use TMDB for IMDb

common/scrapers/imdb.py

@@ -16,10 +16,18 @@ class ImdbMovieScraper(AbstractScraper):
     regex = re.compile(r"(?<=https://www\.imdb\.com/title/)[a-zA-Z0-9]+")
 
     def scrape(self, url):
-
         effective_url = self.get_effective_url(url)
         if effective_url is None:
             raise ValueError("not valid url")
+        code = self.regex.findall(effective_url)[0]
+        s = TmdbMovieScraper()
+        s.scrape_imdb(code)
+        self.raw_data = s.raw_data
+        self.raw_img = s.raw_img
+        self.img_ext = s.img_ext
+        self.raw_data['source_site'] = self.site_name
+        self.raw_data['source_url'] = effective_url
+        return self.raw_data, self.raw_img
 
         api_url = self.get_api_url(effective_url)
         r = requests.get(api_url)

common/scrapers/tmdb.py

@@ -45,6 +45,18 @@ class TmdbMovieScraper(AbstractScraper):
         '音乐':             'Music',
     }
 
+    def scrape_imdb(self, imdb_code):
+        api_url = f"https://api.themoviedb.org/3/find/{imdb_code}?api_key={settings.TMDB_API3_KEY}&language=zh-CN&external_source=imdb_id"
+        r = requests.get(api_url)
+        res_data = r.json()
+        if 'movie_results' in res_data and len(res_data['movie_results']) > 0:
+            url = f"https://www.themoviedb.org/movie/{res_data['movie_results'][0]['id']}"
+        elif 'tv_results' in res_data and len(res_data['tv_results']) > 0:
+            url = f"https://www.themoviedb.org/tv/{res_data['tv_results'][0]['id']}"
+        else:
+            raise ValueError("Cannot find IMDb ID in TMDB")
+        return self.scrape(url)
+
     def scrape(self, url):
         m = self.regex.match(url)
         if m: