U

�R�]�
�@s�dZd
dl
Z
d
dlZddlmZ
ddlmZ
ddlmZm	Z	
ddl
mZmZ
ddl
mZ
dd	lmZmZmZ
dd
lmZ
ddlmZ
ddd�
ZdS)z�
Functions that encapsulate "usual" use-cases for pdfminer, for use making
bundled scripts and for using pdfminer as a module for routine tasks.
�N�
)
�PDFDocument)
�	PDFParser)�PDFResourceManager�PDFPageInterpreter)�	PDFDevice�TagExtractor)
�PDFPage)�XMLConverter�
HTMLConverter�
TextConverter)
�CMapDB)
�ImageWriter�text�utf-8���?�normalFc	Ks
tj
rtjjr|�tjj�
}d
}|r,t|�
}t|d�
}|dkrRt||
|||d�}tj	rj|
tj
krjtj
j}
|dkr�t||
||||
d�}n6|dkr�t
||
||	|||d�}n|d	kr�t||
|d
�}t||�}tj|||||dd�D]}|j|
d
|_|�|�

q�|��
d
S)a
    Parses text from inf-file and writes to outfp file-like object.
    Takes loads of optional arguments but the defaults are somewhat sane.
    Beware laparams: Including an empty LAParams is not the same as passing None!
    Returns nothing, acting as it does on two streams. Use StringIO to get strings.
    
    output_type: May be 'text', 'xml', 'html', 'tag'. Only 'text' works properly.
    codec: Text decoding codec
    laparams: An LAParams object from pdfminer.layout.
        Default is None but may not layout correctly.
    maxpages: How many pages to stop parsing after
    page_numbers: zero-indexed page numbers to operate on.
    password: For encrypted PDFs, the password to decrypt.
    scale: Scale factor
    rotation: Rotation factor
    layoutmode: Default is 'normal', see pdfminer.converter.HTMLConverter
    output_dir: If given, creates an ImageWriter for extracted images.
    strip_control: Does what it says on the tin
    debug: Output more logging data
    disable_caching: Does what it says on the tin
    N)
�cachingr)�codec�laparams�imagewriterZxml)rrrZstripcontrolZhtml)r�scale�
layoutmoderr�tag)
rT)�maxpages�passwordrZcheck_extractableih
)�sixZPY2�sys�stdin�encoding�decoderrrZPY3�stdout�bufferr
rrrr	Z	get_pages�rotateZprocess_page�close)�infZoutfpZ_py2_no_more_posargsZoutput_typerrrZpage_numbersrrZrotationrZ
output_dirZ
strip_control�debugZdisable_caching�otherrZrsrcmgrZdeviceZinterpreterZpage�r)�5/usr/lib/python3/dist-packages/pdfminer/high_level.py�extract_text_to_fpsH





�




�



�







�

r+)NrrNr
Nrrr
rNFFF)�__doc__rrZpdfdocumentrZ	pdfparserrZ	pdfinterprrZ	pdfdevicerrZpdfpager	Z	converterr
rrZcmapdbr
Zimagerr+r)r)r)r*�<module>s2











�