Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
@@ -6,6 +6,7 @@ import html2text
|
|
6 |
import requests
|
7 |
import httpx
|
8 |
import re
|
|
|
9 |
|
10 |
from fastapi.middleware.cors import CORSMiddleware
|
11 |
|
@@ -58,6 +59,80 @@ async def linkedin_post_details(post_id: str):
|
|
58 |
"is_edited": edited,
|
59 |
"insights": {"likeCount": likes, "commentCount": comments, "shareCount": None, "viewCount":None},
|
60 |
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
61 |
|
62 |
|
63 |
@app.get("/google_search")
|
@@ -86,6 +161,8 @@ async def google_search(q: str, delimiter: str = "\n---\n", sites: Annotated[lis
|
|
86 |
|
87 |
@app.get("/tiktok_video_details")
|
88 |
async def tiktok_video_details(username: str, video_id:str):
|
|
|
|
|
89 |
url = f"https://www.tiktok.com/{username}/video/{video_id}"
|
90 |
# user_agent = "LinkedInBot"
|
91 |
user_agent = "Mozilla/5.0 (compatible; YandexBot/3.0; +http://yandex.com/bots)"
|
|
|
6 |
import requests
|
7 |
import httpx
|
8 |
import re
|
9 |
+
import json
|
10 |
|
11 |
from fastapi.middleware.cors import CORSMiddleware
|
12 |
|
|
|
59 |
"is_edited": edited,
|
60 |
"insights": {"likeCount": likes, "commentCount": comments, "shareCount": None, "viewCount":None},
|
61 |
}
|
62 |
+
|
63 |
+
|
64 |
+
@app.get("/facebook_post_detail")
|
65 |
+
async def fb_post_detail(username: str, post_id: str):
|
66 |
+
url = f"https://www.facebook.com/{username}/posts/{post_id}"
|
67 |
+
user_agent = "Googlebot"
|
68 |
+
|
69 |
+
res = requests.get(
|
70 |
+
url,
|
71 |
+
headers={
|
72 |
+
"user-agent": user_agent,
|
73 |
+
"accept-language": "en-US"
|
74 |
+
},
|
75 |
+
timeout=(10, 27),
|
76 |
+
)
|
77 |
+
|
78 |
+
soup = BeautifulSoup(res.content, "html.parser")
|
79 |
+
|
80 |
+
script_tags = soup.find_all("script")
|
81 |
+
print(len(script_tags))
|
82 |
+
for script_tag in script_tags:
|
83 |
+
try:
|
84 |
+
if "important_reactors" in script_tag.string:
|
85 |
+
splitter = '"reaction_count":{"count":'
|
86 |
+
total_react, reaction_split = script_tag.string.split(splitter, 2)[1].split("},", 1)
|
87 |
+
total_react = total_react.split(',"')[0]
|
88 |
+
pattern = r"\[.*?\]"
|
89 |
+
|
90 |
+
reactions = re.search(pattern, reaction_split)
|
91 |
+
|
92 |
+
if reactions:
|
93 |
+
reactions = json.loads(reactions.group(0))
|
94 |
+
else:
|
95 |
+
reactions = []
|
96 |
+
|
97 |
+
reactions = [
|
98 |
+
dict(
|
99 |
+
name=reaction["node"]["localized_name"].lower(),
|
100 |
+
count=reaction["reaction_count"],
|
101 |
+
is_visible=reaction["visible_in_bling_bar"],
|
102 |
+
)
|
103 |
+
for reaction in reactions
|
104 |
+
]
|
105 |
+
|
106 |
+
splitter = '"share_count":{"count":'
|
107 |
+
|
108 |
+
shares = script_tag.string.split(splitter, 2)[1].split(",")[0]
|
109 |
+
splitter = '"comments":{"total_count":'
|
110 |
+
comments = script_tag.string.split(splitter, 2)[1].split("}")[0]
|
111 |
+
likes = [x.get("count") for x in reactions if x.get("name") == "like"][0]
|
112 |
+
|
113 |
+
print(total_react, reactions, shares, comments, likes)
|
114 |
+
if '"message":{"text":"' in script_tag.string:
|
115 |
+
desc = script_tag.string.split('"message":{"text":"', 1)[-1].split('"},')[0]
|
116 |
+
except Exception as e:
|
117 |
+
print(e)
|
118 |
+
continue
|
119 |
+
|
120 |
+
name = soup.find("meta", {"property": "og:title"}).get("content")
|
121 |
+
|
122 |
+
|
123 |
+
return {
|
124 |
+
"insights": {
|
125 |
+
"likeCount": likes,
|
126 |
+
"commentCount": comments,
|
127 |
+
"shareCount": shares,
|
128 |
+
"reactionCount": total_react,
|
129 |
+
"reactions": reactions,
|
130 |
+
},
|
131 |
+
"description": desc,
|
132 |
+
"username": username,
|
133 |
+
"name": name,
|
134 |
+
"date": None,
|
135 |
+
}
|
136 |
|
137 |
|
138 |
@app.get("/google_search")
|
|
|
161 |
|
162 |
@app.get("/tiktok_video_details")
|
163 |
async def tiktok_video_details(username: str, video_id:str):
|
164 |
+
if username[0] != @:
|
165 |
+
username = "@" + username
|
166 |
url = f"https://www.tiktok.com/{username}/video/{video_id}"
|
167 |
# user_agent = "LinkedInBot"
|
168 |
user_agent = "Mozilla/5.0 (compatible; YandexBot/3.0; +http://yandex.com/bots)"
|