ari*_*tll 8 python text-extraction pdfminer
我发现这个问题,但它使用命令行,我不想使用子进程在命令行中调用Python脚本并解析HTML文件以获取字体信息.
我想使用PDFminer作为库,我发现这个问题,但它们只是提取纯文本,没有其他信息,如字体名称,字体大小等.
完全披露，我是pdfminer.6的维护者之一。它是 pdfminer for python 3 的社区维护版本。
如今，pdfminer.6 有多个 API 可以从 PDF 中提取文本和信息。对于以编程方式提取信息，我建议使用extract_pages(). 这允许您检查页面上的所有元素，这些元素按布局算法创建的有意义的层次结构排序。
以下示例是显示层次结构中所有元素的 Python 方式。它使用pdfminer.6 的示例目录中的simple1.pdf 。
from pathlib import Path
from typing import Iterable, Any
from pdfminer.high_level import extract_pages
def show_ltitem_hierarchy(o: Any, depth=0):
"""Show location and text of LTItem and all its descendants"""
if depth == 0:
print('element fontname text')
print('------------------------------ -------------------- -----')
print(
f'{get_indented_name(o, depth):<30.30s} '
f'{get_optional_fontinfo(o):<20.20s} '
f'{get_optional_text(o)}'
)
if isinstance(o, Iterable):
for i in o:
show_ltitem_hierarchy(i, depth=depth + 1)
def get_indented_name(o: Any, depth: int) -> str:
"""Indented name of class"""
return ' ' * depth + o.__class__.__name__
def get_optional_fontinfo(o: Any) -> str:
"""Font info of LTChar if available, otherwise empty string"""
if hasattr(o, 'fontname') and hasattr(o, 'size'):
return f'{o.fontname} {round(o.size)}pt'
return ''
def get_optional_text(o: Any) -> str:
"""Text of LTItem if available, otherwise empty string"""
if hasattr(o, 'get_text'):
return o.get_text().strip()
return ''
path = Path('~/Downloads/simple1.pdf').expanduser()
pages = extract_pages(path)
show_ltitem_hierarchy(pages)
输出显示层次结构中的不同元素、字体名称和大小（如果可用）以及该元素包含的文本。
element fontname text
------------------------------ -------------------- -----
generator
LTPage
LTTextBoxHorizontal Hello
LTTextLineHorizontal Hello
LTChar Helvetica 24pt H
LTChar Helvetica 24pt e
LTChar Helvetica 24pt l
LTChar Helvetica 24pt l
LTChar Helvetica 24pt o
LTChar Helvetica 24pt
LTAnno
LTTextBoxHorizontal World
LTTextLineHorizontal World
LTChar Helvetica 24pt W
LTChar Helvetica 24pt o
LTChar Helvetica 24pt r
LTChar Helvetica 24pt l
LTChar Helvetica 24pt d
LTAnno
LTTextBoxHorizontal Hello
LTTextLineHorizontal Hello
LTChar Helvetica 24pt H
LTChar Helvetica 24pt e
LTChar Helvetica 24pt l
LTChar Helvetica 24pt l
LTChar Helvetica 24pt o
LTChar Helvetica 24pt
LTAnno
LTTextBoxHorizontal World
LTTextLineHorizontal World
LTChar Helvetica 24pt W
LTChar Helvetica 24pt o
LTChar Helvetica 24pt r
LTChar Helvetica 24pt l
LTChar Helvetica 24pt d
LTAnno
LTTextBoxHorizontal H e l l o
LTTextLineHorizontal H e l l o
LTChar Helvetica 24pt H
LTAnno
LTChar Helvetica 24pt e
LTAnno
LTChar Helvetica 24pt l
LTAnno
LTChar Helvetica 24pt l
LTAnno
LTChar Helvetica 24pt o
LTAnno
LTChar Helvetica 24pt
LTAnno
LTTextBoxHorizontal W o r l d
LTTextLineHorizontal W o r l d
LTChar Helvetica 24pt W
LTAnno
LTChar Helvetica 24pt o
LTAnno
LTChar Helvetica 24pt r
LTAnno
LTChar Helvetica 24pt l
LTAnno
LTChar Helvetica 24pt d
LTAnno
LTTextBoxHorizontal H e l l o
LTTextLineHorizontal H e l l o
LTChar Helvetica 24pt H
LTAnno
LTChar Helvetica 24pt e
LTAnno
LTChar Helvetica 24pt l
LTAnno
LTChar Helvetica 24pt l
LTAnno
LTChar Helvetica 24pt o
LTAnno
LTChar Helvetica 24pt
LTAnno
LTTextBoxHorizontal W o r l d
LTTextLineHorizontal W o r l d
LTChar Helvetica 24pt W
LTAnno
LTChar Helvetica 24pt o
LTAnno
LTChar Helvetica 24pt r
LTAnno
LTChar Helvetica 24pt l
LTAnno
LTChar Helvetica 24pt d
LTAnno
（类似的答案 在这里， 这里和 这里 ，我会尽力让它们保持同步。）
#!/usr/bin/env python
from pdfminer.pdfparser import PDFParser
from pdfminer.pdfdocument import PDFDocument
from pdfminer.pdfpage import PDFPage
from pdfminer.pdfinterp import PDFResourceManager
from pdfminer.pdfinterp import PDFPageInterpreter
from pdfminer.layout import LAParams
from pdfminer.converter import PDFPageAggregator
import pdfminer
def createPDFDoc(fpath):
fp = open(fpath, 'rb')
parser = PDFParser(fp)
document = PDFDocument(parser, password='')
# Check if the document allows text extraction. If not, abort.
if not document.is_extractable:
raise "Not extractable"
else:
return document
def createDeviceInterpreter():
rsrcmgr = PDFResourceManager()
laparams = LAParams()
device = PDFPageAggregator(rsrcmgr, laparams=laparams)
interpreter = PDFPageInterpreter(rsrcmgr, device)
return device, interpreter
def parse_obj(objs):
for obj in objs:
if isinstance(obj, pdfminer.layout.LTTextBox):
for o in obj._objs:
if isinstance(o,pdfminer.layout.LTTextLine):
text=o.get_text()
if text.strip():
for c in o._objs:
if isinstance(c, pdfminer.layout.LTChar):
print "fontname %s"%c.fontname
# if it's a container, recurse
elif isinstance(obj, pdfminer.layout.LTFigure):
parse_obj(obj._objs)
else:
pass
document=createPDFDoc("/tmp/simple.pdf")
device,interpreter=createDeviceInterpreter()
pages=PDFPage.create_pages(document)
interpreter.process_page(pages.next())
layout = device.get_result()
parse_obj(layout._objs)
| 归档时间： |
|
| 查看次数： |
9070 次 |
| 最近记录： |