splits occur,
    and the remainder of the string is returned as the final element
    of the list.

import re
import requests
if __name__ == '__main__':
    """
    测试函数（main）
    """
    N = 25
    j = 1
    for i in range(0, 226, 25):
        url = f'https://movie.douban.com/top250?start={i}&filter='
        headers = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 '
                          '(KHTML, like Gecko) Chrome/89.0.4389.90 Safari/537.36 Edg/89.0.774.63'
        }
        response = requests.get(url=url, headers=headers)
        result = re.findall(r'<a href="(\S+)">\s+'
                            r'<img width="100" alt="(\S+)" src="\S+" class="">\s+'
                            r'</a>', response.text)
        for movie in result:
            url_0 = movie[0]
            response_0 = requests.get(url=url_0, headers=headers)
            score = re.findall(r'<strong class="ll rating_num" property="v:average">(\S+)'
                               r'</strong>\s+'
                               r'<span property="v:best" content="10.0"></span>',
                               response_0.text)[0]
            print(j, end='  ')
            j += 1
            print(movie[1], end='  ')
            print(movie[0], end='  ')
            print(f'评分 : {score}')
        i += N

result = re.findall(r'<a href="(\S+)">\s+'
                            r'<img width="100" alt="(\S+)" src="\S+" class="">\s+'
                            r'</a>', response.text)

score = re.findall(r'<strong class="ll rating_num" property="v:average">(\S+)'
                               r'</strong>\s+'
                               r'<span property="v:best" content="10.0"></span>',
                               response_0.text)[0]