Update code

This commit is contained in:
Oystein Kristoffer Tveit 2020-06-17 13:08:39 +02:00
parent 510b27b802
commit 55390c0d0f
1 changed files with 50 additions and 45 deletions

View File

@ -334,7 +334,7 @@ ExampleResults parseExamplePageData(String pageHtml, String phrase) {
/* PHRASE SCRAPE FUNCTIONS START */
List<String> getTags(Document document) {
final tags = [];
final List<String> tags = [];
final tagElements = document.querySelectorAll('.concept_light-tag');
for (var i = 0; i < tagElements.length; i += 1) {
@ -345,40 +345,8 @@ List<String> getTags(Document document) {
return tags;
}
PhrasePageScrapeResult getMeaningsOtherFormsAndNotes(Document document) {
final returnValues = PhrasePageScrapeResult( otherForms: [], notes: [] );
// const meaningsWrapper = $('#page_container > div > div > article > div > div.concept_light-meanings.medium-9.columns > div');
final meaningsWrapper = document.querySelector('.meanings-wrapper');
final meaningsChildren = meaningsWrapper.children;
final meanings = [];
var mostRecentWordTypes = [];
for (var meaningIndex = 0; meaningIndex < meaningsChildren.length; meaningIndex += 1) {
final child = meaningsChildren[meaningIndex];
if (child.className.contains('meaning-tags')) {
mostRecentWordTypes = child.text.split(',').map((s) => s.trim().toLowerCase()).toList();
} else if (mostRecentWordTypes[0] == 'other forms') {
returnValues.otherForms = child.text.split('')
.map((s) => s.replaceAll('', '').replaceAll('', '').split(' '))
.map((a) => (KanjiKanaPair( kanji: a[0], kana: a[1] )));
} else if (mostRecentWordTypes[0] == 'notes') {
returnValues.notes = child.text.split('\n');
} else {
final meaning = child.querySelector('.meaning-meaning').text;
child.querySelector('.meaning-abstract')
.querySelector('a')
.remove();
final meaningAbstract = child.querySelector('.meaning-abstract').text;
final supplemental = child.querySelector('.supplemental_info').text.split(',')
.map((s) => s.trim())
.toList();
final seeAlsoTerms = [];
List<String> getSeeAlsoTerms(List<String> supplemental) {
final List<String> seeAlsoTerms = [];
for (var i = supplemental.length - 1; i >= 0; i -= 1) {
final supplementalEntry = supplemental[i];
if (supplementalEntry.startsWith('See also')) {
@ -386,23 +354,60 @@ PhrasePageScrapeResult getMeaningsOtherFormsAndNotes(Document document) {
supplemental.removeAt(i);
}
}
return seeAlsoTerms;
}
final sentences = [];
final sentenceElements = child.querySelector('.sentences').querySelectorAll('.sentence');
List<PhraseScrapeSentence> getSentences(sentenceElements) {
final List<PhraseScrapeSentence> sentences = [];
for (var sentenceIndex = 0; sentenceIndex < sentenceElements.length; sentenceIndex += 1) {
for (var sentenceIndex = 0; sentenceIndex < (sentenceElements?.length ?? 0); sentenceIndex += 1) {
final sentenceElement = sentenceElements[sentenceIndex];
final english = sentenceElement.querySelector('.english').text;
final pieces = getPieces(sentenceElement);
sentenceElement.querySelector('.english').remove();
sentenceElement.querySelector('.furigana').remove();
sentenceElement.querySelector('.english')?.remove();
sentenceElement.querySelector('.furigana')?.remove();
final japanese = sentenceElement.text;
sentences.add(PhraseScrapeSentence(english: english, japanese: japanese, pieces: pieces));
}
return sentences;
}
PhrasePageScrapeResult getMeaningsOtherFormsAndNotes(Document document) {
final returnValues = PhrasePageScrapeResult( otherForms: [], notes: [] );
// const meaningsWrapper = $('#page_container > div > div > article > div > div.concept_light-meanings.medium-9.columns > div');
final meaningsWrapper = document.querySelector('.meanings-wrapper');
final meaningsChildren = meaningsWrapper.children;
final List<PhraseScrapeMeaning> meanings = [];
var mostRecentWordTypes = [];
for (var meaningIndex = 0; meaningIndex < meaningsChildren.length; meaningIndex += 1) {
final child = meaningsChildren[meaningIndex];
if (child.className.contains('meaning-tags')) {
mostRecentWordTypes = child.text.split(',').map((s) => s.trim().toLowerCase()).toList();
} else if (mostRecentWordTypes[0] == 'other forms') {
returnValues.otherForms = child.text.split('')
.map((s) => s.replaceAll('', '').replaceAll('', '').split(' '))
.map((a) => (KanjiKanaPair( kanji: a[0], kana: (a.length == 2) ? a[1] : null ))).toList();
} else if (mostRecentWordTypes[0] == 'notes') {
returnValues.notes = child.text.split('\n');
} else {
final meaning = child.querySelector('.meaning-meaning').text;
child.querySelector('.meaning-abstract')?.querySelector('a')?.remove();
final meaningAbstract = child.querySelector('.meaning-abstract')?.text;
final supplemental = child.querySelector('.supplemental_info')?.text?.split(',')?.map((s) => s.trim())?.toList();
final seeAlsoTerms = (supplemental != null) ? getSeeAlsoTerms(supplemental) : null;
final sentenceElements = child.querySelector('.sentences')?.querySelectorAll('.sentence');
final sentences = (sentenceElements != null) ? getSentences(sentenceElements) : null;
meanings.add(PhraseScrapeMeaning(
seeAlsoTerms: seeAlsoTerms,
sentences: sentences,
@ -465,19 +470,19 @@ class JishoApi {
/// @async
Future<PhrasePageScrapeResult> scrapeForPhrase(String phrase) async {
final uri = uriForPhraseScrape(phrase);
try {
// try {
final response = await http.get(uri);
return parsePhrasePageData(response.body, phrase);
} catch (err) {
if (err.response.status == 404) {
return PhrasePageScrapeResult(
query: phrase,
found: false,
);
}
// } catch (err) {
// // if (err.response?.status == 404) {
// // return PhrasePageScrapeResult(
// // query: phrase,
// // found: false,
// // );
// // }
throw err;
}
// throw err;
// }
}
/// Scrape Jisho.org for information about a kanji character.