0
import requests
from bs4 import BeautifulSoup
import pandas as pd
def get_object(url):
soup = BeautifulSoup(requests.get(url).content,'html.parser')
return soup
def get_all_links_players(bsObject):
links_a = bsObject.find("td",class_ = "headcol no_sorter").findAll( "a")
urls = [i.get("href") for i in links_a]
return urls
def get_links_players():
links = ["https://www.mlb.com/stats" + "/?page" + "=" + str(i) for i in range(1,7)]
result = [requests.get(i).text for i in links]
bsObject = [BeautifulSoup(i,"lxml") for i in result]
all_players = [i.get("href") for i in bsObject.find("tbody",class_ = "notranslate").find_all("a")]
return all_players
if __name__ == "__main__":
for i in get_links_players():
print(i)
AttributeError: 'list' object has no attribute 'find'
The
findis not set to list, in fact. You should apply find to each element in the list. If you exchange line 23 forall_players = [i.get("href") for i in bsObject[0].find("tbody",class_ = "notranslate").find_all("a")], the program prints the number of players for that element. But it’s not clear what you’re doing, so it’s hard to answer. If you can, explain it better– Lucas
So, I’m making a web scraping of the baseball players from Mlb. I was able to iterate over all the player stats pages, so I want to take each player’s link and build a comic with all the details of each player.
– isabele alves pereira