Merge branch 'fix-undefined-actor-error' into fix/search-all-api-and-login-init

This commit is contained in:
YuBai 2026-03-04 18:25:45 +08:00
commit 4e8d3f1318
7 changed files with 132 additions and 42 deletions

@ -33,24 +33,24 @@ export default class DoubanTheaterAiLoadHandler extends DoubanAbstractLoadHandle
"director", "director",
DataValueType.array, DataValueType.array,
extract.director, extract.director,
extract.director.map(SchemaOrg.getPersonName).filter(c => c) (extract.director || []).map(SchemaOrg.getPersonName).filter(c => c)
)); ));
variableMap.set("actor", new DataField( variableMap.set("actor", new DataField(
"actor", "actor",
DataValueType.array, DataValueType.array,
extract.actor, extract.actor,
extract.actor.map(SchemaOrg.getPersonName).filter(c => c) (extract.actor || []).map(SchemaOrg.getPersonName).filter(c => c)
)); ));
variableMap.set("author", new DataField( variableMap.set("author", new DataField(
"author", "author",
DataValueType.array, DataValueType.array,
extract.author, extract.author,
extract.author.map(SchemaOrg.getPersonName).map(name => super.getPersonName(name, context)).filter(c => c) (extract.author || []).map(SchemaOrg.getPersonName).map(name => super.getPersonName(name, context)).filter(c => c)
)); ));
variableMap.set("aliases", new DataField("aliases", DataValueType.array, extract.aliases, variableMap.set("aliases", new DataField("aliases", DataValueType.array, extract.aliases,
extract.aliases.map(a=>a (extract.aliases || []).map(a=>a
.trim() .trim()
// .replace(TITLE_ALIASES_SPECIAL_CHAR_REG_G, '_') // .replace(TITLE_ALIASES_SPECIAL_CHAR_REG_G, '_')
// //replase multiple _ to single _ // //replase multiple _ to single _

@ -142,7 +142,7 @@ export default abstract class DoubanAbstractLoadHandler<T extends DoubanSubject>
}else { }else {
context.syncStatusHolder?context.syncStatusHolder.syncStatus.handled(1):null; context.syncStatusHolder?context.syncStatusHolder.syncStatus.handled(1):null;
} }
return e; return undefined;
}); });
@ -608,12 +608,20 @@ export default abstract class DoubanAbstractLoadHandler<T extends DoubanSubject>
handlePersonNameByMeta(html: CheerioAPI, movie: DoubanSubject, context: HandleContext, handlePersonNameByMeta(html: CheerioAPI, movie: DoubanSubject, context: HandleContext,
metaProperty:string, objectProperty:string) { metaProperty:string, objectProperty:string) {
if (!movie) {
return;
}
const metaProperties: string[] = html(`head > meta[property='${metaProperty}']`).get() const metaProperties: string[] = html(`head > meta[property='${metaProperty}']`).get()
.map((e) => { .map((e) => {
return html(e).attr('content'); return html(e).attr('content');
}); });
// @ts-ignore // @ts-ignore
movie[objectProperty] const currentArray = movie[objectProperty];
if (!Array.isArray(currentArray)) {
return;
}
// @ts-ignore
currentArray
// @ts-ignore // @ts-ignore
.filter((p:Person) => p.name) .filter((p:Person) => p.name)
// @ts-ignore // @ts-ignore

@ -30,9 +30,9 @@ export default class DoubanBookLoadHandler extends DoubanAbstractLoadHandler<Dou
parseVariable(beforeContent: string, variableMap:Map<string, DataField>, extract: DoubanBookSubject, context: HandleContext): void { parseVariable(beforeContent: string, variableMap:Map<string, DataField>, extract: DoubanBookSubject, context: HandleContext): void {
variableMap.set(DoubanBookParameter.author, new DataField(DoubanBookParameter.author, variableMap.set(DoubanBookParameter.author, new DataField(DoubanBookParameter.author,
DataValueType.array, extract.author, extract.author.map(this.handleSpecialAuthorName))); DataValueType.array, extract.author, (extract.author || []).map(this.handleSpecialAuthorName)));
variableMap.set(DoubanBookParameter.translator, new DataField(DoubanBookParameter.translator, variableMap.set(DoubanBookParameter.translator, new DataField(DoubanBookParameter.translator,
DataValueType.array, extract.translator, extract.translator.map(this.handleSpecialAuthorName))); DataValueType.array, extract.translator, (extract.translator || []).map(this.handleSpecialAuthorName)));
} }
support(extract: DoubanSubject): boolean { support(extract: DoubanSubject): boolean {

@ -31,7 +31,7 @@ export default class DoubanGameLoadHandler extends DoubanAbstractLoadHandler<Dou
parseVariable(beforeContent: string, variableMap:Map<string, DataField>, extract: DoubanGameSubject, context: HandleContext): void { parseVariable(beforeContent: string, variableMap:Map<string, DataField>, extract: DoubanGameSubject, context: HandleContext): void {
// super.parseAliases(beforeContent, variableMap, extract, context); // super.parseAliases(beforeContent, variableMap, extract, context);
variableMap.set("aliases", new DataField("aliases", DataValueType.array, extract.aliases, variableMap.set("aliases", new DataField("aliases", DataValueType.array, extract.aliases,
extract.aliases.map(a=>a (extract.aliases || []).map(a=>a
.trim() .trim()
// .replace(TITLE_ALIASES_SPECIAL_CHAR_REG_G, '_') // .replace(TITLE_ALIASES_SPECIAL_CHAR_REG_G, '_')
// //replase multiple _ to single _ // //replase multiple _ to single _

@ -35,24 +35,24 @@ export default class DoubanMovieLoadHandler extends DoubanAbstractLoadHandler<Do
"director", "director",
DataValueType.array, DataValueType.array,
extract.director, extract.director,
extract.director.map(SchemaOrg.getPersonName).filter(c => c) (extract.director || []).map(SchemaOrg.getPersonName).filter(c => c)
)); ));
variableMap.set("actor", new DataField( variableMap.set("actor", new DataField(
"actor", "actor",
DataValueType.array, DataValueType.array,
extract.actor, extract.actor,
extract.actor.map(SchemaOrg.getPersonName).filter(c => c) (extract.actor || []).map(SchemaOrg.getPersonName).filter(c => c)
)); ));
variableMap.set("author", new DataField( variableMap.set("author", new DataField(
"author", "author",
DataValueType.array, DataValueType.array,
extract.author, extract.author,
extract.author.map(SchemaOrg.getPersonName).map(name => super.getPersonName(name, context)).filter(c => c) (extract.author || []).map(SchemaOrg.getPersonName).map(name => super.getPersonName(name, context)).filter(c => c)
)); ));
variableMap.set("aliases", new DataField("aliases", DataValueType.array, extract.aliases, variableMap.set("aliases", new DataField("aliases", DataValueType.array, extract.aliases,
extract.aliases.map(a=>a (extract.aliases || []).map(a=>a
.trim() .trim()
// .replace(TITLE_ALIASES_SPECIAL_CHAR_REG_G, '_') // .replace(TITLE_ALIASES_SPECIAL_CHAR_REG_G, '_')
// //replase multiple _ to single _ // //replase multiple _ to single _
@ -98,7 +98,7 @@ export default class DoubanMovieLoadHandler extends DoubanAbstractLoadHandler<Do
} }
parseSubjectFromHtml(html: CheerioAPI, context: HandleContext): DoubanMovieSubject { parseSubjectFromHtml(html: CheerioAPI, context: HandleContext): DoubanMovieSubject {
const movie:DoubanMovieSubject = html('script') let movie: DoubanMovieSubject | undefined = html('script')
.get() .get()
.filter(scd => "application/ld+json" == html(scd).attr("type")) .filter(scd => "application/ld+json" == html(scd).attr("type"))
.map(i => { .map(i => {
@ -108,8 +108,8 @@ export default class DoubanMovieLoadHandler extends DoubanAbstractLoadHandler<Do
const idPattern = /(\d){5,10}/g; const idPattern = /(\d){5,10}/g;
const id = idPattern.exec(obj.url); const id = idPattern.exec(obj.url);
const name = obj.name; const name = obj.name;
const title = super.getTitleNameByMode(name, PersonNameMode.CH_NAME, context)??name; const title = super.getTitleNameByMode(name, PersonNameMode.CH_NAME, context) ?? name;
const originalTitle = super.getTitleNameByMode(name, PersonNameMode.EN_NAME, context) ?? name; const originalTitle = super.getTitleNameByMode(name, PersonNameMode.EN_NAME, context) ?? name;
const result: DoubanMovieSubject = { const result: DoubanMovieSubject = {
id: id ? id[0] : '', id: id ? id[0] : '',
@ -119,14 +119,14 @@ export default class DoubanMovieLoadHandler extends DoubanAbstractLoadHandler<Do
originalTitle: originalTitle, originalTitle: originalTitle,
desc: obj.description, desc: obj.description,
url: "https://movie.douban.com" + obj.url, url: "https://movie.douban.com" + obj.url,
director: obj.director, director: obj.director || [],
author: obj.author, author: obj.author || [],
actor: obj.actor, actor: obj.actor || [],
aggregateRating: obj.aggregateRating, aggregateRating: obj.aggregateRating,
datePublished: obj.datePublished ? new Date(obj.datePublished) : undefined, datePublished: obj.datePublished ? new Date(obj.datePublished) : undefined,
image: obj.image, image: obj.image,
imageUrl: obj.image, imageUrl: obj.image,
genre: obj.genre, genre: obj.genre || [],
publisher: '', publisher: '',
aliases: [""], aliases: [""],
language: [""], language: [""],
@ -136,10 +136,52 @@ export default class DoubanMovieLoadHandler extends DoubanAbstractLoadHandler<Do
} }
return result; return result;
})[0]; })[0];
this.handlePersonNameByMeta(html, movie, context, 'video:actor', 'actor');
this.handlePersonNameByMeta(html, movie, context, 'video:director', 'director');
const desc:string = html("span[property='v:summary']").text(); // Fallback: if JSON-LD parsing failed (e.g., anti-bot page), extract from meta tags
if (!movie) {
const title = html(html("head > meta[property='og:title']").get(0)).attr("content") || '';
const image = html(html("head > meta[property='og:image']").get(0)).attr("content") || '';
const urlMeta = html(html("head > meta[property='og:url']").get(0)).attr("content") || '';
const desc = html(html("head > meta[property='og:description']").get(0)).attr("content") || '';
// Extract ID from URL
const idPattern = /(\d){5,10}/g;
const idMatch = idPattern.exec(urlMeta);
const id = idMatch ? idMatch[0] : '';
// Extract score from HTML
const scoreText = html("#interest_sectl strong[property='v:average']").text();
const score = scoreText ? parseFloat(scoreText) : undefined;
movie = {
id,
title,
type: this.getSupportType(),
score,
originalTitle: title,
desc,
url: urlMeta || (id ? `https://movie.douban.com/subject/${id}/` : ''),
director: [],
author: [],
actor: [],
aggregateRating: undefined,
datePublished: undefined,
image,
imageUrl: image,
genre: [],
publisher: '',
aliases: [],
language: [],
country: [],
time: null,
IMDb: null,
};
}
this.handlePersonNameByMeta(html, movie, context, 'video:actor', 'actor');
this.handlePersonNameByMeta(html, movie, context, 'video:director', 'director');
const desc: string = html("span[property='v:summary']").text();
if (desc) { if (desc) {
movie.desc = desc; movie.desc = desc;
} }
@ -156,7 +198,7 @@ export default class DoubanMovieLoadHandler extends DoubanAbstractLoadHandler<Do
// value = html(info.next.next).text().trim(); // value = html(info.next.next).text().trim();
const vas = html(info.next).text().trim(); const vas = html(info.next).text().trim();
value = vas.split("/").map((v) => v.trim()); value = vas.split("/").map((v) => v.trim());
} else if(key.indexOf('片长') >= 0) { } else if (key.indexOf('片长') >= 0) {
value = html(info.next.next).text().trim() value = html(info.next.next).text().trim()
} else { } else {
value = html(info.next).text().trim(); value = html(info.next).text().trim();
@ -164,11 +206,11 @@ export default class DoubanMovieLoadHandler extends DoubanAbstractLoadHandler<Do
valueMap.set(MovieKeyValueMap.get(key), value); valueMap.set(MovieKeyValueMap.get(key), value);
}) })
movie.country = valueMap.has('country') ? valueMap.get('country') : []; movie.country = valueMap.has('country') ? valueMap.get('country') : [];
movie.language = valueMap.has('language') ? valueMap.get('language') : []; movie.language = valueMap.has('language') ? valueMap.get('language') : [];
movie.time = valueMap.has('time') ? valueMap.get('time') : ""; movie.time = valueMap.has('time') ? valueMap.get('time') : "";
movie.aliases = valueMap.has('aliases') ? valueMap.get('aliases') : []; movie.aliases = valueMap.has('aliases') ? valueMap.get('aliases') : [];
movie.IMDb = valueMap.has('IMDb') ? valueMap.get('IMDb') : ""; movie.IMDb = valueMap.has('IMDb') ? valueMap.get('IMDb') : "";
return movie; return movie;
} }

@ -25,22 +25,22 @@ export class DoubanTeleplayLoadHandler extends DoubanAbstractLoadHandler<DoubanT
} }
parseVariable(beforeContent: string, variableMap:Map<string, DataField>, extract: DoubanTeleplaySubject, context: HandleContext): void { parseVariable(beforeContent: string, variableMap:Map<string, DataField>, extract: DoubanTeleplaySubject, context: HandleContext): void {
variableMap.set("director", new DataField("director", DataValueType.array, extract.director,extract.director.map(SchemaOrg.getPersonName).filter(c => c))); variableMap.set("director", new DataField("director", DataValueType.array, extract.director,(extract.director || []).map(SchemaOrg.getPersonName).filter(c => c)));
variableMap.set("actor", new DataField( variableMap.set("actor", new DataField(
"actor", "actor",
DataValueType.array, DataValueType.array,
extract.actor, extract.actor,
extract.actor.map(SchemaOrg.getPersonName).filter(c => c) (extract.actor || []).map(SchemaOrg.getPersonName).filter(c => c)
)); ));
variableMap.set("author", new DataField( variableMap.set("author", new DataField(
"author", "author",
DataValueType.array, DataValueType.array,
extract.author, extract.author,
extract.author.map(SchemaOrg.getPersonName).map(name => super.getPersonName(name, context)).filter(c => c) (extract.author || []).map(SchemaOrg.getPersonName).map(name => super.getPersonName(name, context)).filter(c => c)
)); ));
variableMap.set("aliases", new DataField("aliases", DataValueType.array, extract.aliases, variableMap.set("aliases", new DataField("aliases", DataValueType.array, extract.aliases,
extract.aliases.map(a=>a (extract.aliases || []).map(a=>a
.trim() .trim()
// .replace(TITLE_ALIASES_SPECIAL_CHAR_REG_G, '_') // .replace(TITLE_ALIASES_SPECIAL_CHAR_REG_G, '_')
// //replase multiple _ to single _ // //replase multiple _ to single _
@ -84,7 +84,7 @@ export class DoubanTeleplayLoadHandler extends DoubanAbstractLoadHandler<DoubanT
} }
parseSubjectFromHtml(html: CheerioAPI, context: HandleContext): DoubanTeleplaySubject { parseSubjectFromHtml(html: CheerioAPI, context: HandleContext): DoubanTeleplaySubject {
const teleplay:DoubanTeleplaySubject = html('script') let teleplay: DoubanTeleplaySubject | undefined = html('script')
.get() .get()
.filter(scd => "application/ld+json" == html(scd).attr("type")) .filter(scd => "application/ld+json" == html(scd).attr("type"))
.map(i => { .map(i => {
@ -104,14 +104,14 @@ export class DoubanTeleplayLoadHandler extends DoubanAbstractLoadHandler<DoubanT
originalTitle: originalTitle, originalTitle: originalTitle,
desc: obj.description, desc: obj.description,
url: "https://movie.douban.com" + obj.url, url: "https://movie.douban.com" + obj.url,
director: obj.director, director: obj.director || [],
author: obj.author, author: obj.author || [],
actor: obj.actor, actor: obj.actor || [],
aggregateRating: obj.aggregateRating, aggregateRating: obj.aggregateRating,
datePublished: obj.datePublished ? new Date(obj.datePublished) : undefined, datePublished: obj.datePublished ? new Date(obj.datePublished) : undefined,
image: obj.image, image: obj.image,
imageUrl: obj.image, imageUrl: obj.image,
genre: obj.genre, genre: obj.genre || [],
score: obj.aggregateRating ? obj.aggregateRating.ratingValue : undefined, score: obj.aggregateRating ? obj.aggregateRating.ratingValue : undefined,
publisher: "", publisher: "",
aliases: [""], aliases: [""],
@ -124,6 +124,46 @@ export class DoubanTeleplayLoadHandler extends DoubanAbstractLoadHandler<DoubanT
return result; return result;
})[0]; })[0];
// Fallback: if JSON-LD parsing failed, extract from meta tags
if (!teleplay) {
const title = html(html("head > meta[property='og:title']").get(0)).attr("content") || '';
const image = html(html("head > meta[property='og:image']").get(0)).attr("content") || '';
const urlMeta = html(html("head > meta[property='og:url']").get(0)).attr("content") || '';
const desc = html(html("head > meta[property='og:description']").get(0)).attr("content") || '';
const idPattern = /(\d){5,10}/g;
const idMatch = idPattern.exec(urlMeta);
const id = idMatch ? idMatch[0] : '';
const scoreText = html("#interest_sectl strong[property='v:average']").text();
const score = scoreText ? parseFloat(scoreText) : undefined;
teleplay = {
id,
title,
type: this.getSupportType(),
score,
originalTitle: title,
desc,
url: urlMeta || (id ? `https://movie.douban.com/subject/${id}/` : ''),
director: [],
author: [],
actor: [],
aggregateRating: undefined,
datePublished: undefined,
image,
imageUrl: image,
genre: [],
publisher: '',
aliases: [],
language: [],
country: [],
episode: null,
time: null,
IMDb: null,
};
}
this.handlePersonNameByMeta(html, teleplay, context, 'video:actor', 'actor'); this.handlePersonNameByMeta(html, teleplay, context, 'video:actor', 'actor');
this.handlePersonNameByMeta(html, teleplay, context, 'video:director', 'director'); this.handlePersonNameByMeta(html, teleplay, context, 'video:director', 'director');
const desc:string = html("span[property='v:summary']").text(); const desc:string = html("span[property='v:summary']").text();

@ -33,28 +33,28 @@ export default class DoubanTheaterLoadHandler extends DoubanAbstractLoadHandler<
"director", "director",
DataValueType.array, DataValueType.array,
extract.director, extract.director,
extract.director.map(SchemaOrg.getPersonName).filter(c => c) (extract.director || []).map(SchemaOrg.getPersonName).filter(c => c)
)); ));
variableMap.set("actor", new DataField( variableMap.set("actor", new DataField(
"actor", "actor",
DataValueType.array, DataValueType.array,
extract.actor, extract.actor,
extract.actor.map(SchemaOrg.getPersonName).filter(c => c) (extract.actor || []).map(SchemaOrg.getPersonName).filter(c => c)
)); ));
variableMap.set("author", new DataField( variableMap.set("author", new DataField(
"author", "author",
DataValueType.array, DataValueType.array,
extract.author, extract.author,
extract.author.map(SchemaOrg.getPersonName).map(name => super.getPersonName(name, context)).filter(c => c) (extract.author || []).map(SchemaOrg.getPersonName).map(name => super.getPersonName(name, context)).filter(c => c)
)); ));
variableMap.set("aliases", new DataField( variableMap.set("aliases", new DataField(
"aliases", "aliases",
DataValueType.array, DataValueType.array,
extract.aliases, extract.aliases,
extract.aliases.map(a => a (extract.aliases || []).map(a => a
.trim() .trim()
.replace(TITLE_ALIASES_SPECIAL_CHAR_REG_G, '_') .replace(TITLE_ALIASES_SPECIAL_CHAR_REG_G, '_')
//replace multiple _ to single _ //replace multiple _ to single _