Skip to content

⚡ Bolt: Optimize JSON-LD parsing for movie scraper #82

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.

Sign up for GitHub

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

Closed
bartholomej wants to merge 1 commit into from
Closed

⚡ Bolt: Optimize JSON-LD parsing for movie scraper #82

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
26 changes: 14 additions & 12 deletions src/helpers/movie.helper.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -123,23 +123,23 @@ export const getMovieRatingCount = (el: HTMLElement): number => {
}
};

export const getMovieYear = (el: string): number => {
try {
const jsonLd = JSON.parse(el);
export const getMovieYear = (jsonLd: any): number => {
if (jsonLd && jsonLd.dateCreated) {
return +jsonLd.dateCreated;
} catch (error) {
console.error('node-csfd-api: Error parsing JSON-LD', error);
return null;
}
return null;
};

export const getMovieDuration = (jsonLdRaw: string, el: HTMLElement): number => {
let duration = null;
export const getMovieDuration = (jsonLd: any, el: HTMLElement): number => {
try {
const jsonLd = JSON.parse(jsonLdRaw);
duration = jsonLd.duration;
return parseISO8601Duration(duration);
if (jsonLd && jsonLd.duration) {
return parseISO8601Duration(jsonLd.duration);
}
} catch (error) {
// ignore
}

try {
const origin = el.querySelector('.origin').innerText;
const timeString = origin.split(',');
if (timeString.length > 2) {
Expand All @@ -151,11 +151,13 @@ export const getMovieDuration = (jsonLdRaw: string, el: HTMLElement): number =>
const hoursMinsRaw = timeRaw.split('min')[0];
const hoursMins = hoursMinsRaw.split('h');
// Resolve hours + minutes format
duration = hoursMins.length > 1 ? +hoursMins[0] * 60 + +hoursMins[1] : +hoursMins[0];
const duration = hoursMins.length > 1 ? +hoursMins[0] * 60 + +hoursMins[1] : +hoursMins[0];
return duration;
} else {
return null;
}
} catch (e) {
return null;
}
};

Expand Down
10 changes: 8 additions & 2 deletions src/services/movie.service.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,7 +41,13 @@ export class MovieScraper {
const pageClasses = movieHtml.querySelector('.page-content').classNames.split(' ');
const asideNode = movieHtml.querySelector('.aside-movie-profile');
const movieNode = movieHtml.querySelector('.main-movie-profile');
const jsonLd = movieHtml.querySelector('script[type="application/ld+json"]').innerText;
const jsonLdString = movieHtml.querySelector('script[type="application/ld+json"]').innerText;
let jsonLd = null;
try {
jsonLd = JSON.parse(jsonLdString);
} catch (e) {
console.error('node-csfd-api: Error parsing JSON-LD', e);
}
return this.buildMovie(+movieId, movieNode, asideNode, pageClasses, jsonLd, options);
}

Expand All @@ -50,7 +56,7 @@ export class MovieScraper {
el: HTMLElement,
asideEl: HTMLElement,
pageClasses: string[],
jsonLd: string,
jsonLd: any,
options: CSFDOptions
): CSFDMovie {
return {
Expand Down
11 changes: 8 additions & 3 deletions tests/movie.test.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -48,13 +48,18 @@ const getNode = (node: HTMLElement): HTMLElement => {
return node.querySelector('.main-movie-profile') as HTMLElement;
};

const getJsonLd = (node: HTMLElement): string => {
return node.querySelector('script[type="application/ld+json"]')?.innerText ?? '{}';
const getJsonLd = (node: HTMLElement): any => {
const json = node.querySelector('script[type="application/ld+json"]')?.innerText || '{}';
try {
return JSON.parse(json);
} catch (e) {
return null;
}
};

const getMovie = (
node: HTMLElement
): { pClasses: string[]; aside: HTMLElement; pNode: HTMLElement; jsonLd: string } => {
): { pClasses: string[]; aside: HTMLElement; pNode: HTMLElement; jsonLd: any } => {
return {
pClasses: getPageClasses(node),
aside: getAsideNode(node),
Expand Down