Skip to content

Commit 65533c1

Browse files
datalogics-cgreendatalogics-cgreen
committed
Add Convert to PDF
- Add methods for conversion from file and conversion from url - Do argument validation based on input file format Assisted-by: Codex
1 parent d74d92f commit 65533c1

4 files changed

Lines changed: 422 additions & 0 deletions

File tree

‎src/pdfrest/client.py‎

Lines changed: 196 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -76,6 +76,8 @@
7676
BasePdfRestGraphicPayload,
7777
BmpPdfRestPayload,
7878
ConvertToMarkdownPayload,
79+
ConvertToPdfPayload,
80+
ConvertUrlsToPdfPayload,
7981
DeletePayload,
8082
ExtractImagesPayload,
8183
ExtractTextPayload,
@@ -125,10 +127,16 @@
125127
FlattenQuality,
126128
GifColorModel,
127129
GraphicSmoothing,
130+
HtmlPageOrientation,
131+
HtmlPageSize,
132+
HtmlWebLayout,
128133
JpegColorModel,
129134
OcrLanguage,
130135
PdfAddTextObject,
131136
PdfAType,
137+
PdfConversionCompression,
138+
PdfConversionDownsample,
139+
PdfConversionLocale,
132140
PdfInfoQuery,
133141
PdfMergeInput,
134142
PdfPageOrientation,
@@ -3292,6 +3300,100 @@ def rasterize_pdf(
32923300
timeout=timeout,
32933301
)
32943302

3303+
def convert_to_pdf(
3304+
self,
3305+
file: PdfRestFile | Sequence[PdfRestFile],
3306+
*,
3307+
output: str | None = None,
3308+
compression: PdfConversionCompression | None = None,
3309+
downsample: PdfConversionDownsample | None = None,
3310+
tagged_pdf: bool | None = None,
3311+
locale: PdfConversionLocale | None = None,
3312+
page_size: HtmlPageSize | None = None,
3313+
page_margin: str | None = None,
3314+
page_orientation: HtmlPageOrientation | None = None,
3315+
web_layout: HtmlWebLayout | None = None,
3316+
extra_query: Query | None = None,
3317+
extra_headers: AnyMapping | None = None,
3318+
extra_body: Body | None = None,
3319+
timeout: TimeoutTypes | None = None,
3320+
) -> PdfRestFileBasedResponse:
3321+
"""Convert a supported file type to PDF."""
3322+
3323+
payload: dict[str, Any] = {"files": file}
3324+
if output is not None:
3325+
payload["output"] = output
3326+
if compression is not None:
3327+
payload["compression"] = compression
3328+
if downsample is not None:
3329+
payload["downsample"] = downsample
3330+
if tagged_pdf is not None:
3331+
payload["tagged_pdf"] = tagged_pdf
3332+
if locale is not None:
3333+
payload["locale"] = locale
3334+
if page_size is not None:
3335+
payload["page_size"] = page_size
3336+
if page_margin is not None:
3337+
payload["page_margin"] = page_margin
3338+
if page_orientation is not None:
3339+
payload["page_orientation"] = page_orientation
3340+
if web_layout is not None:
3341+
payload["web_layout"] = web_layout
3342+
3343+
return self._post_file_operation(
3344+
endpoint="/pdf",
3345+
payload=payload,
3346+
payload_model=ConvertToPdfPayload,
3347+
extra_query=extra_query,
3348+
extra_headers=extra_headers,
3349+
extra_body=extra_body,
3350+
timeout=timeout,
3351+
)
3352+
3353+
def convert_urls_to_pdf(
3354+
self,
3355+
urls: UrlInput,
3356+
*,
3357+
output: str | None = None,
3358+
compression: PdfConversionCompression | None = None,
3359+
downsample: PdfConversionDownsample | None = None,
3360+
page_size: HtmlPageSize | None = None,
3361+
page_margin: str | None = None,
3362+
page_orientation: HtmlPageOrientation | None = None,
3363+
web_layout: HtmlWebLayout | None = None,
3364+
extra_query: Query | None = None,
3365+
extra_headers: AnyMapping | None = None,
3366+
extra_body: Body | None = None,
3367+
timeout: TimeoutTypes | None = None,
3368+
) -> PdfRestFileBasedResponse:
3369+
"""Convert HTML content from one or more URLs to PDF."""
3370+
3371+
payload: dict[str, Any] = {"url": urls}
3372+
if output is not None:
3373+
payload["output"] = output
3374+
if compression is not None:
3375+
payload["compression"] = compression
3376+
if downsample is not None:
3377+
payload["downsample"] = downsample
3378+
if page_size is not None:
3379+
payload["page_size"] = page_size
3380+
if page_margin is not None:
3381+
payload["page_margin"] = page_margin
3382+
if page_orientation is not None:
3383+
payload["page_orientation"] = page_orientation
3384+
if web_layout is not None:
3385+
payload["web_layout"] = web_layout
3386+
3387+
return self._post_file_operation(
3388+
endpoint="/pdf",
3389+
payload=payload,
3390+
payload_model=ConvertUrlsToPdfPayload,
3391+
extra_query=extra_query,
3392+
extra_headers=extra_headers,
3393+
extra_body=extra_body,
3394+
timeout=timeout,
3395+
)
3396+
32953397
def convert_to_pdfa(
32963398
self,
32973399
file: PdfRestFile | Sequence[PdfRestFile],
@@ -4783,6 +4885,100 @@ async def rasterize_pdf(
47834885
timeout=timeout,
47844886
)
47854887

4888+
async def convert_to_pdf(
4889+
self,
4890+
file: PdfRestFile | Sequence[PdfRestFile],
4891+
*,
4892+
output: str | None = None,
4893+
compression: PdfConversionCompression | None = None,
4894+
downsample: PdfConversionDownsample | None = None,
4895+
tagged_pdf: bool | None = None,
4896+
locale: PdfConversionLocale | None = None,
4897+
page_size: HtmlPageSize | None = None,
4898+
page_margin: str | None = None,
4899+
page_orientation: HtmlPageOrientation | None = None,
4900+
web_layout: HtmlWebLayout | None = None,
4901+
extra_query: Query | None = None,
4902+
extra_headers: AnyMapping | None = None,
4903+
extra_body: Body | None = None,
4904+
timeout: TimeoutTypes | None = None,
4905+
) -> PdfRestFileBasedResponse:
4906+
"""Asynchronously convert a supported file type to PDF."""
4907+
4908+
payload: dict[str, Any] = {"files": file}
4909+
if output is not None:
4910+
payload["output"] = output
4911+
if compression is not None:
4912+
payload["compression"] = compression
4913+
if downsample is not None:
4914+
payload["downsample"] = downsample
4915+
if tagged_pdf is not None:
4916+
payload["tagged_pdf"] = tagged_pdf
4917+
if locale is not None:
4918+
payload["locale"] = locale
4919+
if page_size is not None:
4920+
payload["page_size"] = page_size
4921+
if page_margin is not None:
4922+
payload["page_margin"] = page_margin
4923+
if page_orientation is not None:
4924+
payload["page_orientation"] = page_orientation
4925+
if web_layout is not None:
4926+
payload["web_layout"] = web_layout
4927+
4928+
return await self._post_file_operation(
4929+
endpoint="/pdf",
4930+
payload=payload,
4931+
payload_model=ConvertToPdfPayload,
4932+
extra_query=extra_query,
4933+
extra_headers=extra_headers,
4934+
extra_body=extra_body,
4935+
timeout=timeout,
4936+
)
4937+
4938+
async def convert_urls_to_pdf(
4939+
self,
4940+
urls: UrlInput,
4941+
*,
4942+
output: str | None = None,
4943+
compression: PdfConversionCompression | None = None,
4944+
downsample: PdfConversionDownsample | None = None,
4945+
page_size: HtmlPageSize | None = None,
4946+
page_margin: str | None = None,
4947+
page_orientation: HtmlPageOrientation | None = None,
4948+
web_layout: HtmlWebLayout | None = None,
4949+
extra_query: Query | None = None,
4950+
extra_headers: AnyMapping | None = None,
4951+
extra_body: Body | None = None,
4952+
timeout: TimeoutTypes | None = None,
4953+
) -> PdfRestFileBasedResponse:
4954+
"""Asynchronously convert HTML content from one or more URLs to PDF."""
4955+
4956+
payload: dict[str, Any] = {"url": urls}
4957+
if output is not None:
4958+
payload["output"] = output
4959+
if compression is not None:
4960+
payload["compression"] = compression
4961+
if downsample is not None:
4962+
payload["downsample"] = downsample
4963+
if page_size is not None:
4964+
payload["page_size"] = page_size
4965+
if page_margin is not None:
4966+
payload["page_margin"] = page_margin
4967+
if page_orientation is not None:
4968+
payload["page_orientation"] = page_orientation
4969+
if web_layout is not None:
4970+
payload["web_layout"] = web_layout
4971+
4972+
return await self._post_file_operation(
4973+
endpoint="/pdf",
4974+
payload=payload,
4975+
payload_model=ConvertUrlsToPdfPayload,
4976+
extra_query=extra_query,
4977+
extra_headers=extra_headers,
4978+
extra_body=extra_body,
4979+
timeout=timeout,
4980+
)
4981+
47864982
async def convert_to_pdfa(
47874983
self,
47884984
file: PdfRestFile | Sequence[PdfRestFile],

0 commit comments

Comments
 (0)