Develop Reference

Creating multiple dataframe using loop or function

I'm trying to extract the hash rate for 3 cryptocurrencies and I have attached the code for the same below. Now, I want to pass three urls and in return I need three different different dictionaries which should have the values. I'm stuck and I don't understand how should I go about it. I have tried using loops but it is not working out for me.
url = {'Bitcoin' : 'https://bitinfocharts.com/comparison/bitcoin-hashrate.html#3y',
'Ethereum': 'https://bitinfocharts.com/comparison/ethereum-hashrate.html#3y',
'Litecoin': 'https://bitinfocharts.com/comparison/litecoin-hashrate.html'}
for ele in url:
#### requesting the page and extracting the script which has date and values
session = requests.Session()
page = session.get(ele[i])
soup = BeautifulSoup(page.content, 'html.parser')
values = str(soup.find_all('script')[4])
values = values.split('d = new Dygraph(document.getElementById("container"),')[1]
#create an empty dict to append date and hashrates
dict([("crypto_1 %s" % i,[]) for i in range(len(url))])
#run a loop over all the dates and adding to dictionary
for i in range(values.count('new Date')):
date = values.split('new Date("')[i+1].split('"')[0]
value = values.split('"),')[i+1].split(']')[0]
dict([("crypto_1 %s" % i)[date] = value

You can use next example how to get data from all 3 URLs and create a dataframe/dictionary from it:
import re
import requests
import pandas as pd
url = {
"Bitcoin": "https://bitinfocharts.com/comparison/bitcoin-hashrate.html#3y",
"Ethereum": "https://bitinfocharts.com/comparison/ethereum-hashrate.html#3y",
"Litecoin": "https://bitinfocharts.com/comparison/litecoin-hashrate.html",
}
data = []
for name, u in url.items():
html_doc = requests.get(u).text
for date, hash_rate in re.findall(
r'\[new Date\("(.*?)"\),(.*?)\]', html_doc
):
data.append(
{
"Name": name,
"Date": date,
"Hash Rate": float("nan")
if hash_rate == "null"
else float(hash_rate),
}
)
df = pd.DataFrame(data)
df["Date"] = pd.to_datetime(df["Date"])
# here save df to CSV
# this will create a dictionary, where the keys are crypto names and values
# are dicts with keys Date/HashRate:
out = {}
for name, g in df.groupby("Name"):
out[name] = g[["Date", "Hash Rate"]].to_dict(orient="list")
print(out)
Prints:
{
"Bitcoin": {
"Date": [
Timestamp("2009-01-03 00:00:00"),
Timestamp("2009-01-04 00:00:00"),
Timestamp("2009-01-05 00:00:00"),
...

Cannot getting the "href" attributes via BeautifulSoup

in short, i can't get the links of "href" attribute from this link (a turkish online book and related stuff seller).
here's my code (i know it's not the best, i'm learning python for a few months online, so any heads up for best practices also welcomed)
i tried to get book names, writers, prices, publishers and the links for each book; without links it's working as i expected.
import requests
import pandas as pd
from bs4 import BeautifulSoup
from time import sleep
from random import randint
yazar = []
fiyat = []
yayın = []
isim = []
for i in range(1,10):
url = "https://www.dr.com.tr/CokSatanlar/Kitap#/page="+str(i)
page = requests.get(url)
soup = BeautifulSoup(page.text, "lxml")
# book names
k = soup.find_all("a", {"class":"prd-name"})
for i in k:
isim.append(i.text)
# writer names
y = soup.find_all("a", {"class":"who text-overflow"})
for i in y:
yazar.append(i.text)
# prices
f = soup.find_all("div", {"class":"prd-price"})
for i in f:
fiyat.append(i.text.split()[0])
# publishers
ye = soup.find_all("a", {"class":"prd-publisher"})
for i in ye:
yayın.append(i.get("title"))
sleep(randint(2, 4))
however when i try to get links
soup.find_all("a", {"class":"prd-name"}).get("href")
it turns none and i couldn't manage to make this work whatever i tried.
thank you all in advance and sorry for a little longer than usual post.

The data you see on the page is loaded from external location, so you need other URL to get correct data:
import requests
import pandas as pd
from bs4 import BeautifulSoup
url = "https://www.dr.com.tr/Catalog/CatalogProducts"
data = {
"catalogId": "4020",
"page": "1",
"sortfield": "soldcount",
"sortorder": "desc",
"size": "60",
"categoryid": "0",
"parentId": "0",
"mediatypes": "",
"HideNotForSale": "true",
"minPrice": "-1",
"maxPrice": "-1",
"writer": "",
"minDiscount": "-1",
"maxdiscount": "-1",
"language": "",
}
all_data = []
for page in range(1, 3): # <-- increase number of pages here
print(f"Getting page {page}")
data["page"] = page
soup = BeautifulSoup(requests.post(url, data=data).content, "html.parser")
for p in soup.select(".prd-content"):
all_data.append(p.get_text(strip=True, separator="|").split("|")[:5])
df = pd.DataFrame(
all_data, columns=["name", "autor", "price", "type", "publisher"]
)
print(df)
df.to_csv("data.csv", index=False)
Prints:
name autor price type publisher
0 Esra Ezmeci Seti 5 Kitap Takım - Defter Hediyeli Esra Ezmeci 155,45 TL İnce Kapak Destek Yayınları
1 Şimdi Onlar Düşünsün Bircan Yıldırım 36,20 TL İnce Kapak Destek Yayınları
2 İz Bıraktığın Kadar Varsın Esra Ezmeci 36,20 TL İnce Kapak Destek Yayınları
...
and saves data.csv (screenshot from Libre Office):

Think you wont get a None you will get:
AttributeError: ResultSet object has no attribute 'get'. You're probably treating a list of elements like a single element. Did you call find_all() when you meant to call find()?
find_all() produces a ResultSet, so you have to iterate it to get all the href:
for a in soup.find_all("a", {"class":"prd-name"}):
print('https://www.dr.com.tr'+a.get("href"))
Output
https://www.dr.com.tr/kitap/daha-adil-bir-dunya-mumkun/arastirma-tarih/politika-arastirma/turkiye-politika-/urunno=0001934858001
https://www.dr.com.tr/kitap/burasi-cok-onemli-enerjiden-ekonomiye-tam-bagimsiz-turkiye/arastirma-tarih/politika-arastirma/turkiye-politika-/urunno=0001966362001
https://www.dr.com.tr/kitap/iz-biraktigin-kadar-varsin/egitim-basvuru/psikoloji-bilimi/urunno=0001947472001
https://www.dr.com.tr/kitap/simdi-onlar-dusunsun/bircan-yildirim/egitim-basvuru/kisisel-gelisim/urunno=0001964436001
https://www.dr.com.tr/kitap/kadinlar-sicak-erkekler-soguk-sever/esra-ezmeci/egitim-basvuru/psikoloji-bilimi/urunno=0001904239001
https://www.dr.com.tr/kitap/dustugunde-kalkarsan-hayat-guzeldir/egitim-basvuru/psikoloji-bilimi/urunno=0001816754001
...

Find coordinates in wikipedia pages iterating over a list

Probably this is a simple question, but my experience in for loop is very limited.
I was trying to adapt the solution in this page https://www.mediawiki.org/wiki/API:Geosearch with some simple examples that i have, but the result is not what i expected.
For example:
I have this simple data frame:
df= pd.DataFrame({'City':['Sesimbra','Ciudad Juárez','31100 Treviso','Ramada Portugal','Olhão'],
'Country':['Portugal','México','Itália','Portugal','Portugal']})
I created a list based on cities:
lista_cidades = list(df['City'])
and i would like to iterate over this list to get the coordinates (decimal, preferably)
So far i tried this approach:
import requests
lng_dict = {}
lat_dict = {}
S = requests.Session()
URL = "https://en.wikipedia.org/w/api.php"
PARAMS = {
"action": "query",
"format": "json",
"titles": [lista_cidades],
"prop": "coordinates"
}
R = S.get(url=URL, params=PARAMS)
DATA = R.json()
PAGES = DATA['query']['pages']
for i in range(len(lista_cidades)):
for k, v in PAGES.items():
try:
lat_dict[lista_cidades[i]] = str(v['coordinates'][0]['lat'])
lng_dict[lista_cidades[i]] = str(v['coordinates'][0]['lon'])
except:
pass
but it looks like the code doesn't iterate over the list and always returns the same coordinate
For example, when i call the dictionary with latitude coordinates, this is what i get
lng_dict
{'Sesimbra': '-7.84166667',
'Ciudad Juárez': '-7.84166667',
'31100 Treviso': '-7.84166667',
'Ramada Portugal': '-7.84166667',
'Olhão': '-7.84166667'}
What should i do to solve this?
Thanks in advance

I think the query returns only one result, it will take only the last city from you list (in your cas the "Olhão" coordinates).
You can check it by logging the DATA content.
I do not know about wikipedia API, but either your call lack a parameter (documentation should give you the information) or you have to call the API for each city like :
import pandas as pd
import requests
df = pd.DataFrame({'City': ['Sesimbra', 'Ciudad Juárez', '31100 Treviso', 'Ramada Portugal', 'Olhão'],
'Country': ['Portugal', 'México', 'Itália', 'Portugal', 'Portugal']})
lista_cidades = list(df['City'])
lng_dict = {}
lat_dict = {}
S = requests.Session()
URL = "https://en.wikipedia.org/w/api.php"
for city in lista_cidades:
PARAMS = {
"action": "query",
"format": "json",
"titles": city,
"prop": "coordinates"
}
R = S.get(url=URL, params=PARAMS)
DATA = R.json()
PAGES = DATA['query']['pages']
for k, v in PAGES.items():
try:
lat_dict[city] = str(v['coordinates'][0]['lat'])
lng_dict[city] = str(v['coordinates'][0]['lon'])
except:
pass

Scrape eBay Sold Items Using Selenium Returns []

I have almost no webscraping experience, and wasn't able to solve this using BeautifulSoup, so I'm trying selenium (installed it today). I'm trying to scrape sold items on eBay. I'm trying to scrape:
https://www.ebay.com/sch/i.html?_from=R40&_nkw=oakley+sunglasses&_sacat=0&Brand=Oakley&rt=nc&LH_Sold=1&LH_Complete=1&_ipg=200&_oaa=1&_fsrp=1&_dcat=79720
Here is my code where I load in html code and convert to selenium html:
ebay_url = 'https://www.ebay.com/sch/i.html?_from=R40&_nkw=oakley+sunglasses&_sacat=0&Brand=Oakley&rt=nc&LH_Sold=1&LH_Complete=1&_ipg=200&_oaa=1&_fsrp=1&_dcat=79720'
html = requests.get(ebay_url)
#print(html.text)
driver = wd.Chrome(executable_path=r'/Users/mburley/Downloads/chromedriver')
driver.get(ebay_url)
Which correctly opens a new chrome session at the correct url. I'm working on getting the titles, prices, and date sold and then loading it into a csv file. Here is the code I have for those:
# Find all div tags and set equal to main_data
all_items = driver.find_elements_by_class_name("s-item__info clearfix")[1:]
#print(main_data)
# Loop over main_data to extract div classes for title, price, and date
for item in all_items:
date = item.find_element_by_xpath("//span[contains(#class, 'POSITIVE']").text.strip()
title = item.find_element_by_xpath("//h3[contains(#class, 's-item__title s-item__title--has-tags']").text.strip()
price = item.find_element_by_xpath("//span[contains(#class, 's-item__price']").text.strip()
print('title:', title)
print('price:', price)
print('date:', date)
print('---')
data.append( [title, price, date] )
Which just returns []. I think ebay may be blocking my IP, but the html code loads in and looks correct. Hopefully someone can help! Thanks!

It is not necessary to use Selenium for eBay scraping, as the data is not rendered by JavaScript thus can be extracted from plain HTML. It is enough to use BeautifulSoup web scraping library.
Keep in mind that problems with site parsing may arise when you try to request a site multiple times. eBay may consider that this is a bot that sends a request (not a real user).
To avoid this, one of the ways is to send headers that contain user-agent in the request, then the site will assume that you're a user and display information.
As an additional step is to rotate those user-agents. The ideal scenario is to use proxies in combo with rotated user-agents (besides CAPTCHA solver)
from bs4 import BeautifulSoup
import requests, json, lxml
# https://requests.readthedocs.io/en/latest/user/quickstart/#custom-headers
headers = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/106.0.0.0 Safari/537.36"
}
params = {
'_nkw': 'oakley+sunglasses', # search query
'LH_Sold': '1', # shows sold items
'_pgn': 1 # page number
}
data = []
while True:
page = requests.get('https://www.ebay.com/sch/i.html', params=params, headers=headers, timeout=30)
soup = BeautifulSoup(page.text, 'lxml')
print(f"Extracting page: {params['_pgn']}")
print("-" * 10)
for products in soup.select(".s-item__info"):
title = products.select_one(".s-item__title span").text
price = products.select_one(".s-item__price").text
link = products.select_one(".s-item__link")["href"]
data.append({
"title" : title,
"price" : price,
"link" : link
})
if soup.select_one(".pagination__next"):
params['_pgn'] += 1
else:
break
print(json.dumps(data, indent=2, ensure_ascii=False)
Example output
Extracting page: 1
----------
[
{
"title": "Shop on eBay",
"price": "$20.00",
"link": "https://ebay.com/itm/123456?hash=item28caef0a3a:g:E3kAAOSwlGJiMikD&amdata=enc%3AAQAHAAAAsJoWXGf0hxNZspTmhb8%2FTJCCurAWCHuXJ2Xi3S9cwXL6BX04zSEiVaDMCvsUbApftgXEAHGJU1ZGugZO%2FnW1U7Gb6vgoL%2BmXlqCbLkwoZfF3AUAK8YvJ5B4%2BnhFA7ID4dxpYs4jjExEnN5SR2g1mQe7QtLkmGt%2FZ%2FbH2W62cXPuKbf550ExbnBPO2QJyZTXYCuw5KVkMdFMDuoB4p3FwJKcSPzez5kyQyVjyiIq6PB2q%7Ctkp%3ABlBMULq7kqyXYA"
},
{
"title": "Oakley X-metal Juliet Men's Sunglasses",
"price": "$280.00",
"link": "https://www.ebay.com/itm/265930582326?hash=item3deab2a936:g:t8gAAOSwMNhjRUuB&amdata=enc%3AAQAHAAAAoH76tlPncyxembf4SBvTKma1pJ4vg6QbKr21OxkL7NXZ5kAr7UvYLl2VoCPRA8KTqOumC%2Bl5RsaIpJgN2o2OlI7vfEclGr5Jc2zyO0JkAZ2Gftd7a4s11rVSnktOieITkfiM3JLXJM6QNTvokLclO6jnS%2FectMhVc91CSgZQ7rc%2BFGDjXhGyqq8A%2FoEyw4x1Bwl2sP0viGyBAL81D2LfE8E%3D%7Ctkp%3ABk9SR8yw1LH9YA"
},
{
"title": " Used Oakley PROBATION Sunglasses Polished Gold/Dark Grey (OO4041-03)",
"price": "$120.00",
"link": "https://www.ebay.com/itm/334596701765?hash=item4de7847e45:g:d5UAAOSw4YtjTfEE&amdata=enc%3AAQAHAAAAoItMbbzfQ74gNUiinmOVnzKlPWE%2Fc54B%2BS1%2BrZpy6vm5lB%2Bhvm5H43UFR0zeCU0Up6sPU2Wl6O6WR0x9FPv5Y1wYKTeUbpct5vFKu8OKFBLRT7Umt0yxmtLLMWaVlgKf7StwtK6lQ961Y33rf3YuQyp7MG7H%2Fa9fwSflpbJnE4A9rLqvf3hccR9tlWzKLMj9ZKbGxWT17%2BjyUp19XIvX2ZI%3D%7Ctkp%3ABk9SR8yw1LH9YA"
},
As an alternative, you can use Ebay Organic Results API from SerpApi. It`s a paid API with a free plan that handles blocks and parsing on their backend.
Example code that paginates through all pages:
from serpapi import EbaySearch
import os, json
params = {
"api_key": os.getenv("API_KEY"), # serpapi api key
"engine": "ebay", # search engine
"ebay_domain": "ebay.com", # ebay domain
"_nkw": "oakley+sunglasses", # search query
"_pgn": 1, # page number
"LH_Sold": "1" # shows sold items
}
search = EbaySearch(params) # where data extraction happens
page_num = 0
data = []
while True:
results = search.get_dict() # JSON -> Python dict
if "error" in results:
print(results["error"])
break
for organic_result in results.get("organic_results", []):
link = organic_result.get("link")
price = organic_result.get("price")
data.append({
"price" : price,
"link" : link
})
page_num += 1
print(page_num)
if "next" in results.get("pagination", {}):
params['_pgn'] += 1
else:
break
print(json.dumps(data, indent=2))
Output:
[
{
"price": {
"raw": "$68.96",
"extracted": 68.96
},
"link": "https://www.ebay.com/itm/125360598217?epid=20030526224&hash=item1d3012ecc9:g:478AAOSwCt5iqgG5&amdata=enc%3AAQAHAAAA4Ls3N%2FEH5OR6w3uoTlsxUlEsl0J%2B1aYmOoV6qsUxRO1d1w3twg6LrBbUl%2FCrSTxNOjnDgIh8DSI67n%2BJe%2F8c3GMUrIFpJ5lofIRdEmchFDmsd2I3tnbJEqZjIkWX6wXMnNbPiBEM8%2FML4ljppkSl4yfUZSV%2BYXTffSlCItT%2B7ZhM1fDttRxq5MffSRBAhuaG0tA7Dh69ZPxV8%2Bu1HuM0jDQjjC4g17I3Bjg6J3daC4ZuK%2FNNFlCLHv97w2fW8tMaPl8vANMw8OUJa5z2Eclh99WUBvAyAuy10uEtB3NDwiMV%7Ctkp%3ABk9SR5DKgLD9YA"
},
{
"price": {
"raw": "$62.95",
"extracted": 62.95
},
"link": "https://www.ebay.com/itm/125368283608?epid=1567457519&hash=item1d308831d8:g:rnsAAOSw7PJiqMQz&amdata=enc%3AAQAHAAAA4AwZhKJZfTqrG8VskZL8rtfsuNtZrMdWYpndpFs%2FhfrIOV%2FAjLuzNzaMNIvTa%2B6QUTdkOwTLRun8n43cZizqtOulsoBLQIwy3wf19N0sHxGF5HaIDOBeW%2B2sobRnzGdX%2Fsmgz1PRiKFZi%2BUxaLQpWCoGBf9n8mjcsFXi3esxbmAZ8kenO%2BARbRBzA2Honzaleb2tyH5Tf8%2Bs%2Fm5goqbon%2FcEsR0URO7BROkBUUjDCdDH6fFi99m6anNMMC3yTBpzypaFWio0u2qu5TgjABUfO1wzxb4ofA56BNKjoxttb7E%2F%7Ctkp%3ABk9SR5DKgLD9YA"
},
# ...
]
Disclaimer, I work for SerpApi.

You can use the below code to scrape the details. also you can use pandas to store data in csv file.
Code :
ebay_url = 'https://www.ebay.com/sch/i.html?_from=R40&_nkw=oakley+sunglasses&_sacat=0&Brand=Oakley&rt=nc&LH_Sold=1&LH_Complete=1&_ipg=200&_oaa=1&_fsrp=1&_dcat=79720'
html = requests.get(ebay_url)
# print(html.text)
driver = wd.Chrome(executable_path=r'/Users/mburley/Downloads/chromedriver')
driver.maximize_window()
driver.implicitly_wait(30)
driver.get(ebay_url)
wait = WebDriverWait(driver, 20)
sold_date = []
title = []
price = []
i = 1
for item in driver.find_elements(By.XPATH, "//div[contains(#class,'title--tagblock')]/span[#class='POSITIVE']"):
sold_date.append(item.text)
title.append(driver.find_element_by_xpath(f"(//div[contains(#class,'title--tagblock')]/span[#class='POSITIVE']/ancestor::div[contains(#class,'tag')]/following-sibling::a/h3)[{i}]").text)
price.append(item.find_element_by_xpath(f"(//div[contains(#class,'title--tagblock')]/span[#class='POSITIVE']/ancestor::div[contains(#class,'tag')]/following-sibling::div[contains(#class,'details')]/descendant::span[#class='POSITIVE'])[{i}]").text)
i = i + 1
print(sold_date)
print(title)
print(price)
data = {
'Sold_date': sold_date,
'title': title,
'price': price
}
df = pd.DataFrame.from_dict(data)
df.to_csv('out.csv', index = 0)
Imports :
import pandas as pd
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.common.by import By

Scrape Tables on Multiple Pages with Single URL

I am trying to scrape data from Fangraphs. The tables are split into 21 pages but all of the pages use the same url. I am very new to webscraping (or python in general), but Fangraphs does not have a public API so scraping the page seems to be my only option. I am currently using BeautifulSoup to parse the HTML code and I am able to scrape the initial table, but that only contains the first 30 players, but I want the entire player pool. Two days of web searching and I am stuck. Link and my current code are below. I know they have a link to download the csv file, but that gets tedious through out the season and I would like expedite the data harvesting process. Any direction would be helpful, thank you.
https://www.fangraphs.com/projections.aspx?pos=all&stats=bat&type=fangraphsdc
import requests
import pandas as pd
url = 'https://www.fangraphs.com/projections.aspx?pos=all&stats=bat&type=fangraphsdc&team=0&lg=all&players=0'
response = requests.get(url, verify=False)
# Use BeautifulSoup to parse the HTML code
soup = BeautifulSoup(response.content, 'html.parser')
# changes stat_table from ResultSet to a Tag
stat_table = stat_table[0]
# Convert html table to list
rows = []
for tr in stat_table.find_all('tr')[1:]:
cells = []
tds = tr.find_all('td')
if len(tds) == 0:
ths = tr.find_all('th')
for th in ths:
cells.append(th.text.strip())
else:
for td in tds:
cells.append(td.text.strip())
rows.append(cells)
# convert table to df
table = pd.DataFrame(rows)

import requests
from bs4 import BeautifulSoup
import pandas as pd
params = {
"pos": "all",
"stats": "bat",
"type": "fangraphsdc"
}
data = {
'RadScriptManager1_TSM': 'ProjectionBoard1$dg1',
"__EVENTTARGET": "ProjectionBoard1$dg1",
'__EVENTARGUMENT': 'FireCommand:ProjectionBoard1$dg1$ctl00;PageSize;1000',
'__VIEWSTATEGENERATOR': 'C239D6F0',
'__SCROLLPOSITIONX': '0',
'__SCROLLPOSITIONY': '1366',
"ProjectionBoard1_tsStats_ClientState": "{\"selectedIndexes\":[\"0\"],\"logEntries\":[],\"scrollState\":{}}",
"ProjectionBoard1_tsPosition_ClientState": "{\"selectedIndexes\":[\"0\"],\"logEntries\":[],\"scrollState\":{}}",
"ProjectionBoard1$rcbTeam": "All+Teams",
"ProjectionBoard1_rcbTeam_ClientState": "",
"ProjectionBoard1$rcbLeague": "All",
"ProjectionBoard1_rcbLeague_ClientState": "",
"ProjectionBoard1_tsProj_ClientState": "{\"selectedIndexes\":[\"5\"],\"logEntries\":[],\"scrollState\":{}}",
"ProjectionBoard1_tsUpdate_ClientState": "{\"selectedIndexes\":[],\"logEntries\":[],\"scrollState\":{}}",
"ProjectionBoard1$dg1$ctl00$ctl02$ctl00$PageSizeComboBox": "30",
"ProjectionBoard1_dg1_ctl00_ctl02_ctl00_PageSizeComboBox_ClientState": "",
"ProjectionBoard1$dg1$ctl00$ctl03$ctl01$PageSizeComboBox": "1000",
"ProjectionBoard1_dg1_ctl00_ctl03_ctl01_PageSizeComboBox_ClientState": "{\"logEntries\":[],\"value\":\"1000\",\"text\":\"1000\",\"enabled\":true,\"checkedIndices\":[],\"checkedItemsTextOverflows\":false}",
"ProjectionBoard1_dg1_ClientState": ""
}
def main(url):
with requests.Session() as req:
r = req.get(url, params=params)
soup = BeautifulSoup(r.content, 'html.parser')
data['__VIEWSTATE'] = soup.find("input", id="__VIEWSTATE").get("value")
data['__EVENTVALIDATION'] = soup.find(
"input", id="__EVENTVALIDATION").get("value")
r = req.post(url, params=params, data=data)
df = pd.read_html(r.content, attrs={
'id': 'ProjectionBoard1_dg1_ctl00'})[0]
df.drop(df.columns[1], axis=1, inplace=True)
print(df)
df.to_csv("data.csv", index=False)
main("https://www.fangraphs.com/projections.aspx")
Output: view-online