How to use the pdfplumber.page.Page function in pdfplumber

To help you get started, we’ve selected a few pdfplumber examples, based on popular ways it is used in public projects.

Secure your code as it's written. Use Snyk Code to scan source code in minutes - no build needed - and fix issues immediately.

github jsvine / pdfplumber / pdfplumber / page.py View on Github external
def __init__(self, parent_page):
        self.parent_page = parent_page
        self.pdf = parent_page.pdf
        self.page_obj = parent_page.page_obj
        self.page_number = parent_page.page_number
        self.flush_cache(Container.cached_properties)

        if type(parent_page) == Page:
            self.root_page = parent_page
        else:
            self.root_page = parent_page.root_page
github jsvine / pdfplumber / pdfplumber / pdf.py View on Github external
def pages(self):
        if hasattr(self, "_pages"): return self._pages

        doctop = 0
        pp = self.pages_to_parse
        self._pages = []
        for i, page in enumerate(PDFPage.create_pages(self.doc)):
            page_number = i+1
            if pp != None and page_number not in pp: continue
            p = Page(self, page, page_number=page_number, initial_doctop=doctop)
            self._pages.append(p)
            doctop += p.height
        return self._pages
github jsvine / pdfplumber / pdfplumber / page.py View on Github external
test_function
                )
                return self._objects
        filtered = FilteredPage(self)
        filtered.bbox = self.bbox
        return filtered

    def to_image(self, resolution=None):
        """
        For conversion_kwargs, see http://docs.wand-py.org/en/latest/wand/image.html#wand.image.Image
        """
        from .display import PageImage, DEFAULT_RESOLUTION
        res = resolution or DEFAULT_RESOLUTION
        return PageImage(self, resolution=res)

class DerivedPage(Page):
    is_original = False
    def __init__(self, parent_page):
        self.parent_page = parent_page
        self.pdf = parent_page.pdf
        self.page_obj = parent_page.page_obj
        self.page_number = parent_page.page_number
        self.flush_cache(Container.cached_properties)

        if type(parent_page) == Page:
            self.root_page = parent_page
        else:
            self.root_page = parent_page.root_page