Skip to content

Commit a60e2db

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 ce5e2de commit a60e2db

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
@@ -75,6 +75,8 @@
7575
BasePdfRestGraphicPayload,
7676
BmpPdfRestPayload,
7777
ConvertToMarkdownPayload,
78+
ConvertToPdfPayload,
79+
ConvertUrlsToPdfPayload,
7880
DeletePayload,
7981
ExtractImagesPayload,
8082
ExtractTextPayload,
@@ -113,9 +115,15 @@
113115
FlattenQuality,
114116
GifColorModel,
115117
GraphicSmoothing,
118+
HtmlPageOrientation,
119+
HtmlPageSize,
120+
HtmlWebLayout,
116121
JpegColorModel,
117122
OcrLanguage,
118123
PdfAType,
124+
PdfConversionCompression,
125+
PdfConversionDownsample,
126+
PdfConversionLocale,
119127
PdfInfoQuery,
120128
PdfMergeInput,
121129
PdfPageSelection,
@@ -2822,6 +2830,100 @@ def rasterize_pdf(
28222830
timeout=timeout,
28232831
)
28242832

2833+
def convert_to_pdf(
2834+
self,
2835+
file: PdfRestFile | Sequence[PdfRestFile],
2836+
*,
2837+
output: str | None = None,
2838+
compression: PdfConversionCompression | None = None,
2839+
downsample: PdfConversionDownsample | None = None,
2840+
tagged_pdf: bool | None = None,
2841+
locale: PdfConversionLocale | None = None,
2842+
page_size: HtmlPageSize | None = None,
2843+
page_margin: str | None = None,
2844+
page_orientation: HtmlPageOrientation | None = None,
2845+
web_layout: HtmlWebLayout | None = None,
2846+
extra_query: Query | None = None,
2847+
extra_headers: AnyMapping | None = None,
2848+
extra_body: Body | None = None,
2849+
timeout: TimeoutTypes | None = None,
2850+
) -> PdfRestFileBasedResponse:
2851+
"""Convert a supported file type to PDF."""
2852+
2853+
payload: dict[str, Any] = {"files": file}
2854+
if output is not None:
2855+
payload["output"] = output
2856+
if compression is not None:
2857+
payload["compression"] = compression
2858+
if downsample is not None:
2859+
payload["downsample"] = downsample
2860+
if tagged_pdf is not None:
2861+
payload["tagged_pdf"] = tagged_pdf
2862+
if locale is not None:
2863+
payload["locale"] = locale
2864+
if page_size is not None:
2865+
payload["page_size"] = page_size
2866+
if page_margin is not None:
2867+
payload["page_margin"] = page_margin
2868+
if page_orientation is not None:
2869+
payload["page_orientation"] = page_orientation
2870+
if web_layout is not None:
2871+
payload["web_layout"] = web_layout
2872+
2873+
return self._post_file_operation(
2874+
endpoint="/pdf",
2875+
payload=payload,
2876+
payload_model=ConvertToPdfPayload,
2877+
extra_query=extra_query,
2878+
extra_headers=extra_headers,
2879+
extra_body=extra_body,
2880+
timeout=timeout,
2881+
)
2882+
2883+
def convert_urls_to_pdf(
2884+
self,
2885+
urls: UrlInput,
2886+
*,
2887+
output: str | None = None,
2888+
compression: PdfConversionCompression | None = None,
2889+
downsample: PdfConversionDownsample | None = None,
2890+
page_size: HtmlPageSize | None = None,
2891+
page_margin: str | None = None,
2892+
page_orientation: HtmlPageOrientation | None = None,
2893+
web_layout: HtmlWebLayout | None = None,
2894+
extra_query: Query | None = None,
2895+
extra_headers: AnyMapping | None = None,
2896+
extra_body: Body | None = None,
2897+
timeout: TimeoutTypes | None = None,
2898+
) -> PdfRestFileBasedResponse:
2899+
"""Convert HTML content from one or more URLs to PDF."""
2900+
2901+
payload: dict[str, Any] = {"url": urls}
2902+
if output is not None:
2903+
payload["output"] = output
2904+
if compression is not None:
2905+
payload["compression"] = compression
2906+
if downsample is not None:
2907+
payload["downsample"] = downsample
2908+
if page_size is not None:
2909+
payload["page_size"] = page_size
2910+
if page_margin is not None:
2911+
payload["page_margin"] = page_margin
2912+
if page_orientation is not None:
2913+
payload["page_orientation"] = page_orientation
2914+
if web_layout is not None:
2915+
payload["web_layout"] = web_layout
2916+
2917+
return self._post_file_operation(
2918+
endpoint="/pdf",
2919+
payload=payload,
2920+
payload_model=ConvertUrlsToPdfPayload,
2921+
extra_query=extra_query,
2922+
extra_headers=extra_headers,
2923+
extra_body=extra_body,
2924+
timeout=timeout,
2925+
)
2926+
28252927
def convert_to_pdfa(
28262928
self,
28272929
file: PdfRestFile | Sequence[PdfRestFile],
@@ -3864,6 +3966,100 @@ async def rasterize_pdf(
38643966
timeout=timeout,
38653967
)
38663968

3969+
async def convert_to_pdf(
3970+
self,
3971+
file: PdfRestFile | Sequence[PdfRestFile],
3972+
*,
3973+
output: str | None = None,
3974+
compression: PdfConversionCompression | None = None,
3975+
downsample: PdfConversionDownsample | None = None,
3976+
tagged_pdf: bool | None = None,
3977+
locale: PdfConversionLocale | None = None,
3978+
page_size: HtmlPageSize | None = None,
3979+
page_margin: str | None = None,
3980+
page_orientation: HtmlPageOrientation | None = None,
3981+
web_layout: HtmlWebLayout | None = None,
3982+
extra_query: Query | None = None,
3983+
extra_headers: AnyMapping | None = None,
3984+
extra_body: Body | None = None,
3985+
timeout: TimeoutTypes | None = None,
3986+
) -> PdfRestFileBasedResponse:
3987+
"""Asynchronously convert a supported file type to PDF."""
3988+
3989+
payload: dict[str, Any] = {"files": file}
3990+
if output is not None:
3991+
payload["output"] = output
3992+
if compression is not None:
3993+
payload["compression"] = compression
3994+
if downsample is not None:
3995+
payload["downsample"] = downsample
3996+
if tagged_pdf is not None:
3997+
payload["tagged_pdf"] = tagged_pdf
3998+
if locale is not None:
3999+
payload["locale"] = locale
4000+
if page_size is not None:
4001+
payload["page_size"] = page_size
4002+
if page_margin is not None:
4003+
payload["page_margin"] = page_margin
4004+
if page_orientation is not None:
4005+
payload["page_orientation"] = page_orientation
4006+
if web_layout is not None:
4007+
payload["web_layout"] = web_layout
4008+
4009+
return await self._post_file_operation(
4010+
endpoint="/pdf",
4011+
payload=payload,
4012+
payload_model=ConvertToPdfPayload,
4013+
extra_query=extra_query,
4014+
extra_headers=extra_headers,
4015+
extra_body=extra_body,
4016+
timeout=timeout,
4017+
)
4018+
4019+
async def convert_urls_to_pdf(
4020+
self,
4021+
urls: UrlInput,
4022+
*,
4023+
output: str | None = None,
4024+
compression: PdfConversionCompression | None = None,
4025+
downsample: PdfConversionDownsample | None = None,
4026+
page_size: HtmlPageSize | None = None,
4027+
page_margin: str | None = None,
4028+
page_orientation: HtmlPageOrientation | None = None,
4029+
web_layout: HtmlWebLayout | None = None,
4030+
extra_query: Query | None = None,
4031+
extra_headers: AnyMapping | None = None,
4032+
extra_body: Body | None = None,
4033+
timeout: TimeoutTypes | None = None,
4034+
) -> PdfRestFileBasedResponse:
4035+
"""Asynchronously convert HTML content from one or more URLs to PDF."""
4036+
4037+
payload: dict[str, Any] = {"url": urls}
4038+
if output is not None:
4039+
payload["output"] = output
4040+
if compression is not None:
4041+
payload["compression"] = compression
4042+
if downsample is not None:
4043+
payload["downsample"] = downsample
4044+
if page_size is not None:
4045+
payload["page_size"] = page_size
4046+
if page_margin is not None:
4047+
payload["page_margin"] = page_margin
4048+
if page_orientation is not None:
4049+
payload["page_orientation"] = page_orientation
4050+
if web_layout is not None:
4051+
payload["web_layout"] = web_layout
4052+
4053+
return await self._post_file_operation(
4054+
endpoint="/pdf",
4055+
payload=payload,
4056+
payload_model=ConvertUrlsToPdfPayload,
4057+
extra_query=extra_query,
4058+
extra_headers=extra_headers,
4059+
extra_body=extra_body,
4060+
timeout=timeout,
4061+
)
4062+
38674063
async def convert_to_pdfa(
38684064
self,
38694065
file: PdfRestFile | Sequence[PdfRestFile],

0 commit comments

Comments
 (0)