我正在尝试在简短的pdf中查找正则表达式的出现。但是,它不起作用。我不明白为什么,因为如果我尝试搜索一个简单的字符串,我不会遇到任何问题。文本正确呈现。这是我的代码:
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from pdfminer.pdfpage import PDFPage
from io import StringIO
import re
def convert_pdf_to_txt(path):
#\[\s*prima(?!\S)regex = re.compile(r"\[(\s)prima(?!\S)")
rsrcmgr = PDFResourceManager()
retstr = StringIO()
codec = 'utf-8'
laparams = LAParams()
device = TextConverter(rsrcmgr, retstr, codec=codec, laparams=laparams)
fp = open(path, 'rb')
interpreter = PDFPageInterpreter(rsrcmgr, device)
password = ""
maxpages = 0
caching = True
pagenos=set()
for page in PDFPage.get_pages(fp, pagenos, maxpages=maxpages, password=password,caching=caching, check_extractable=True):
interpreter.process_page(page)
text = retstr.getvalue()
fp.close()
device.close()
retstr.close()
reg = re.compile(r"\[(\s)prima(?!\S)")
matches = re.findall(reg, text)
return matches
print(convert_pdf_to_txt("fel_split.pdf"))
这是我的正则表达式:(r"\[(\s)prima(?!\S)")
我想找到“ [prima“。
也许有多个空格字符?试试这个:r"\]\s+prima\s+"