pax_global_header00006660000000000000000000000064142135176630014522gustar00rootroot0000000000000052 comment=f3e89dacc00c55180c7ccf8b91dce40797d6c7b4 api2pdf.python-2.1/000077500000000000000000000000001421351766300142315ustar00rootroot00000000000000api2pdf.python-2.1/.gitignore000066400000000000000000000022721421351766300162240ustar00rootroot00000000000000# Byte-compiled / optimized / DLL files __pycache__/ *.py[cod] *$py.class # C extensions *.so # Distribution / packaging .Python build/ develop-eggs/ dist/ downloads/ eggs/ .eggs/ lib/ lib64/ parts/ sdist/ var/ wheels/ *.egg-info/ .installed.cfg *.egg MANIFEST # PyInstaller # Usually these files are written by a python script from a template # before PyInstaller builds the exe, so as to inject date/other infos into it. *.manifest *.spec # Installer logs pip-log.txt pip-delete-this-directory.txt # Unit test / coverage reports htmlcov/ .tox/ .coverage .coverage.* .cache nosetests.xml coverage.xml *.cover .hypothesis/ .pytest_cache/ # Translations *.mo *.pot # Django stuff: *.log local_settings.py db.sqlite3 # Flask stuff: instance/ .webassets-cache # Scrapy stuff: .scrapy # Sphinx documentation docs/_build/ # PyBuilder target/ # Jupyter Notebook .ipynb_checkpoints # pyenv .python-version # celery beat schedule file celerybeat-schedule # SageMath parsed files *.sage.py # Environments .env .venv env/ venv/ ENV/ env.bak/ venv.bak/ # Spyder project settings .spyderproject .spyproject # Rope project settings .ropeproject # mkdocs documentation /site # mypy .mypy_cache/ test.pyapi2pdf.python-2.1/LICENSE.txt000066400000000000000000000020471421351766300160570ustar00rootroot00000000000000MIT License Copyright (c) 2018 Api2Pdf Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions: The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software. THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.api2pdf.python-2.1/README.md000066400000000000000000000242501421351766300155130ustar00rootroot00000000000000# api2pdf.python Python bindings for [Api2Pdf REST API](https://www.api2pdf.com/documentation/v2) Api2Pdf.com is a powerful REST API for instantly generating PDF and Office documents from HTML, URLs, Microsoft Office Documents (Word, Excel, PPT), Email files, and images. You can generate image preview or thumbnail of a PDF, office document, or email file. The API also supports merge / concatenation of two or more PDFs, setting passwords on PDFs, adding bookmarks to PDFs, splitting or extracting pages from a PDF. Api2Pdf is a wrapper for popular libraries such as **wkhtmltopdf**, **Headless Chrome**, **PdfSharp**, and **LibreOffice**. - [Installation](#installation) - [Resources](#resources) - [Authorization](#authorization) - [Usage](#usage) - [FAQ](https://www.api2pdf.com/faq) ## Add a dependency ### PyPI Run the pip command for installing the client `pip install api2pdf` ## Resources Resources this API supports: - [wkhtmltopdf](#wkhtmltopdf) - [Headless Chrome](#chrome) - [LibreOffice](#libreoffice) - [Merge / Concatenate PDFs](#merge) - [Helper Methods](#helpers) ## Authorization ### Acquire API Key Create an account at [portal.api2pdf.com](https://portal.api2pdf.com/register) to get your API key. ## Usage ### Initialize the Client All usage starts by calling the import command and initializing the client by passing your API key as a parameter to the constructor. from api2pdf import Api2Pdf a2p_client = Api2Pdf('YOUR-API-KEY') Once you initialize the client, you can make calls like so: api_response = a2p_client.Chrome.html_to_pdf('

Hello, World

') print(api_response.result) ### Result Object An `Api2PdfResponse` object is returned from every API call. Call the `result` attribute to retrieve the data. If a call is unsuccessful then `success` will show False and the `error` will provide the reason for failure. Additional attributes include the total data usage in, out, and the cost for the API call, typically very small fractions of a penny. { 'FileUrl': 'https://link-to-pdf-only-available-for-24-hours', 'MbOut': 0.08830547332763672, 'Seconds': 9.43, 'Cost': 0.00017251586914062501, 'Success': True, 'Error': None, 'ResponseId': '6e46637a-650d-46d5-af0b-3d7831baccbb' } For debugging, you can print the `Api2PdfResponse` object to see the request and response data. api_response = a2p_client.Chrome.html_to_pdf('

Hello, World

') print(api_response) Output: ---- API2PDF REQUEST ---- - Headers: {'Authorization': 'YOUR-API-KEY'} - Endpoint: https://v2018.api2pdf.com/chrome/html - Payload: {'html': '

Hello, World

'} ---- API2PDF RESPONSE ---- {'ResponseId': '5ef656a7-2856-43f4-aae3-7b580b0e0421', 'MbOut': 0.012622, 'Cost': 0.000257195288, 'Seconds': 1.208, 'Error': None, 'Success': True, 'FileUrl': 'https://storage.googleapis.com/a2p-v2-storage/5ef656a7-2856-43f4-aae3-7b580b0e0421'} ### wkhtmltopdf **Convert HTML to PDF** api_response = a2p_client.WkHtml.html_to_pdf('

Hello, World

') **Convert HTML to PDF (ldownload PDF as a file and specify a file name)** api_response = a2p_client.WkHtml.html_to_pdf('

Hello, World

', inline_pdf=True, file_name='test.pdf') **Convert HTML to PDF (use keyword arguments for advanced wkhtmltopdf settings)** [View full list of wkhtmltopdf options available.](https://www.api2pdf.com/documentation/advanced-options-wkhtmltopdf/) options = { 'orientation': 'landscape', 'pageSize': 'A4' } api_response = a2p_client.WkHtml.html_to_pdf('

Hello, World

', **options) **Convert URL to PDF** api_response = a2p_client.WkHtml.url_to_pdf('http://www.api2pdf.com') **Convert URL to PDF (download PDF as a file and specify a file name)** api_response = a2p_client.WkHtml.url_to_pdf('http://www.api2pdf.com', inline=False, file_name='test.pdf') **Convert URL to PDF (use keyword arguments for advanced wkhtmltopdf settings)** [View full list of wkhtmltopdf options available.](https://www.api2pdf.com/documentation/advanced-options-wkhtmltopdf/) options = { 'orientation': 'landscape', 'pageSize': 'A4' } api_response = a2p_client.WkHtml.url_to_pdf('http://www.api2pdf.com', **options) --- ## Headless Chrome **Convert HTML to PDF** api_response = a2p_client.Chrome.html_to_pdf('

Hello, World

') **Convert HTML to PDF (download PDF as a file and specify a file name)** api_response = a2p_client.Chrome.html_to_pdf('

Hello, World

', inline=False, file_name='test.pdf') **Convert HTML to PDF (use keyword arguments for advanced Headless Chrome settings)** [View full list of Headless Chrome options available.](https://www.api2pdf.com/documentation/advanced-options-headless-chrome/) options = { 'landscape': True } api_response = a2p_client.Chrome.html_to_pdf('

Hello, World

', **options) **Convert URL to PDF** api_response = a2p_client.Chrome.url_to_pdf('http://www.api2pdf.com') **Convert URL to PDF (download PDF as a file and specify a file name)** api_response = a2p_client.Chrome.url_to_pdf('http://www.api2pdf.com', inline=False, file_name='test.pdf') **Convert URL to PDF (use keyword arguments for advanced Headless Chrome settings)** [View full list of Headless Chrome options available.](https://www.api2pdf.com/documentation/advanced-options-headless-chrome/) options = { 'landscape': True } api_response = a2p_client.Chrome.url_to_pdf('http://www.api2pdf.com', **options) **Convert HTML to Image** api_response = a2p_client.Chrome.html_to_image('

Hello, World

') **Convert URL to Image** api_response = a2p_client.Chrome.url_to_image('http://www.api2pdf.com') --- ## LibreOffice Convert any office file to PDF, image file to PDF, email file to PDF, HTML to Word, HTML to Excel, and PDF to HTML. Any file that can be reasonably opened by LibreOffice should be convertible. Additionally, we have an endpoint for generating a *thumbnail* of the first page of your PDF or Office Document. This is great for generating an image preview of your files to users. You must provide a url to the file. Our engine will consume the file at that URL and convert it. **Convert Microsoft Office Document or Image to PDF** api_response = a2p_client.LibreOffice.any_to_pdf('https://www.api2pdf.com/wp-content/themes/api2pdf/assets/samples/sample-word-doc.docx') **Convert Microsoft Office Document or Image to PDF (download PDF as a file and specify a file name)** api_response = a2p_client.LibreOffice.any_to_pdf('https://www.api2pdf.com/wp-content/themes/api2pdf/assets/samples/sample-word-doc.docx', inline=False, file_name='test.pdf') **Thumbnail or Image Preview of a PDF or Office Document or Email file** api_response = a2p_client.LibreOffice.thumbnail('https://www.api2pdf.com/wp-content/themes/api2pdf/assets/samples/sample-word-doc.docx') **Convert HTML to Microsoft Word or Docx** api_response = a2p_client.LibreOffice.html_to_docx('http://www.api2pdf.com/wp-content/uploads/2021/01/sampleHtml.html') **Convert HTML to Microsoft Excel or Xlsx** api_response = a2p_client.LibreOffice.html_to_xlsx('http://www.api2pdf.com/wp-content/uploads/2021/01/sampleTables.html') **Convert PDF to HTML** api_response = a2p_client.LibreOffice.pdf_to_html('http://www.api2pdf.com/wp-content/uploads/2021/01/1a082b03-2bd6-4703-989d-0443a88e3b0f-4.pdf') --- ## PdfSharp - Merge / Concatenate Two or More PDFs, Add bookmarks to pdfs, add passwords to pdfs To use the merge endpoint, supply a list of urls to existing PDFs. The engine will consume all of the PDFs and merge them into a single PDF, in the order in which they were provided in the list. **Merge PDFs from list of URLs to existing PDFs** links_to_pdfs = ['https://LINK-TO-PDF', 'https://LINK-TO-PDF'] merge_result = a2p_client.PdfSharp.merge(links_to_pdfs) **Merge PDFs from list of URLs to existing PDFs (download PDF as a file and specify a file name)** links_to_pdfs = ['https://LINK-TO-PDF', 'https://LINK-TO-PDF'] merge_result = a2p_client.PdfSharp.merge(links_to_pdfs, inline=True, file_name='test.pdf') **Add bookmarks to existing PDF** url = 'https://link-to-pdf' bookmarks = [ { 'Page': 0, 'Title': 'Introduction' }, { 'Page': 1, 'Title': 'Second page' } ] response = a2p.PdfSharp.add_bookmarks(url, bookmarks) **Add password to existing PDF** url = 'https://link-to-pdf' password = 'hello' response = a2p.PdfSharp.add_password(url, password) **Extract pages, or split an existing PDF** [More information here](https://www.api2pdf.com/extract-pages-out-of-a-pdf-with-rest-api/) url = 'https://link-to-pdf' start = 0 end = 2 response = a2p.PdfSharp.extract_pages(url, start, end) --- ## Helper Methods **Api2PdfResponse: download_file()** On any `Api2PdfResponse` that succesfully generated a pdf, you can use the handy `download_file()` method to download the pdf to a file-like object which you can then save to your local cache. If the pdf generation was unsuccessful, it will throw a FileNotFoundException. ``` from api2pdf import Api2Pdf a2p_client = Api2Pdf('YOUR-API-KEY') # merge pdfs links_to_pdfs = ['https://LINK-TO-PDF', 'https://LINK-TO-PDF'] merge_result = a2p_client.PdfSharp.merge(links_to_pdfs) pdf_as_file_object = merge_result.download_file() ``` **Delete a PDF on Command with delete(response_id)** By default, Api2Pdf will automatically delete your PDFs after 24 hours. If you have higher security requirements and need to delete the PDFs at-will, you can do so by calling the `delete(response_id)` method on the Api2Pdf object where `response_id` parameter comes from the responseId attribute in the Api2PdfResponse result. ``` from api2pdf import Api2Pdf a2p_client = Api2Pdf('YOUR-API-KEY') # generate a pdf api_response = a2p_client.Chrome.html_to_pdf('

Hello World

') response_id = api_response.result['ResponseId'] # delete the pdf a2p_client.delete(response_id) ``` api2pdf.python-2.1/api2pdf/000077500000000000000000000000001421351766300155565ustar00rootroot00000000000000api2pdf.python-2.1/api2pdf/__init__.py000066400000000000000000000000471421351766300176700ustar00rootroot00000000000000from .api2pdf import * name = 'api2pdf'api2pdf.python-2.1/api2pdf/api2pdf.py000066400000000000000000000153661421351766300174700ustar00rootroot00000000000000import requests import json class Api2Pdf(object): def __init__(self, api_key, base_url='https://v2.api2pdf.com', tag=''): self.api_key = api_key self.tag = tag self.base_url = base_url @property def WkHtml(self): return Api2Pdf_WkHtml(self.api_key, self.base_url) @property def Chrome(self): return Api2Pdf_Chrome(self.api_key, self.base_url) @property def LibreOffice(self): return Api2Pdf_LibreOffice(self.api_key, self.base_url) @property def PdfSharp(self): return Api2Pdf_PdfSharp(self.api_key, self.base_url) def delete(self, response_id): headers = self.request_header endpoint = f'/file/{response_id}'.format(response_id=response_id) full_endpoint = self.base_url + endpoint response = requests.delete(full_endpoint, headers=headers) return Api2PdfResponse(headers, full_endpoint, '', response) def _build_base_payload(self, inline=True, file_name=None, **options): payload = { 'inline': inline } if file_name != None: payload['fileName'] = file_name if options != None: payload['options'] = options return payload def _make_request(self, endpoint, payload): headers = self.request_header payload_as_json = json.dumps(payload) full_endpoint = self.base_url + endpoint response = requests.post(full_endpoint, data=payload_as_json, headers=headers) return Api2PdfResponse(headers, full_endpoint, payload, response) @property def request_header(self): header = {} header['Authorization'] = self.api_key if self.tag: header['Tag'] = self.tag return header class Api2Pdf_WkHtml(Api2Pdf): def html_to_pdf(self, html, inline=True, file_name=None, **options): payload = self._build_base_payload(inline, file_name, **options) payload['html'] = html return self._make_request('/wkhtml/pdf/html', payload) def url_to_pdf(self, url, inline=True, file_name=None, **options): payload = self._build_base_payload(inline, file_name, **options) payload['url'] = url return self._make_request('/wkhtml/pdf/url', payload) class Api2Pdf_Chrome(Api2Pdf): def html_to_pdf(self, html, inline=True, file_name=None, **options): payload = self._build_base_payload(inline, file_name, **options) payload['html'] = html return self._make_request('/chrome/pdf/html', payload) def url_to_pdf(self, url, inline=True, file_name=None, **options): payload = self._build_base_payload(inline, file_name, **options) payload['url'] = url return self._make_request('/chrome/pdf/url', payload) def html_to_image(self, html, inline=True, file_name=None, **options): payload = self._build_base_payload(inline, file_name, **options) payload['html'] = html return self._make_request('/chrome/image/html', payload) def url_to_image(self, url, inline=True, file_name=None, **options): payload = self._build_base_payload(inline, file_name, **options) payload['url'] = url return self._make_request('/chrome/image/url', payload) class Api2Pdf_LibreOffice(Api2Pdf): def any_to_pdf(self, url, inline=True, file_name=None): payload = self._build_base_payload(inline, file_name) payload['url'] = url return self._make_request('/libreoffice/any-to-pdf', payload) def thumbnail(self, url, inline=True, file_name=None): payload = self._build_base_payload(inline, file_name) payload['url'] = url return self._make_request('/libreoffice/thumbnail', payload) def pdf_to_html(self, url, inline=True, file_name=None): payload = self._build_base_payload(inline, file_name) payload['url'] = url return self._make_request('/libreoffice/pdf-to-html', payload) def html_to_docx(self, url, inline=True, file_name=None): payload = self._build_base_payload(inline, file_name) payload['url'] = url return self._make_request('/libreoffice/html-to-docx', payload) def html_to_xlsx(self, url, inline=True, file_name=None): payload = self._build_base_payload(inline, file_name) payload['url'] = url return self._make_request('/libreoffice/html-to-xlsx', payload) class Api2Pdf_PdfSharp(Api2Pdf): def merge(self, urls, inline=True, file_name=None): payload = self._build_base_payload(inline, file_name) payload['urls'] = urls return self._make_request('/pdfsharp/merge', payload) def add_bookmarks(self, url, bookmarks, inline=True, file_name=None): payload = self._build_base_payload(inline, file_name) payload['url'] = url payload['bookmarks'] = bookmarks return self._make_request('/pdfsharp/bookmarks', payload) def add_password(self, url, userpassword, ownerpassword=None, inline=True, file_name=None): payload = self._build_base_payload(inline, file_name) payload['url'] = url payload['userpassword'] = userpassword if ownerpassword != None: payload['ownerpassword'] = ownerpassword return self._make_request('/pdfsharp/password', payload) def extract_pages(self, url, start=0, end=0, inline=True, file_name=None): payload = self._build_base_payload(inline, file_name) payload['url'] = url payload['start'] = start payload['end'] = end return self._make_request('/pdfsharp/extract-pages', payload) class Api2PdfResponse(object): def __init__(self, headers, endpoint, payload_as_json, response): self.headers = headers self.endpoint = endpoint self.payload_as_json = payload_as_json self._result = json.loads(response.text) @property def request(self): request_info = { 'headers': self.headers, 'endpoint': self.endpoint, 'payload': self.payload_as_json, } return request_info @property def result(self): return self._result def download_file(self): USERAGENT = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36'} if self.result['Success']: downloaded_file = requests.get(self.result['FileUrl'], headers=USERAGENT) data = downloaded_file.content return data else: raise FileNotFoundError("File never generated " + self.result['error']) def __str__(self): return """ ---- API2PDF REQUEST ---- - Headers: {0} - Endpoint: {1} - Payload: {2} ---- API2PDF RESPONSE ---- {3} """.format(self.headers, self.endpoint, self.payload_as_json, self.result) api2pdf.python-2.1/setup.py000066400000000000000000000020341421351766300157420ustar00rootroot00000000000000import setuptools with open("README.md", "r") as fh: long_description = fh.read() setuptools.setup( name="api2pdf", version="2.1.0", author="Zack Schwartz", author_email="support@api2pdf.com", description="This client library is a wrapper for the Api2Pdf.com REST API. See full REST api documentation at https://www.api2pdf.com/documentation/v2. Api2Pdf is a powerful API that supports HTML to PDF, URL to PDF, HTML to Image, URL to Image, Thumbnail / image preview of an Office file, Office files (Word to PDF), HTML to Docx, HTML to excel, PDF to HTML, merge PDFs together, add bookmarks to PDFs, add passwords to PDFs", long_description=long_description, long_description_content_type="text/markdown", url="https://github.com/api2pdf/api2pdf.python", packages=setuptools.find_packages(), install_requires=[ 'requests', ], classifiers=( "Programming Language :: Python :: 3", "License :: OSI Approved :: MIT License", "Operating System :: OS Independent", ), )