Skip to content
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

[imdb] fix reviews #1038

Merged
merged 1 commit into from
Dec 8, 2024
Merged
Show file tree
Hide file tree
Changes from all 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
9 changes: 9 additions & 0 deletions imdb/po/ru.po
Original file line number Diff line number Diff line change
Expand Up @@ -289,3 +289,12 @@ msgstr "Импорт из EPG"

msgid "Channel Selection"
msgstr "Селектор каналов"

msgid "Spoiler"
msgstr "Спойлер"

msgid "%d out of %d found this helpful."
msgstr "%d из %d нашли это полезным."

msgid "IMDb Reviews failed"
msgstr "IMDb - ошибка получения отзывов"
72 changes: 46 additions & 26 deletions imdb/src/plugin.py
Original file line number Diff line number Diff line change
Expand Up @@ -327,6 +327,7 @@ def resetLabels(self):
self["extralabel"].setText("")
self.ratingstars = -1
self.reviews = []
self.reviewsJSON = None
self.spoilers = False
self.originalName = ""

Expand Down Expand Up @@ -514,35 +515,49 @@ def downloadTitle(self, title, titleId):

def gotReviews(self, response):
self["statusbar"].setText(_("Parsing reviews..."))
self.reviewsHTML = response.content
self.reviewsHTML = self.reviewsHTML.decode("utf8")

reviewsmask = re.compile(
r'(?:<span>(?P<rating>\d+)</span>.*?)?'
r'class="title" > (?P<title>.*?)\n.*?'
r'\n>(?P<author>.*?)</a></span><span class="review-date">(?P<date>.*?)</span>.*?'
r'(?:spoiler-warning">(?P<spoiler>.*?)</.*?)?'
r'"text show-more__control">(?P<review>.*?)</div>.*?'
r'text-muted">\s+(?P<helpful>.*?)\s+<span', re.DOTALL)

for review in reviewsmask.finditer(self.reviewsHTML):
self.reviewsJSON = response.content.decode("utf8")

try:
reviews = json.loads(self.reviewsJSON)['data']['title']['reviews']['edges']
except Exception as e:
self["statusbar"].setText(_("IMDb Reviews failed"))
print("[IMDB] reviews failed:", str(e))
self.reviewsJSON = None
return

for review in reviews:
if 'node' not in review:
continue
review = review['node']
try:
helpful = review['helpfulness']['upVotes']
total = helpful + review['helpfulness']['downVotes']
if total:
helpful = _("%d out of %d found this helpful.") % (helpful, total)
else:
helpful = ""
except:
helpful = ""
self.reviews.append({
'rating': review.group('rating'),
'title': html2text(review.group('title')),
'author': html2text(review.group('author')),
'date': html2text(review.group('date')),
'spoiler': html2text(review.group('spoiler') or ""),
'review': html2text(review.group('review')),
'helpful': html2text(review.group('helpful'))
'rating': str(get(review, 'authorRating')),
'title': html2text(get(review, ('summary', 'originalText'))),
'author': html2text(get(review, ('author', 'nickName'))),
'date': get(review, 'submissionDate'),
'spoiler': get(review, 'spoiler') and self.spoiler_i18n,
'review': html2text(get(review, ('text', 'originalText', 'plaidHtml'))),
'helpful': helpful
})
self["statusbar"].setText(_("IMDb Reviews parsed"))
self.showExtras(reviews=True)

def downloadReviews(self):
self["statusbar"].setText(_("Downloading reviews..."))
fetchurl = "https://www.imdb.com/title/" + self.titleId + "/reviews/_ajax"
# print("[IMDB] downloadReviews()", fetchurl)
download = getPage(fetchurl, cookies=self.cookie)
params = {
"operationName": 'TitleReviewsRefine',
"variables": '{"const":"%s","first":25}' % self.titleId,
"extensions": '{"persistedQuery":{"sha256Hash":"89aff4cd7503e060ff1dd5aba91885d8bac0f7a21aa1e1f781848a786a5bdc19","version":1}}'
}
download = getPage("https://caching.graphql.imdb.com/", params=params, headers={"content-type": "application/json"}, cookies=self.cookie)
download.addCallback(self.gotReviews).addErrback(self.http_failed)

def showDetails(self):
Expand Down Expand Up @@ -606,8 +621,9 @@ def showExtras(self, synopsis=False, reviews=False):
if self.spoilers or not review['spoiler']:
reviews.append(review['review'])
reviews.append("")
reviews.append(review['helpful'])
reviews.append("")
if review['helpful']:
reviews.append(review['helpful'])
reviews.append("")
reviews.append("-" * 72)
reviews.append("")
self.reviewsTxt = "\n".join(reviews[:-3])
Expand Down Expand Up @@ -696,8 +712,11 @@ def saveHtmlDetails(self):
open(isave + ".html", 'w').write(self.html)
if self.json:
open(isave + ".json", 'w').write(self.json)
if self.reviews:
open(isave + "-reviews.html", 'w').write(self.reviewsHTML)
try:
if self.reviewsJSON:
open(isave + "-reviews.json", 'w').write(self.reviewsJSON)
except:
pass
try:
copy("/tmp/poster.jpg", isave + ".jpg")
except:
Expand Down Expand Up @@ -1082,6 +1101,7 @@ def makedate(date):
'sound': get(i18n, 'title_main_techspec_soundmix'),
'aspect': get(i18n, 'title_main_techspec_aspectratio'),
}
self.spoiler_i18n = get(i18n, 'common_label_spoiler', _("Spoiler"))

self.generalinfos = {
'director': ", ".join(get(name, ('name', 'nameText', 'text')) for name in get(main, ('directors', 'credits'))),
Expand Down
Loading