Python正则表达式：循环浏览目录中每个文件的第一行

Question

I want to loop through .txt files and use the date (eg April 1, 1993) from the first line in that file.

This code works, but matches through the entire file and not just the first line (note: the code Im showing below shows more than just the date matching loop):

Script below is updated and it works:

articles = glob.glob("*.txt")
y = 1

for f in articles:
    with open(f, "r") as content:
        wordcount = "x"
        lines = content.readlines()
        for line in lines :
            if line[0:7] == "LENGTH:":
                lineclean = re.sub('[#%&\<>*?:/{}$@+|=]', '', line)
                wordcount = lineclean[7:13]
                if wordcount[5] == "w":
                    wordcount = wordcount[0:4]
                elif wordcount[4] == "w":
                    wordcount = wordcount[0:3]
                elif wordcount[3] == "w":
                    wordcount =  wordcount[0:2]
                elif wordcount[2] == "w":
                    wordcount =  wordcount[0:1]
    with open(f, "r") as content:
        first_line = next(content)
        try:
            import re
            match = re.search('(Jan(uary)?|Feb(ruary)?|Mar(ch)?|Apr(il)?|May|Jun(e)?|Jul(y)?|Aug(ust)?|Sep(tember)?|Oct(ober)?|Nov(ember)?|Dec(ember)?)\s+\d{1,2},\s+\d{4}', first_line).group()
        except:
            pass           
        from dateutil import parser  
        parsed_pubdate = parser.parse(match).strftime('%Y-%m-%d')                  
    try:
        if wordcount != "x":
            move(f, "{parsed_pubdate}_{wordcount}_{source}.txt".format(**locals()))
        else:
            pass
    except OSError:
        pass
    y += 1
    content.close() 

In order to match dates only in the first line of the file, I add ^\\s and flags=re.MULTILINE , so I get:

match = re.search('^\s(Jan(uary)?|Feb(ruary)?|Mar(ch)?|Apr(il)?|May|Jun(e)?
|Jul(y)?|Aug(ust)?|Sep(tember)?|Oct(ober)?|Nov(ember)?
|Dec(ember)?)\s+\d{1,2},\s+\d{4}', line, flags=re.MULTILINE).group()

However, now the program only uses one date (the date of the last file in the folder) and uses that for every file (so every file gets the same date, while the dates vary in the original .txt files).

I uncluded the entire step this loop is part of, but my problem only applies to the regex date matching loop. Thanks in advance for your help!

Answer 1

articles = glob.glob("*.txt")
y = 1

for f in articles:
    with open(f, "r") as content:
        wordcount = "x"
        lines = content.readlines()
        for line in lines :
            if line[0:7] == "LENGTH:":
                lineclean = re.sub('[#%&\<>*?:/{}$@+|=]', '', line)
                wordcount = lineclean[7:13]
                if wordcount[5] == "w":
                    wordcount = wordcount[0:4]
                elif wordcount[4] == "w":
                    wordcount = wordcount[0:3]
                elif wordcount[3] == "w":
                    wordcount =  wordcount[0:2]
                elif wordcount[2] == "w":
                    wordcount =  wordcount[0:1]
    with open(f, "r") as content:
        first_line = next(content)
        try:
            import re
            match = re.search('(Jan(uary)?|Feb(ruary)?|Mar(ch)?|Apr(il)?|May|Jun(e)?|Jul(y)?|Aug(ust)?|Sep(tember)?|Oct(ober)?|Nov(ember)?|Dec(ember)?)\s+\d{1,2},\s+\d{4}', first_line).group()
        except:
            pass           
        from dateutil import parser  
        parsed_pubdate = parser.parse(match).strftime('%Y-%m-%d')                  
    try:
        if wordcount != "x":
            move(f, "{parsed_pubdate}_{wordcount}_{source}.txt".format(**locals()))
        else:
            pass
    except OSError:
        pass
    y += 1
    content.close()