bug fix for iqiyi list loopback error

wwqgtxx · Jan 15, 2018 · efcca8e · efcca8e
1 parent c2ae65a
commit efcca8e
Show file tree

Hide file tree

Showing 4 changed files with 32 additions and 23 deletions.
diff --git a/wwqLyParse/parsers/iqiyilistparser.py b/wwqLyParse/parsers/iqiyilistparser.py
@@ -324,25 +324,26 @@ def parse(self, input_text, *k, **kk):
         }
 
         data_doc_id = html('span.play_source').attr('data-doc-id')
-        ejson_url = 'http://rq.video.iqiyi.com/aries/e.json?site=iqiyi&docId=' + data_doc_id + '&count=100000'
-        ejson = json.loads(get_url(ejson_url))
-        ejson_datas = ejson["data"]["objs"]
-        data["total"] = ejson_datas["info"]["total_video_number"]
-        data["title"] = ejson_datas["info"]["album_title"]
-        album_items = ejson_datas["episode"]["data"]
-        for album_item in album_items:
-            no = '第' + str(album_item["play_order"]) + '集'
-            name = album_item["title"]
-            url = album_item["play_url"]
-            subtitle = album_item["desciption"]
-            info = {
-                "name": name,
-                "no": no,
-                "subtitle": subtitle,
-                "url": url
-            }
-            data["data"].append(info)
-        # print(ejson)
+        if data_doc_id:
+            ejson_url = 'http://rq.video.iqiyi.com/aries/e.json?site=iqiyi&docId=' + data_doc_id + '&count=100000'
+            ejson = json.loads(get_url(ejson_url))
+            ejson_datas = ejson["data"]["objs"]
+            data["total"] = ejson_datas["info"]["total_video_number"]
+            data["title"] = ejson_datas["info"]["album_title"]
+            album_items = ejson_datas["episode"]["data"]
+            for album_item in album_items:
+                no = '第' + str(album_item["play_order"]) + '集'
+                name = album_item["title"]
+                url = album_item["play_url"]
+                subtitle = album_item["desciption"]
+                info = {
+                    "name": name,
+                    "no": no,
+                    "subtitle": subtitle,
+                    "url": url
+                }
+                data["data"].append(info)
+            # print(ejson)
         return data
 
 
@@ -376,9 +377,10 @@ def parse(self, input_text, *k, **kk):
                                         if type(item2) == dict and 'level' in item2 and \
                                                 item2['level'] == 3 and 'url' in item2:
                                             url = item2['url']
-                                            if url:
-                                                break
+                                            if url and re.search(r"www.iqiyi.com/v_", url):
+                                                url = None
                                 if url:
+                                    logging.debug(url)
                                     break
                     except json.JSONDecodeError:
                         logging.exception("IQiYiVListParser Error")
@@ -396,7 +398,10 @@ def parse(self, input_text, *k, **kk):
                                     item1['position'] == 3 and 'item' in item1:
                                 if type(item1['item']) == dict and '@id' in item1['item']:
                                     url = item1['item']['@id']
+                                    if url and re.search(r"www.iqiyi.com/v_", url):
+                                        url = None
                         if url:
+                            logging.debug(url)
                             break
                 except json.JSONDecodeError:
                     logging.exception("IQiYiVListParser Error")
@@ -408,6 +413,7 @@ def parse(self, input_text, *k, **kk):
                 a = PyQuery(a)
                 url = a.attr("href")
                 if url:
+                    logging.debug(url)
                     break
         if url:
             if str(url).startswith("//"):

diff --git a/wwqLyParse/parsers/yinyuetaiparser.py b/wwqLyParse/parsers/yinyuetaiparser.py
@@ -46,6 +46,7 @@ def parse(self, input_text, types=None, *k, **kk):
         video_data = api_data['videoInfo']['coreVideoInfo']
 
         title = video_data['videoName']
+        title = str(title).replace("&lt;", "《").replace("&gt;", "》")
         artist = video_data['artistNames']
         data["name"] = title
         for s in video_data['videoUrlModels']:

diff --git a/wwqLyParse/test.py b/wwqLyParse/test.py
@@ -25,12 +25,14 @@
     # main(r"file:///E:\QQDownloads\url.media")
     # main(r"https://youku.pohaier.com/yk.php?url=d1BTTTFlVnRTell1VDhtQmlLZ3lrTkZSUGtTdlhrY3JOZlJOTnZZRmE2ZDZiSVNkNU9rdVJoMlBoL1doR1FDRGVmWkJCR25rbkE=")
     # main("http://defaultts.tc.qq.com/defaultts.tc.qq.com/mcvctgljBW77YvaEtxIhsDu81rGkBDNrvJH-aOijrz6vYDOAERMwo8YjsMhsUX30gycp3l48NFvhiK0q8RrcI_piINVQwY4sfKdsmv5qi459Q7GV-rljooWl1yRZcP-f/c00248syj3f.321004.ts.m3u8?ver=4")
+    main("http://v.yinyuetai.com/video/2811002", parsers_name=["YinYueTaiParser"])
     # main("http://v.yinyuetai.com/video/2796852", parsers_name=["YinYueTaiParser"])
     # main("http://www.mgtv.com/b/316045/4096972.html", types="collection")
     # main("http://www.mgtv.com/b/316045/4096972.html", parsers_name=["MgTVParser"])
     # main("http://www.mgtv.com/b/316045/4096972.html", label="3@MgTVParser")
     # url_cache.timeout = 10
-    main("http://www.iqiyi.com/v_19rrl8pmn8.html")
+    # main("http://www.iqiyi.com/lib/m_201087714.html")
+    # main("http://www.iqiyi.com/v_19rrl8pmn8.html")
     # main("http://www.iqiyi.com/v_19rr8jbmeo.html", types="list")
     # time.sleep(10)
     # main("http://www.iqiyi.com/v_19rrl8pmn8.html", types="list")

diff --git a/wwqLyParse/version.txt b/wwqLyParse/version.txt
@@ -1 +1 @@
-1.2.4
+1.2.5