Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
@@ -90,51 +90,51 @@ async def tiktok_video_details(username: str, video_id:str):
|
|
90 |
user_agent = "Mozilla/5.0 (compatible; YandexBot/3.0; +http://yandex.com/bots)"
|
91 |
res = requests.get(url, headers={"user-agent": user_agent})
|
92 |
|
93 |
-
soup = BeautifulSoup(res.content, "html.parser")
|
94 |
|
95 |
-
insights = soup.find("meta", {"property": "og:description"}).get("content")
|
96 |
-
likes = insights.split(" ", 1)[0]
|
97 |
-
desc = insights.rsplit(" comments. “", 1)[-1][:-1]
|
98 |
-
comments = insights.split(", ", 1)[-1].split(" ", 1)[0]
|
99 |
|
100 |
-
name = soup.find("meta", {"property": "og:title"}).get("content")[9:]
|
101 |
|
102 |
-
return {
|
103 |
-
|
104 |
-
|
105 |
-
|
106 |
-
|
107 |
-
}
|
108 |
|
109 |
-
|
110 |
-
|
111 |
-
|
112 |
-
|
113 |
|
114 |
-
|
115 |
|
116 |
-
|
117 |
|
118 |
-
|
119 |
|
120 |
-
|
121 |
|
122 |
-
|
123 |
|
124 |
|
125 |
-
|
126 |
-
|
127 |
-
|
128 |
-
|
129 |
|
130 |
-
|
131 |
-
|
132 |
-
|
133 |
-
|
134 |
-
|
135 |
-
|
136 |
-
|
137 |
-
|
138 |
-
|
139 |
-
|
140 |
-
|
|
|
90 |
user_agent = "Mozilla/5.0 (compatible; YandexBot/3.0; +http://yandex.com/bots)"
|
91 |
res = requests.get(url, headers={"user-agent": user_agent})
|
92 |
|
93 |
+
# soup = BeautifulSoup(res.content, "html.parser")
|
94 |
|
95 |
+
# insights = soup.find("meta", {"property": "og:description"}).get("content")
|
96 |
+
# likes = insights.split(" ", 1)[0]
|
97 |
+
# desc = insights.rsplit(" comments. “", 1)[-1][:-1]
|
98 |
+
# comments = insights.split(", ", 1)[-1].split(" ", 1)[0]
|
99 |
|
100 |
+
# name = soup.find("meta", {"property": "og:title"}).get("content")[9:]
|
101 |
|
102 |
+
# return {
|
103 |
+
# "insights": {"likeCount": likes, "commentCount": comments, "shareCount":None, "viewCount":None},
|
104 |
+
# "description": desc,
|
105 |
+
# "username": username,
|
106 |
+
# "name": name,
|
107 |
+
# }
|
108 |
|
109 |
+
text_maker = html2text.HTML2Text()
|
110 |
+
text_maker.ignore_links = True
|
111 |
+
text_maker.ignore_images = True
|
112 |
+
text_maker.bypass_tables = False
|
113 |
|
114 |
+
print("RESPONSE DETAIlL", res.content.decode("utf-8"))
|
115 |
|
116 |
+
docs = text_maker.handle(res.content.decode("utf-8"))
|
117 |
|
118 |
+
print("DOCS", docs)
|
119 |
|
120 |
+
content_detail = docs.split("###")[5]
|
121 |
|
122 |
+
likes, comments, bookmarks, shares = re.findall(r'\*\*([\w.]+)\*\*', content_detail)
|
123 |
|
124 |
|
125 |
+
profile = [x.strip() for x in content_detail.split("\n\nSpeed\n\n", 1)[1].split("\n", 6) if x.strip()]
|
126 |
+
username = profile[0]
|
127 |
+
date = profile[1].rsplit(" · ", 1)[-1]
|
128 |
+
desc = profile[-1].replace("**", "")
|
129 |
|
130 |
+
return {
|
131 |
+
"insights":{
|
132 |
+
"likeCount":likes,
|
133 |
+
"commentCount":comments,
|
134 |
+
"bookmarkCount":bookmarks,
|
135 |
+
"shareCount":shares
|
136 |
+
},
|
137 |
+
"username":username,
|
138 |
+
"date":date,
|
139 |
+
"description":desc
|
140 |
+
}
|