Skip to content

support plain text on enum validated params #10

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 5 commits into from
Oct 4, 2024
Merged
Show file tree
Hide file tree
Changes from 4 commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion __tests__/result.test.ts
Original file line number Diff line number Diff line change
Expand Up @@ -14,7 +14,7 @@ Deno.test('cheerio selector lazy loads and caches itself', async () => {


Deno.test('cheerio selector loads with case sensitive headers', async () => {
const response = JSON.parse(await Deno.readTextFile('__tests__/data/response_html_case_sensitive_headers.json'));
const response = JSON.parse(await Deno.readTextFile('__tests__/data/response_html_success.json'));
const result = new ScrapeResult(response);
assertEquals(result.selector('h1').text(), 'Herman Melville - Moby-Dick');
});
Expand Down
2 changes: 1 addition & 1 deletion deno.json
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@
},
"name": "@scrapfly/scrapfly-sdk",
"exports": "./src/main.ts",
"version": "0.6.6",
"version": "0.6.7",
"description": "SDK for Scrapfly.io API for web scraping, screenshotting and data extraction",
"tasks": {
"start": "deno run --allow-net --allow-read src/main.ts",
Expand Down
7 changes: 5 additions & 2 deletions src/extractionconfig.ts
Original file line number Diff line number Diff line change
Expand Up @@ -26,7 +26,7 @@ type ExtractionConfigOptions = {
extraction_prompt?: string;
extraction_model?: string;
is_document_compressed?: boolean;
document_compression_format?: CompressionFormat;
document_compression_format?: 'gzip' | 'zstd' | 'deflate' | CompressionFormat;
webhook?: string;
};

Expand All @@ -40,11 +40,14 @@ export class ExtractionConfig {
extraction_prompt?: string;
extraction_model?: string;
is_document_compressed?: boolean;
document_compression_format?: CompressionFormat;
document_compression_format?: 'gzip' | 'zstd' | 'deflate' | CompressionFormat;
webhook?: string;

constructor(options: ExtractionConfigOptions) {
this.validateOptions(options);
if (options.document_compression_format && !Object.values(CompressionFormat).includes(options.document_compression_format as CompressionFormat)) {
throw new errors.ExtractionConfigError(`Invalid CompressionFormat param value: ${options.document_compression_format}`);
}
this.body = options.body;
this.content_type = options.content_type;
this.url = options.url ?? this.url;
Expand Down
28 changes: 18 additions & 10 deletions src/scrapeconfig.ts
Original file line number Diff line number Diff line change
Expand Up @@ -38,6 +38,7 @@ export enum Format {
export enum FormatOption {
NO_LINKS = 'no_links',
NO_IMAGES = 'no_images',
ONLY_CONTENT = 'only_content'
}

type ScrapeConfigOptions = {
Expand All @@ -58,8 +59,8 @@ type ScrapeConfigOptions = {
proxy_pool?: string;
session?: string;
tags?: string[];
format?: Format;
format_options?: FormatOption[];
format?: 'json' | 'text' | 'markdown' | 'clean_html' | 'raw' | Format;
format_options?: ('no_links' | 'no_images' | 'only_content')[] | FormatOption[];
correlation_id?: string;
cookies?: Rec<string>;
body?: string;
Expand All @@ -69,7 +70,7 @@ type ScrapeConfigOptions = {
rendering_wait?: number;
wait_for_selector?: string;
screenshots?: Rec<any>;
screenshot_flags?: ScreenshotFlags[];
screenshot_flags?: ('load_images' | 'dark_mode' | 'block_banners' | 'print_media_format' | 'high_quality')[] | ScreenshotFlags[];
session_sticky_proxy?: boolean;
webhook?: string;
timeout?: number;
Expand Down Expand Up @@ -100,8 +101,8 @@ export class ScrapeConfig {
proxy_pool?: string;
session?: string;
tags: Set<string> = new Set<string>();
format?: Format; // raw(unchanged)
format_options?: FormatOption[];
format?: 'json' | 'text' | 'markdown' | 'clean_html' | 'raw' | Format;
format_options?: ('no_links' | 'no_images' | 'only_content')[] | FormatOption[];
correlation_id?: string;
cookies?: Rec<string>;
body?: string;
Expand All @@ -112,7 +113,7 @@ export class ScrapeConfig {
wait_for_selector?: string;
session_sticky_proxy = false;
screenshots?: Rec<any>;
screenshot_flags?: ScreenshotFlags[];
screenshot_flags?: ('load_images' | 'dark_mode' | 'block_banners' | 'print_media_format' | 'high_quality')[] | ScreenshotFlags[];
webhook?: string;
timeout?: number; // in milliseconds
js_scenario?: Rec<any>;
Expand All @@ -122,14 +123,21 @@ export class ScrapeConfig {

constructor(options: ScrapeConfigOptions) {
this.validateOptions(options);
if (options.format && !Object.values(Format).includes(options.format)) {
throw new ScrapeConfigError(`Invalid format param value: ${options.format}`);
if (options.format && !Object.values(Format).includes(options.format as Format)) {
throw new ScrapeConfigError(`Invalid Format param value: ${options.format}`);
}
this.format = options.format ?? this.format;
if (options.format_options) {
options.format_options.forEach((flag) => {
if (!Object.values(FormatOption).includes(flag as FormatOption)) {
throw new ScrapeConfigError(`Invalid FormatOption param value: ${flag}`);
}
});
}
if (options.screenshot_flags) {
options.screenshot_flags.forEach((flag) => {
if (!Object.values(ScreenshotFlags).includes(flag)) {
throw new ScrapeConfigError(`Invalid screenshot_flags param value: ${flag}`);
if (!Object.values(ScreenshotFlags).includes(flag as ScreenshotFlags)) {
throw new ScrapeConfigError(`Invalid ScreenshotFlags param value: ${flag}`);
}
});
}
Expand Down
19 changes: 9 additions & 10 deletions src/screenshotconfig.ts
Original file line number Diff line number Diff line change
Expand Up @@ -34,14 +34,14 @@ export enum Format {

type ScreenshotConfigOptions = {
url: string;
format?: Format;
format?: 'jpg'| 'png' | 'webp'| 'gif' | Format;
capture?: string;
resolution?: string;
country?: string;
timeout?: number;
rendering_wait?: number;
wait_for_selector?: string;
options?: Options[];
options?: ('load_images' | 'dark_mode' | 'block_banners' | 'print_media_format')[] | Options[];
auto_scroll?: boolean;
js?: string;
cache?: boolean;
Expand All @@ -52,14 +52,14 @@ type ScreenshotConfigOptions = {

export class ScreenshotConfig {
url: string;
format?: Format;
format?: 'jpg'| 'png' | 'webp'| 'gif' | Format;
capture?: string;
resolution?: string;
country?: string = undefined;
timeout?: number;
rendering_wait?: number;
wait_for_selector?: string;
options?: Options[];
options?: ('load_images' | 'dark_mode' | 'block_banners' | 'print_media_format')[] | Options[];
auto_scroll?: boolean;
js?: string;
cache?: boolean;
Expand All @@ -69,18 +69,17 @@ export class ScreenshotConfig {

constructor(options: ScreenshotConfigOptions) {
this.validateOptions(options);
if (options.format && !Object.values(Format).includes(options.format)) {
throw new ScreenshotConfigError(`Invalid format param value: ${options.format}`);
if (options.format && !Object.values(Format).includes(options.format as Format)) {
throw new ScreenshotConfigError(`Invalid Format param value: ${options.format}`);
}
this.format = options.format ?? this.format;
// Validate options against the enum
if (options.options) {
options.options.forEach((opt) => {
if (!Object.values(Options).includes(opt)) {
throw new ScreenshotConfigError(`Invalid options param value: ${opt}`);
if (!Object.values(Options).includes(opt as Options)) {
throw new ScreenshotConfigError(`Invalid Options param value: ${opt}`);
}
});
}
}
this.url = options.url;
this.format = options.format ?? this.format;
this.capture = options.capture ?? this.capture;
Expand Down
Loading