BS4 Not Locating Element in Python - python

I am somewhat new to Python and can't for the life of me figure out why the following code isn’t pulling the element I am trying to get.
It currently returns:
for player in all_players:
player_first, player_last = player.split()
player_first = player_first.lower()
player_last = player_last.lower()
first_name_letters = player_first[:2]
last_name_letters = player_last[:5]
player_url_code = '/{}/{}{}01'.format(last_name_letters[0], last_name_letters, first_name_letters)
player_url = 'https://www.basketball-reference.com/players' + player_url_code + '.html'
print(player_url) #test
req = urlopen(player_url)
soup = bs.BeautifulSoup(req, 'lxml')
wrapper = soup.find('div', id='all_advanced_pbp')
table = wrapper.find('div', class_='table_outer_container')
for td in table.find_all('td'):
player_pbp_data.append(td.get_text())
Currently returning:
--> for td in table.find_all('td'):
player_pbp_data.append(td.get_text()) #if this works, would like to
AttributeError: 'NoneType' object has no attribute 'find_all'
Note: iterating through children of the wrapper object returns:
< div class="table_outer_container" > as part of the tree.
Thanks!

Make sure that table contains the data you expect.
For example https://www.basketball-reference.com/players/a/abdulka01.html doesn't seem to contain a div with id='all_advanced_pbp'

Try to explicitly pass the html instead:
bs.BeautifulSoup(the_html, 'html.parser')

I trie to extract data from the url you gave but it did not get full DOM. after then i try to access the page with browser with javascrip and without javascrip, i know website need javascrip to load some data. But the page like players it need not. The simple way to get dynamic data is using selenium
This is my test code
import requests
from bs4 import BeautifulSoup
from selenium import webdriver
player_pbp_data = []
def get_list(t="a"):
with requests.Session() as se:
url = "https://www.basketball-reference.com/players/{}/".format(t)
req = se.get(url)
soup = BeautifulSoup(req.text,"lxml")
with open("a.html","wb") as f:
f.write(req.text.encode())
table = soup.find("div",class_="table_wrapper setup_long long")
players = {player.a.text:"https://www.basketball-reference.com"+player.a["href"] for player in table.find_all("th",class_="left ")}
def get_each_player(player_url="https://www.basketball-reference.com/players/a/abdulta01.html"):
with webdriver.Chrome() as ph:
ph.get(player_url)
text = ph.page_source
'''
with requests.Session() as se:
text = se.get(player_url).text
'''
soup = BeautifulSoup(text, 'lxml')
try:
wrapper = soup.find('div', id='all_advanced_pbp')
table = wrapper.find('div', class_='table_outer_container')
for td in table.find_all('td'):
player_pbp_data.append(td.get_text())
except Exception as e:
print("This page dose not contain pbp")
get_each_player()

Related

BeautifulSoup and Lists

I am attempting to use beautifulsoup to look through and request each url in a txt file. So far I am able to scrape the first link for what I seek, progressing to the next url I hit an error.
This is the error I keep getting:
AttributeError: ResultSet object has no attribute 'find'. You're
probably treating a list of elements like a single element. Did you
call find_all() when you meant to call find()?
from bs4 import BeautifulSoup as bs
import requests
import constants as c
file = open(c.fvtxt)
read = file.readlines()
res = []
DOMAIN = c.vatican_domain
pdf = []
def get_soup(url):
return bs(requests.get(url).text, 'html.parser')
for link in read:
bs = get_soup(link)
res.append(bs)
soup = bs.find('div', {'class': 'headerpdf'})
pdff = soup.find('a')
li = pdff.get('href')
surl = f"{DOMAIN}{li}"
pdf.append(f"{surl}\n")
print(pdf)
It's your variable name confuses the Python interpreter, you cannot have the same name as a function and a variable at the same time, in your case 'bs'.
It should work fine if you rename the variable bs to parsed_text or something else but bs.
for link in read:
parsed_text = get_soup(link)
res.append(parsed_text)
soup = parsed_text.find('div', {'class': 'headerpdf'})
pdff = soup.find('a')
li = pdff.get('href')
print(li)
surl = f"{DOMAIN}{li}"
pdf.append(f"{surl}\n")
print(pdf)
The result:

Pulling p tags from multiple URLs

I've struggled on this for days and not sure what the issue could be - basically, I'm trying to extract the profile box data (picture below) of each link -- going through inspector, I thought I could pull the p tags and do so.
I'm new to this and trying to understand, but here's what I have thus far:
-- a code that (somewhat) succesfully pulls the info for ONE link:
import requests
from bs4 import BeautifulSoup
# getting html
url = 'https://basketball.realgm.com/player/Darius-Adams/Summary/28720'
req = requests.get(url)
soup = BeautifulSoup(req.text, 'html.parser')
container = soup.find('div', attrs={'class', 'main-container'})
playerinfo = container.find_all('p')
print(playerinfo)
I then also have a code that pulls all of the HREF tags from multiple links:
from bs4 import BeautifulSoup
import requests
def get_links(url):
links = []
website = requests.get(url)
website_text = website.text
soup = BeautifulSoup(website_text)
for link in soup.find_all('a'):
links.append(link.get('href'))
for link in links:
print(link)
print(len(links))
get_links('https://basketball.realgm.com/dleague/players/2022')
get_links('https://basketball.realgm.com/dleague/players/2021')
get_links('https://basketball.realgm.com/dleague/players/2020')
So basically, my goal is to combine these two, and get one code that will pull all of the P tags from multiple URLs. I've been trying to do it, and I'm really not sure at all why this isn't working here:
from bs4 import BeautifulSoup
import requests
def get_profile(url):
profiles = []
req = requests.get(url)
soup = BeautifulSoup(req.text, 'html.parser')
container = soup.find('div', attrs={'class', 'main-container'})
for profile in container.find_all('a'):
profiles.append(profile.get('p'))
for profile in profiles:
print(profile)
get_profile('https://basketball.realgm.com/player/Darius-Adams/Summary/28720')
get_profile('https://basketball.realgm.com/player/Marial-Shayok/Summary/26697')
Again, I'm really new to web scraping with Python but any advice would be greatly appreciated. Ultimately, my end goal is to have a tool that can scrape this data in a clean way all at once.
(Player name, Current Team, Born, Birthplace, etc).. maybe I'm doing it entirely wrong but any guidance is welcome!
You need to combine your two scripts together and make requests for each player. Try the following approach. This searches for <td> tags that have the data-td=Player attribute:
import requests
from bs4 import BeautifulSoup
def get_links(url):
data = []
req_url = requests.get(url)
soup = BeautifulSoup(req_url.content, "html.parser")
for td in soup.find_all('td', {'data-th' : 'Player'}):
a_tag = td.a
name = a_tag.text
player_url = a_tag['href']
print(f"Getting {name}")
req_player_url = requests.get(f"https://basketball.realgm.com{player_url}")
soup_player = BeautifulSoup(req_player_url.content, "html.parser")
div_profile_box = soup_player.find("div", class_="profile-box")
row = {"Name" : name, "URL" : player_url}
for p in div_profile_box.find_all("p"):
try:
key, value = p.get_text(strip=True).split(':', 1)
row[key.strip()] = value.strip()
except: # not all entries have values
pass
data.append(row)
return data
urls = [
'https://basketball.realgm.com/dleague/players/2022',
'https://basketball.realgm.com/dleague/players/2021',
'https://basketball.realgm.com/dleague/players/2020',
]
for url in urls:
print(f"Getting: {url}")
data = get_links(url)
for entry in data:
print(entry)

How to scrape data from interactive chart using python?

I have a next link which represent an exact graph I want to scrape: https://index.minfin.com.ua/ua/economy/index/svg.php?indType=1&fromYear=2010&acc=1
I'm simply can't understand is it a xml or svg graph and how to scrape data. I think I need to use bs4, requests but don't know the way to do that.
Anyone could help?
You will load HTML like this:
import requests
url = "https://index.minfin.com.ua/ua/economy/index/svg.php?indType=1&fromYear=2010&acc=1"
resp = requests.get(url)
data = resp.text
Then you will create a BeatifulSoup object with this HTML.
from bs4 import BeautifulSoup
soup = BeautifulSoup(html, features="html.parser")
After this, it is usually very subjective how to parse out what you want. The candidate codes may vary a lot. This is how I did it:
Using BeautifulSoup, I parsed all "rect"s and check if "onmouseover" exists in that rect.
rects = soup.svg.find_all("rect")
yx_points = []
for rect in rects:
if rect.has_attr("onmouseover"):
text = rect["onmouseover"]
x_start_index = text.index("'") + 1
y_finish_index = text[x_start_index:].index("'") + x_start_index
yx = text[x_start_index:y_finish_index].split()
print(text[x_start_index:y_finish_index])
yx_points.append(yx)
As you can see from the image below, I scraped onmouseover= part and get those 02.2015 155,1 parts.
Here, this is how yx_points looks like now:
[['12.2009', '100,0'], ['01.2010', '101,8'], ['02.2010', '103,7'], ...]
from bs4 import BeautifulSoup
import requests
import re
#First get all the text from the url.
url="https://index.minfin.com.ua/ua/economy/index/svg.php?indType=1&fromYear=2010&acc=1"
response = requests.get(url)
html = response.text
#Find all the tags in which the data is stored.
soup = BeautifulSoup(html, 'lxml')
texts = soup.findAll("rect")
final = []
for each in texts:
names = each.get('onmouseover')
try:
q = re.findall(r"'(.*?)'", names)
final.append(q[0])
except Exception as e:
print(e)
#The details are appended to the final variable

web-scraping using python ('NoneType' object is not iterable)

I am new to python and web-scraping. I am trying to scrape a website (link is the url). I am getting an error as "'NoneType' object is not iterable", with the last line of below code. Could anyone point what could have gone wrong?
import requests
from bs4 import BeautifulSoup
from urllib.parse import urljoin
url = 'https://labtestsonline.org/tests-index'
soup = BeautifulSoup(requests.get(url).content, 'lxml')
# Function to get hyper-links for all test components
hyperlinks = []
def parseUrl(url):
global hyperlinks
page = requests.get(url).content
soup = BeautifulSoup(page, 'lxml')
for a in soup.findAll('div',{'class':'field-content'}):
a = a.find('a')
href = urlparse.urljoin(Url,a.get('href'))
hyperlinks.append(href)
parseUrl(url)
# function to get header and common questions for each test component
def header(url):
page = requests.get(url).content
soup = BeautifulSoup(page, 'lxml')
h = []
commonquestions = []
for head in soup.find('div',{'class':'field-item'}).find('h1'):
heading = head.get_text()
h.append(heading)
for q in soup.find('div',{'id':'Common_Questions'}):
questions = q.get_text()
commonquestions.append(questions)
for i in range(0, len(hyperlinks)):
header(hyperlinks[i])
Below is the traceback error:
<ipython-input-50-d99e0af6db20> in <module>()
1 for i in range(0, len(hyperlinks)):
2 header(hyperlinks[i])
<ipython-input-49-15ac15f9071e> in header(url)
5 soup = BeautifulSoup(page, 'lxml')
6 h = []
for head in soup.find('div',{'class':'field-item'}).find('h1'):
heading = head.get_text()
h.append(heading)
TypeError: 'NoneType' object is not iterable
soup.find('div',{'class':'field-item'}).find('h1') is returning None. First check whether the function returns anything before looping over it.
Something like:
heads = soup.find('div',{'class':'field-item'}).find('h1')
if heads:
for head in heads:
# remaining code
Try this. It should solve the issues you are having at this moment. I used css selector to get the job done.
import requests
from bs4 import BeautifulSoup
from urllib.parse import urljoin
link = 'https://labtestsonline.org/tests-index'
page = requests.get(link)
soup = BeautifulSoup(page.content, 'lxml')
for a in soup.select('.field-content a'):
new_link = urljoin(link,a.get('href')) ##joining broken urls so as to reuse these
response = requests.get(new_link) ##sending another http requests
sauce = BeautifulSoup(response.text,'lxml')
for item in sauce.select("#Common_Questions .field-item"):
print(item.text)
print("<<<<<<<<<>>>>>>>>>>>")

none returned when trying to get tag value

In this html snippet from https://letterboxd.com/shesnicky/list/top-50-favourite-films/, I'm trying to go through all the different li tags and get the info from 'data-target-link' so I can then use that to create a new link that takes me to the page for that film, however every time I try and get the data it simply returns None or an error along those lines.
<li class="poster-container numbered-list-item" data-owner-rating="10"> <div class="poster film-poster really-lazy-load" data-image-width="125" data-image-height="187" data-film-slug="/film/donnie-darko/" data-linked="linked" data-menu="menu" data-target-link="/film/donnie-darko/" > <img src="https://s3.ltrbxd.com/static/img/empty-poster-125.c6227b2a.png" class="image" width="125" height="187" alt="Donnie Darko"/><span class="frame"><span class="frame-title"></span></span> </div> <p class="list-number">1</p> </li>
I'm going to be using the links to grab imgs for a twitter bot, so I tried doing this within my code:
class BotStreamer(tweepy.StreamListener):
print "Bot Streamer"
#on_data method of Tweepy’s StreamListener
#passes data from statuses to the on_status method
def on_status(self, status):
print "on status"
link = 'https://letterboxd.com/shesnicky/list/top-50-favourite-films/'
page = requests.get(link)
soup = BS(page.content, 'html.parser')
movies_ul = soup.find('ul', {'class':'poster-list -p125 -grid film-list'})
movies = []
for mov in movies_ul.find('data-film-slug'):
movies.append(mov)
rand = randint(0,51)
newLink = "https://letterboxd.com%s" % (str(movies[rand]))
newPage = requests.get(newLink)
code = BS(newPage.content, 'html.parser')
code_div = code.find\
('div', {'class':'react-component film-poster film-poster-51910 poster'})
image = code_div.find('img')
url = image.get('src')
username = status.user.screen_name
status_id = status.id
tweet_reply(url, username, status_id)
However, I kept getting errors about list being out of range, or not being able to iterate over NoneType. So I made a test prgrm just to see if I could somehow get the data:
import requests
from bs4 import BeautifulSoup as BS
link = 'https://letterboxd.com/shesnicky/list/top-50-favourite-films/'
page = requests.get(link)
soup = BS(page.content, 'html.parser')
movies_ul = soup.find('ul', {'class':'poster-list -p125 -grid film-list'})
more = movies_ul.find('li', {'class':'poster-container numbered-list-item'})
k = more.find('data-target-link')
print k
And again, all I get is None. Any help greatly appreciated.
Read doc: find() as first argument expects tag name, not attribute.
You may do
soup.find('div', {'data-target-link': True})
or
soup.find(attrs={'data-target-link': True})
Full example
import requests
from bs4 import BeautifulSoup as BS
link = 'https://letterboxd.com/shesnicky/list/top-50-favourite-films/'
page = requests.get(link)
soup = BS(page.content, 'html.parser')
all_items = soup.find_all('div', {'data-target-link': True})
for item in all_items:
print(item['data-target-link'])

Categories