Created
October 16, 2020 16:43
-
-
Save mdvsh/11a4a5b14977d25f443d37ea005b6897 to your computer and use it in GitHub Desktop.
isef scraper
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from bs4 import BeautifulSoup | |
src = open('bhai.html', 'r') | |
import re, csv, pandas | |
soup = BeautifulSoup(src, 'lxml') | |
data = {} | |
table = soup.find("table", attrs={'class':'stripe'}) | |
table_head = table.thead.find_all("tr") | |
heading = [] | |
for th in table_head[0].find_all("th"): | |
heading.append(th.text.replace('\n', '').strip()) | |
table_data = [] | |
for tr in table.tbody.find_all("tr"): | |
t_row = {} | |
for td, th in zip(tr.find_all("td"), heading): | |
t_row[th] = td.text.replace('\n', '').strip() | |
table_data.append(t_row) | |
# print(table_data[1]) | |
schools = [] | |
for row in table_data: | |
if 'School' in row['Finalist Name(s)']: | |
s = re.sub(' +', ' ', row['Finalist Name(s)']) | |
schools.append(s[s.find("(")+1:s.find(")")][8:]) | |
# print(schools[7]) | |
# print(schools) | |
df = pandas.DataFrame(schools) | |
print(df.head) | |
# with open('mangla_learning_schools.csv', 'w', newline="\n") as src: | |
# writer = csv.writer(src, delimiter=',') | |
# writer.writerow(schools) | |
df.to_csv('mangla_learning.csv') |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment