BeautifulSoup getting text from a script within an anchor tag - beautifulsoup

Question

So I have a <tr> tag with multiple <td> as a substring of it.
<tr>
<td align='center' class="row2">
10
</td>
<td align="center" class="row2">
<a href='https://forum.net/index.php?;showuser=17311'>xxboxx</a>
</td>
<td align="center" class="row2">
<!--script type="text/javascript">
s = "236".replace(/,/g,'');
document.write(abbrNum(s,1));
</script-->
236
</td>
</tr>
this is my current code; i have no problem getting the first two, but trying to get out of a script I've tried various ways provided by other similar questions on stackoverflow; but I've not been successful.
def extractDataFromRow2(_url, 'td', 'row2', 'align' , 'center'):
try:
for container in _url.find_all('td', {'class': 'row2','align': 'center''}):
# get data from topic title in table cell
replies_numb = container.select_one(
'a[href^="javascript:]"').text
print('there are ' + replies_numb + ' replies')
topic_starter = container.next_sibling.text
print('the owner of this topic is ' + topic_starter)
for total_view in container.find('a', href=True, style=True):
#total_view = container.select_one(style="background-color:").text
#total_view = container.find(("td")["style"])
#total_view = container.next_sibling.find_next_sibling/next_sibling
#but they're not able to access the last one within <tr> tag
print(total_view )
if replies_numb and topic_starter is not None:
dict_replies = {'Replies' : replies_numb}
dict_topic_S = {'Topic_Starter' : topic_starter}
list_1.append(dict_replies)
list_2.append(dict_topic_S)
else:
print('no data')
except Exception as e:
print('Error.extractDataFromRow2:', e)
return None
Link of the page I'm trying to get data from.
if there is a much cleaner approach to this; I'm more than happy to learn from the feedbacks given.

Answer 1

The html code you shared might not be sufficent for answer so i checked out the url you shared. Here is the way to scrape your table.
from bs4 import BeautifulSoup
import requests
r = requests.get("https://forum.lowyat.net/ReviewsandGuides")
soup = BeautifulSoup(r.text, 'lxml')
index = 0
#First two rows of table is not data so we skip it. Last row of table is for searching we also skip it. Table contains 30 rows of data. That is why we are slicing list
for row in soup.select('table[cellspacing="1"] > tr')[2:32]:
replies = row.select_one('td:nth-of-type(4)').text.strip()
topic_started = row.select_one('td:nth-of-type(5)').text.strip()
total_views = row.select_one('td:nth-of-type(6)').text.strip()
index +=1
print(index,replies, topic_started, total_views)
The result is
1 148 blurjoey 9,992
2 10 xxboxx 263
3 18 JayceOoi 1,636
4 373 idoblu 54,589
5 237 blurjoey 16,101
6 526 JayceOoi 57,577
7 131 JayceOoi 34,354
8 24 blurjoey 4,261
9 2 JayceOoi 249
10 72 KeyMochi 26,622
11 7 champu 331
12 0 asunakirito 210
13 0 asunakirito 172
14 0 asunakirito 199
15 17 blurjoey 3,351
16 860 blurjoey 112,556
17 0 chennegan 174
18 0 goldfries 185
19 4 JayceOoi 601
20 2 JayceOoi 309
21 10 blurjoey 1,826
22 3 JayceOoi 398
23 4 squallz05 310
24 0 asunakirito 265
25 25 asunakirito 12,326
26 0 blurjoey 279
27 14 JayceOoi 2,092
28 0 chennegan 305
29 8 Pharamain 732
30 19 idoblu 1,273

Answer 2

Please note, you must use lxml parser or it will error.
def extractDataFromRow2(url):
results = []
html = requests.get(url).text
soup = BeautifulSoup(html, 'lxml')
for row in soup.select('#forum_topic_list tr'):
cols = row.select('td')
if len(cols) != 7:
continue
cols[2] = cols[2].find('a') # fix title
values = [c.text.strip() for c in cols]
results.append({
'Title' : values[2],
'Replies' : values[3],
'Topic_Starter' : values[4],
'total_view: ' : values[5]
})
return results
threadlists = extractDataFromRow2('https://forum.....')
print(threadlists)
results
[
{
"Title": "Xiaomi 70Mai Pro",
"Replies": "148",
"Topic_Starter": "blurjoey",
"total_view: ": "9,996"
},
{
"Title": "Adata XPG SX8200 Pro 512GB NVME SSD",
"Replies": "10",
"Topic_Starter": "xxboxx",
"total_view: ": "265"
},
....
]