Skip to content

Commit 44fbf73

Browse files
avinashkranjanavinashkranjan
authored
Merge pull request #2467 from avinashkranjan/deepsource-transform-28769d95
format code with autopep8
2 parents 8076072 + 2fa1557 commit 44fbf73

File tree

1 file changed

+82
-80
lines changed

1 file changed

+82
-80
lines changed

‎Youtube_Scraper/main.py

Lines changed: 82 additions & 80 deletions
Original file line numberDiff line numberDiff line change
@@ -2,91 +2,93 @@
22
from bs4 import BeautifulSoup
33
import json
44

5+
56
def getAbout(channel_username):
6-
"""
7-
Returns:
8-
```
9-
{
10-
"name": Name of the channel
11-
"description": Description of the channel
12-
"channel_url": Link to the channel
13-
"channel_avatar": Channel avatar
14-
"channel_banner": Channel banner
15-
"subscriber_count": No. of subscribers of the channel
16-
"toal_videos": Total videos uploaded in the channel
17-
"total_views": Total views till date of the channel
18-
"join_date": Date the channel joined YouTube
19-
"country": Country of origin of the channel
20-
"links": Additional links provided from the channel
21-
}
22-
```
23-
"""
24-
url = f"https://www.youtube.com/@{channel_username}/about"
25-
try:
26-
res = requests.get(url)
27-
soup = BeautifulSoup(res.text, "html.parser")
28-
channel_data = {"channel_data": []}
29-
link_data = {"link_data": []}
30-
scripts = soup.find_all("script")
31-
req_script = scripts[35].text.strip()
32-
script = req_script[20:-1]
33-
data = json.loads(script)
7+
"""
8+
Returns:
9+
```
10+
{
11+
"name": Name of the channel
12+
"description": Description of the channel
13+
"channel_url": Link to the channel
14+
"channel_avatar": Channel avatar
15+
"channel_banner": Channel banner
16+
"subscriber_count": No. of subscribers of the channel
17+
"toal_videos": Total videos uploaded in the channel
18+
"total_views": Total views till date of the channel
19+
"join_date": Date the channel joined YouTube
20+
"country": Country of origin of the channel
21+
"links": Additional links provided from the channel
22+
}
23+
```
24+
"""
25+
url = f"https://www.youtube.com/@{channel_username}/about"
26+
try:
27+
res = requests.get(url)
28+
soup = BeautifulSoup(res.text, "html.parser")
29+
channel_data = {"channel_data": []}
30+
link_data = {"link_data": []}
31+
scripts = soup.find_all("script")
32+
req_script = scripts[35].text.strip()
33+
script = req_script[20:-1]
34+
data = json.loads(script)
35+
36+
metadata = data["metadata"]["channelMetadataRenderer"]
37+
title = metadata["title"]
38+
desc = metadata["description"]
39+
channel_url = metadata["vanityChannelUrl"]
40+
channel_avatar = metadata["avatar"]["thumbnails"][0]["url"]
41+
header = data["header"]["c4TabbedHeaderRenderer"]
42+
channel_banner = header["banner"]["thumbnails"][5]["url"]
43+
subs = header["subscriberCountText"]["simpleText"]
44+
total_videos = header["videosCountText"]["runs"][0]["text"]
3445

35-
metadata = data["metadata"]["channelMetadataRenderer"]
36-
title = metadata["title"]
37-
desc = metadata["description"]
38-
channel_url = metadata["vanityChannelUrl"]
39-
channel_avatar = metadata["avatar"]["thumbnails"][0]["url"]
40-
header = data["header"]["c4TabbedHeaderRenderer"]
41-
channel_banner = header["banner"]["thumbnails"][5]["url"]
42-
subs = header["subscriberCountText"]["simpleText"]
43-
total_videos = header["videosCountText"]["runs"][0]["text"]
46+
baser = data["contents"]["twoColumnBrowseResultsRenderer"]["tabs"]
47+
for b in baser:
48+
try:
49+
base = b["tabRenderer"]["content"]["sectionListRenderer"][
50+
"contents"
51+
][0]["itemSectionRenderer"]["contents"][0][
52+
"channelAboutFullMetadataRenderer"
53+
]
4454

45-
baser = data["contents"]["twoColumnBrowseResultsRenderer"]["tabs"]
46-
for b in baser:
47-
try:
48-
base = b["tabRenderer"]["content"]["sectionListRenderer"][
49-
"contents"
50-
][0]["itemSectionRenderer"]["contents"][0][
51-
"channelAboutFullMetadataRenderer"
52-
]
55+
total_views = base["viewCountText"]["simpleText"]
56+
join_date = base["joinedDateText"]["runs"][1]["text"]
57+
country = base["country"]["simpleText"]
5358

54-
total_views = base["viewCountText"]["simpleText"]
55-
join_date = base["joinedDateText"]["runs"][1]["text"]
56-
country = base["country"]["simpleText"]
59+
links = base["primaryLinks"]
60+
for i in links:
61+
link_data["link_data"].append(
62+
{
63+
"link_url": i["navigationEndpoint"]["urlEndpoint"][
64+
"url"
65+
],
66+
"link_name": i["title"]["simpleText"],
67+
"link_icon": i["icon"]["thumbnails"][0]["url"],
68+
}
69+
)
70+
except:
71+
pass
5772

58-
links = base["primaryLinks"]
59-
for i in links:
60-
link_data["link_data"].append(
61-
{
62-
"link_url": i["navigationEndpoint"]["urlEndpoint"][
63-
"url"
64-
],
65-
"link_name": i["title"]["simpleText"],
66-
"link_icon": i["icon"]["thumbnails"][0]["url"],
67-
}
68-
)
69-
except:
70-
pass
73+
channel_data["channel_data"].append(
74+
{
75+
"name": title,
76+
"description": desc,
77+
"channel_url": channel_url,
78+
"channel_avatar": channel_avatar,
79+
"channel_banner": channel_banner,
80+
"subscriber_count": subs,
81+
"toal_videos": total_videos,
82+
"total_views": total_views,
83+
"join_date": join_date,
84+
"country": country,
85+
"links": link_data,
86+
}
87+
)
88+
return channel_data["channel_data"][0]
89+
except:
90+
return None
7191

72-
channel_data["channel_data"].append(
73-
{
74-
"name": title,
75-
"description": desc,
76-
"channel_url": channel_url,
77-
"channel_avatar": channel_avatar,
78-
"channel_banner": channel_banner,
79-
"subscriber_count": subs,
80-
"toal_videos": total_videos,
81-
"total_views": total_views,
82-
"join_date": join_date,
83-
"country": country,
84-
"links": link_data,
85-
}
86-
)
87-
return channel_data["channel_data"][0]
88-
except:
89-
return None
9092

9193
if __name__ == "__main__":
92-
print(getAbout("BeaBetterDev"))
94+
print(getAbout("BeaBetterDev"))

0 commit comments

Comments
 (0)