Am new to Python and stuck with the 'next page' logic.
I tried while loop & selenium with chrome nothing worked.
Please shed some light in this -
import requests
from bs4 import BeautifulSoup
import csv
pages = [ 0 , 25 , 50 , 75]
for page in pages:
source = requests.get('https://finance.yahoo.com/screener/predefined/day_gainers?count=25&offset={}'.format(page)).text
soup = BeautifulSoup(source , 'lxml')
for link in soup.find_all("a"):
table = soup.find("table",{"class":"W(100%)"})
thead = table.find("thead").find_all("th")
table_head = [th.text for th in thead]
#print(table_head)
table_body = table.find ("tbody").find_all("tr")
with open("report.csv" , "a" , newline="") as csv_file:
csv_write = csv.writer(csv_file)
csv_write.writerow(table_head)
for tr in table_body:
table_data = [td.text.strip() for td in tr.find_all('td') ]
csv_write.writerow(table_data)
I think need to indent your code and its work fine. Here is code:
import requests
from bs4 import BeautifulSoup
import csv
pages = [ 0 , 25 , 50 , 75]
for page in pages:
source = requests.get('https://finance.yahoo.com/screener/predefined/day_gainers?count=25&offset={}'.format(page)).text
soup = BeautifulSoup(source , 'lxml')
for link in soup.find_all("a"):
table = soup.find("table",{"class":"W(100%)"})
thead = table.find("thead").find_all("th")
table_head = [th.text for th in thead]
#print(table_head)
table_body = table.find ("tbody").find_all("tr")
with open("report.csv" , "a" , newline="") as csv_file:
csv_write = csv.writer(csv_file)
csv_write.writerow(table_head)
for tr in table_body:
table_data = [td.text.strip() for td in tr.find_all('td') ]
csv_write.writerow(table_data)
Edit For the second for loop getting duplicates value. So remove second for loop. Here is edited code.
import requests
from bs4 import BeautifulSoup
import csv
pages = [ 0,25,50,75 ]
for page in pages:
source = requests.get('https://finance.yahoo.com/screener/predefined/day_gainers?count=25&offset={}'.format(page)).text
soup = BeautifulSoup(source , 'lxml')
table = soup.find("table",{"class":"W(100%)"})
thead = table.find("thead").find_all("th")
table_head = [th.text for th in thead]
table_body = table.find ("tbody").find_all("tr")
with open("report.csv" , "a" , newline="") as csv_file:
csv_write = csv.writer(csv_file)
csv_write.writerow(table_head)
for tr in table_body:
table_data = [td.text.strip() for td in tr.find_all('td') ]
csv_write.writerow(table_data)
The technical post webpages of this site follow the CC BY-SA 4.0 protocol. If you need to reprint, please indicate the site URL or the original address.Any question please contact:yoyou2525@163.com.