Skip to content

Commit 9ef1566

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 3d1c459 commit 9ef1566

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,
@@ -118,9 +120,15 @@
118120
FlattenQuality,
119121
GifColorModel,
120122
GraphicSmoothing,
123+
HtmlPageOrientation,
124+
HtmlPageSize,
125+
HtmlWebLayout,
121126
JpegColorModel,
122127
OcrLanguage,
123128
PdfAType,
129+
PdfConversionCompression,
130+
PdfConversionDownsample,
131+
PdfConversionLocale,
124132
PdfInfoQuery,
125133
PdfMergeInput,
126134
PdfPageSelection,
@@ -3078,6 +3086,100 @@ def rasterize_pdf(
30783086
timeout=timeout,
30793087
)
30803088

3089+
def convert_to_pdf(
3090+
self,
3091+
file: PdfRestFile | Sequence[PdfRestFile],
3092+
*,
3093+
output: str | None = None,
3094+
compression: PdfConversionCompression | None = None,
3095+
downsample: PdfConversionDownsample | None = None,
3096+
tagged_pdf: bool | None = None,
3097+
locale: PdfConversionLocale | None = None,
3098+
page_size: HtmlPageSize | None = None,
3099+
page_margin: str | None = None,
3100+
page_orientation: HtmlPageOrientation | None = None,
3101+
web_layout: HtmlWebLayout | None = None,
3102+
extra_query: Query | None = None,
3103+
extra_headers: AnyMapping | None = None,
3104+
extra_body: Body | None = None,
3105+
timeout: TimeoutTypes | None = None,
3106+
) -> PdfRestFileBasedResponse:
3107+
"""Convert a supported file type to PDF."""
3108+
3109+
payload: dict[str, Any] = {"files": file}
3110+
if output is not None:
3111+
payload["output"] = output
3112+
if compression is not None:
3113+
payload["compression"] = compression
3114+
if downsample is not None:
3115+
payload["downsample"] = downsample
3116+
if tagged_pdf is not None:
3117+
payload["tagged_pdf"] = tagged_pdf
3118+
if locale is not None:
3119+
payload["locale"] = locale
3120+
if page_size is not None:
3121+
payload["page_size"] = page_size
3122+
if page_margin is not None:
3123+
payload["page_margin"] = page_margin
3124+
if page_orientation is not None:
3125+
payload["page_orientation"] = page_orientation
3126+
if web_layout is not None:
3127+
payload["web_layout"] = web_layout
3128+
3129+
return self._post_file_operation(
3130+
endpoint="/pdf",
3131+
payload=payload,
3132+
payload_model=ConvertToPdfPayload,
3133+
extra_query=extra_query,
3134+
extra_headers=extra_headers,
3135+
extra_body=extra_body,
3136+
timeout=timeout,
3137+
)
3138+
3139+
def convert_urls_to_pdf(
3140+
self,
3141+
urls: UrlInput,
3142+
*,
3143+
output: str | None = None,
3144+
compression: PdfConversionCompression | None = None,
3145+
downsample: PdfConversionDownsample | None = None,
3146+
page_size: HtmlPageSize | None = None,
3147+
page_margin: str | None = None,
3148+
page_orientation: HtmlPageOrientation | None = None,
3149+
web_layout: HtmlWebLayout | None = None,
3150+
extra_query: Query | None = None,
3151+
extra_headers: AnyMapping | None = None,
3152+
extra_body: Body | None = None,
3153+
timeout: TimeoutTypes | None = None,
3154+
) -> PdfRestFileBasedResponse:
3155+
"""Convert HTML content from one or more URLs to PDF."""
3156+
3157+
payload: dict[str, Any] = {"url": urls}
3158+
if output is not None:
3159+
payload["output"] = output
3160+
if compression is not None:
3161+
payload["compression"] = compression
3162+
if downsample is not None:
3163+
payload["downsample"] = downsample
3164+
if page_size is not None:
3165+
payload["page_size"] = page_size
3166+
if page_margin is not None:
3167+
payload["page_margin"] = page_margin
3168+
if page_orientation is not None:
3169+
payload["page_orientation"] = page_orientation
3170+
if web_layout is not None:
3171+
payload["web_layout"] = web_layout
3172+
3173+
return self._post_file_operation(
3174+
endpoint="/pdf",
3175+
payload=payload,
3176+
payload_model=ConvertUrlsToPdfPayload,
3177+
extra_query=extra_query,
3178+
extra_headers=extra_headers,
3179+
extra_body=extra_body,
3180+
timeout=timeout,
3181+
)
3182+
30813183
def convert_to_pdfa(
30823184
self,
30833185
file: PdfRestFile | Sequence[PdfRestFile],
@@ -4365,6 +4467,100 @@ async def rasterize_pdf(
43654467
timeout=timeout,
43664468
)
43674469

4470+
async def convert_to_pdf(
4471+
self,
4472+
file: PdfRestFile | Sequence[PdfRestFile],
4473+
*,
4474+
output: str | None = None,
4475+
compression: PdfConversionCompression | None = None,
4476+
downsample: PdfConversionDownsample | None = None,
4477+
tagged_pdf: bool | None = None,
4478+
locale: PdfConversionLocale | None = None,
4479+
page_size: HtmlPageSize | None = None,
4480+
page_margin: str | None = None,
4481+
page_orientation: HtmlPageOrientation | None = None,
4482+
web_layout: HtmlWebLayout | None = None,
4483+
extra_query: Query | None = None,
4484+
extra_headers: AnyMapping | None = None,
4485+
extra_body: Body | None = None,
4486+
timeout: TimeoutTypes | None = None,
4487+
) -> PdfRestFileBasedResponse:
4488+
"""Asynchronously convert a supported file type to PDF."""
4489+
4490+
payload: dict[str, Any] = {"files": file}
4491+
if output is not None:
4492+
payload["output"] = output
4493+
if compression is not None:
4494+
payload["compression"] = compression
4495+
if downsample is not None:
4496+
payload["downsample"] = downsample
4497+
if tagged_pdf is not None:
4498+
payload["tagged_pdf"] = tagged_pdf
4499+
if locale is not None:
4500+
payload["locale"] = locale
4501+
if page_size is not None:
4502+
payload["page_size"] = page_size
4503+
if page_margin is not None:
4504+
payload["page_margin"] = page_margin
4505+
if page_orientation is not None:
4506+
payload["page_orientation"] = page_orientation
4507+
if web_layout is not None:
4508+
payload["web_layout"] = web_layout
4509+
4510+
return await self._post_file_operation(
4511+
endpoint="/pdf",
4512+
payload=payload,
4513+
payload_model=ConvertToPdfPayload,
4514+
extra_query=extra_query,
4515+
extra_headers=extra_headers,
4516+
extra_body=extra_body,
4517+
timeout=timeout,
4518+
)
4519+
4520+
async def convert_urls_to_pdf(
4521+
self,
4522+
urls: UrlInput,
4523+
*,
4524+
output: str | None = None,
4525+
compression: PdfConversionCompression | None = None,
4526+
downsample: PdfConversionDownsample | None = None,
4527+
page_size: HtmlPageSize | None = None,
4528+
page_margin: str | None = None,
4529+
page_orientation: HtmlPageOrientation | None = None,
4530+
web_layout: HtmlWebLayout | None = None,
4531+
extra_query: Query | None = None,
4532+
extra_headers: AnyMapping | None = None,
4533+
extra_body: Body | None = None,
4534+
timeout: TimeoutTypes | None = None,
4535+
) -> PdfRestFileBasedResponse:
4536+
"""Asynchronously convert HTML content from one or more URLs to PDF."""
4537+
4538+
payload: dict[str, Any] = {"url": urls}
4539+
if output is not None:
4540+
payload["output"] = output
4541+
if compression is not None:
4542+
payload["compression"] = compression
4543+
if downsample is not None:
4544+
payload["downsample"] = downsample
4545+
if page_size is not None:
4546+
payload["page_size"] = page_size
4547+
if page_margin is not None:
4548+
payload["page_margin"] = page_margin
4549+
if page_orientation is not None:
4550+
payload["page_orientation"] = page_orientation
4551+
if web_layout is not None:
4552+
payload["web_layout"] = web_layout
4553+
4554+
return await self._post_file_operation(
4555+
endpoint="/pdf",
4556+
payload=payload,
4557+
payload_model=ConvertUrlsToPdfPayload,
4558+
extra_query=extra_query,
4559+
extra_headers=extra_headers,
4560+
extra_body=extra_body,
4561+
timeout=timeout,
4562+
)
4563+
43684564
async def convert_to_pdfa(
43694565
self,
43704566
file: PdfRestFile | Sequence[PdfRestFile],

0 commit comments

Comments
 (0)