How to extract tables from different pages? (python) - python-3.x

I want to extract the tables of first serval pages on http://
The tables have been scraped by the code below and they are in a list,
import urllib
from bs4 import BeautifulSoup
base_url = "http://"
url_list = ["{}?page={}".format(base_url, str(page)) for page in range(1, 21)]
mega = []
for url in url_list:
html = urllib.request.urlopen(url).read()
soup = BeautifulSoup(html, 'html.parser')
table = soup.find('table', {'class': 'table table-bordered table-striped table-hover'})
mega.append(table)
Because it is a list and cannot use 'soup find_all' to extract the items I want so I converted them into bs4.element.Tag to further serach the items
for i in mega:
trs = table.find_all('tr')[1:]
rows = list()
for tr in trs:
rows.append([td.text.replace('\n', '').replace('\xa0', '').replace('\t', '').strip().rstrip() for td in tr.find_all('td')])
rows
The rows only extract the tables of last page. What is the problem of my codes so the previous 19 tables are not been extracted? Thanks!
The length of the two items are not equivalent.I used for i in meaga to obetain i.
len(mega) = 20
len(i) = 5

The problem is pretty simple. In this for loop:
for i in mega:
trs = table.find_all('tr')[1:]
rows = list()
for tr in trs:
rows.append([td.text.replace('\n', '').replace('\xa0', '').replace('\t', '').strip().rstrip() for td in tr.find_all('td')])
You initialize rows = list() in the for loop. So you loop 21 times, but you also empty the list 20 times.
So you need to have it like this:
rows = list()
for i in mega:
trs = table.find_all('tr')[1:]
for tr in trs:
rows.append([td.text.replace('\n', '').replace('\xa0', '').replace('\t', '').strip().rstrip() for td in tr.find_all('td')])

Related

extracting columns contents only so that all columns for each row are in the same row using Python's BeautifulSoup

I have the following python snippet in Jupyter Notebooks that works.
The challenge I have is to extract just the rows of columnar data only
Here's the snippet:
from bs4 import BeautifulSoup as bs
import pandas as pd
page = requests.get("http://lib.stat.cmu.edu/datasets/boston")
page
soup = bs(page.content)
soup
allrows = soup.find_all("p")
print(allrows)
I'm a little unclear of what you are after but I think it's each individual row of data from URL provided.
I couldn't find a way to use beautiful soup to parse the data you are after but did find a way to separate the rows using .split()
from bs4 import BeautifulSoup as bs
import pandas as pd
import requests
page = requests.get("http://lib.stat.cmu.edu/datasets/boston")
soup = bs(page.content)
allrows = soup.find_all("p")
text = soup.text # turn soup into text
text_split = text.split('\n\n') # split the page into 3 sections
data = text_split[2] # rows of data
# create df column titles using variable titles on page
col_titles = text_split[1].split('\n')
df = pd.DataFrame(columns=range(14))
df.columns = col_titles[1:]
# 'try/except' to catch end of index,
# loop throw text data building complete rows
try:
complete_row = []
n1 = 0 #used to track index
n2 = 1
rows = data.split('\n')
for el in range(len(rows)):
full_row = rows[n1] + rows[n2]
complete_row.append(full_row)
n1 = n1 + 2
n2 = n2 + 2
except IndexError:
print('end of loop')
# loop through rows of data, clean whitespace and append to df
for row in complete_row:
elem = row.split(' ')
df.loc[len(df)] = [el for el in elem if el]
#fininshed dataframe
df

How to assign bs4 strings to pandas dataframe in for loop?

I have an HTML string that I am successfully able to use beautifulsoup4 on to extract the elements I need.
the HTML strings are in a list and I am wanting to extract only certain elements out of the strings and assign them to dataframe columns.
Current code:
import pandas as pd
from bs4 import BeautifulSoup
lst = [ <html>,<html>]
df = pd.DataFrame()
for i in lst:
soup = BeautifulSoup(i)
for link in soup.find_all('a'):
df['links'] = str(link.get('href'))
#print(link.get('href'))
#get all text messages
soup.find_all('p')
df['messages'] = str(soup.find_all('p'))
#get author name
soup.find_all(class_="author--name")
df['author'] = str(soup.find_all(class_="author--name"))
#get username
soup.find_all(class_= "author--username")
df['username'] = str(soup.find_all(class_= "author--username"))
All the soup lines of code are producing the data I need, but why is the dataframe not assigning the string values to the dataframe columns?
I can see that from an empty dataframe, the code creates the new columns but there are no values.
What am I doing wrong?
The solution was to wrap the assignments in brackets like so:
for i in lst:
df = pd.DataFrame()
soup = BeautifulSoup(i)
#print(soup)
for link in soup.find_all('a'):
df['links'] = [str(link.get('href'))]
#print(link.get('href'))
#get all text messages
soup.find_all('p')
df['messages'] = [str(soup.find_all('p'))]
#get author name
soup.find_all(class_="author--name")
df['author'] = [str(soup.find_all(class_="author--name"))]
#get username
soup.find_all(class_= "author--username")
df['username'] = [str(soup.find_all(class_= "author--username"))] text messages
soup.find_all('p')
df['messages'] = str(soup.find_all('p'))
#get author name
soup.find_all(class_="author--name")
df['author'] = str(soup.find_all(class_="author--name"))
#get username
soup.find_all(class_= "author--username")
df['username'] = str(soup.find_all(class_= "author--username"))

BeautifulSoup, Requests, Dataframe, extracting from <SPAN> and Saving to Excel

Python novice here again! 2 questions:
1) Instead of saving to multiple tabs (currently saving each year to a tab named after the year) how can I save all this data into one sheet in excel called "summary".
2) ('div',class_="sidearm-schedule-game-result") returns the format "W, 1-0". How can I split the "W, 1-0" into two columns, one containing "W" and the next column containing "1-0".
Thanks so much
import requests
import pandas as pd
from pandas import ExcelWriter
from bs4 import BeautifulSoup
import openpyxl
import csv
year_id = ['2003','2004','2005','2006','2007','2008','2009','2010','2011','2012','2013','2014','2015','2016','2017','2018','2019']
lehigh_url = 'https://lehighsports.com/sports/mens-soccer/schedule/'
results = []
with requests.Session() as req:
for year in range(2003, 2020):
print(f"Extracting Year# {year}")
url = req.get(f"{lehigh_url}{year}")
if url.status_code == 200:
soup = BeautifulSoup(url.text, 'lxml')
rows = soup.find_all('div',class_="sidearm-schedule-game-row flex flex-wrap flex-align-center row")
sheet = pd.DataFrame()
for row in rows:
date = row.find('div',class_="sidearm-schedule-game-opponent-date").text.strip()
name = row.find('div',class_="sidearm-schedule-game-opponent-name").text.strip()
opp = row.find('div',class_="sidearm-schedule-game-opponent-text").text.strip()
conf = row.find('div',class_="sidearm-schedule-game-conference-conference").text.strip()
try:
result = row.find('div',class_="sidearm-schedule-game-result").text.strip()
except:
result = ''
df = pd.DataFrame([[year,date,name,opp,conf,result]], columns=['year','date','opponent','list','conference','result'])
sheet = sheet.append(df,sort=True).reset_index(drop=True)
results.append(sheet)
def save_xls(list_dfs, xls_path):
with ExcelWriter(xls_path) as writer:
for n, df in enumerate(list_dfs):
df.to_excel(writer,'%s' %year_id[n],index=False,)
writer.save()
save_xls(results,'lehigh.xlsx')
Instead of creating a list of dataframes, you can append each sheet into 1 dataframe and write that to file with pandas. Then to split into 2 columns, just use .str.split() and split on the comma.
import requests
import pandas as pd
from bs4 import BeautifulSoup
year_id = ['2019','2018','2017','2016','2015','2014','2013','2012','2011','2010','2009','2008','2007','2006','2005','2004','2003']
results = pd.DataFrame()
for year in year_id:
url = 'https://lehighsports.com/sports/mens-soccer/schedule/' + year
print (url)
lehigh = requests.get(url).text
soup = BeautifulSoup(lehigh,'lxml')
rows = soup.find_all('div',class_="sidearm-schedule-game-row flex flex-wrap flex-align-center row")
sheet = pd.DataFrame()
for row in rows:
date = row.find('div',class_="sidearm-schedule-game-opponent-date").text.strip()
name = row.find('div',class_="sidearm-schedule-game-opponent-name").text.strip()
opp = row.find('div',class_="sidearm-schedule-game-opponent-text").text.strip()
conf = row.find('div',class_="sidearm-schedule-game-conference-conference").text.strip()
try:
result = row.find('div',class_="sidearm-schedule-game-result").text.strip()
except:
result = ''
df = pd.DataFrame([[year,date,name,opp,conf,result]], columns=['year','date','opponent','list','conference','result'])
sheet = sheet.append(df,sort=True).reset_index(drop=True)
results = results.append(sheet, sort=True).reset_index(drop=True)
results['result'], results['score'] = results['result'].str.split(',', 1).str
results.to_excel('lehigh.xlsx')

How can I use Python to scrape a multipage table and export to a CSV file?

i am trying to scrape a table that spans multiple pages and export to a csv file. only one line of data seems to get exported and it is jumbled up.
I have looked on the web and tried many iterations and very frustrated now. As you can tell from code I am a novice at coding!
import bs4 as bs
import urllib.request
import pandas as pd
import csv
max_page_num = 14
max_page_dig = 1 # number of digits in the page number
with open('result.csv',"w") as f:
f.write("Name, Gender, State, Position, Grad, Club/HS, Rating, Commitment \n")
for i in range(0, max_page_num):
page_num = (max_page_dig - len(str(i))) * "0" +str(i) #gives a string in the format of 1, 01 or 001, 005 etc
print(page_num)
source = "https://www.topdrawersoccer.com/search/?query=&divisionId=&genderId=m&graduationYear=2020&positionId=0&playerRating=&stateId=All&pageNo=" + page_num + "&area=commitments"
print(source)
url = urllib.request.urlopen(source).read()
soup = bs.BeautifulSoup(url,'lxml')
table = soup.find('table')
table_rows = table.find_all('tr')
for tr in table_rows:
td = tr.find_all('td')
row = [i.text for i in td]
#final = row.strip("\n")
#final = row.replace("\n","")
with open('result.csv', 'a') as f:
f.write(row)
It seems when I write to csv it overwrites previous ones. It also pastes it on one line and the players name is concatenated with the school name . Thanks for any and all help.
I think you have a problem with your inside for loop. Try re-writing it as
with open('result.csv', 'a') as f:
for tr in table_rows:
td = tr.find_all('td')
row = [i.text for i in td]
f.write(row)
and see if it works.
More generally, this can probably be done more simply by using pandas. Try changing your for loop to:
for i in range(0, max_page_num):
page_num = ...
source = ....
df = pd.read_html(source)
df.to_csv('results.csv', header=False, index=False, mode='a') #'a' should append each table to the csv file, instead of overwriting it.

Socket Error Exceptions in Python when Scraping

I am trying to learn scraping,
I use exceptions lower down in the code to pass through errors because they dont affect the writing of data to csv
I keep getting a "socket.gaierror" but in the handling of that there is a "urllib.error.URLError" in the handling of that I get "NameError: name 'socket' is not defined" which seems circuitous
I kind of understand that using these exceptions may not be the best way to run the code but I cant seem to get past these errors and I dont know a way around or how to fix the errors.
If you have any suggestions outside of fixing the error exceptions that would be greatly appreciated as well.
import csv
from urllib.request import urlopen
from urllib.error import HTTPError
from bs4 import BeautifulSoup
base_url = 'http://www.fangraphs.com/' # used in line 27 for concatenation
years = ['2017','2016','2015'] # for enough data to run tests
#Getting Links for letters
player_urls = []
data = urlopen('http://www.fangraphs.com/players.aspx')
soup = BeautifulSoup(data, "html.parser")
for link in soup.find_all('a'):
if link.has_attr('href'):
player_urls.append(base_url + link['href'])
#Getting Alphabet Links
test_for_playerlinks = 'players.aspx?letter='
player_alpha_links = []
for i in player_urls:
if test_for_playerlinks in i:
player_alpha_links.append(i)
# Getting Player Links
ind_player_urls = []
for l in player_alpha_links:
data = urlopen(l)
soup = BeautifulSoup(data, "html.parser")
for link in soup.find_all('a'):
if link.has_attr('href'):
ind_player_urls.append(link['href'])
#Player Links
jan = 'statss.aspx?playerid'
players = []
for j in ind_player_urls:
if jan in j:
players.append(j)
# Building Pitcher List
pitcher = 'position=P'
pitchers = []
pos_players = []
for i in players:
if pitcher in i:
pitchers.append(i)
else:
pos_players.append(i)
# Individual Links to Different Tables Sorted by Base URL differences
splits = 'http://www.fangraphs.com/statsplits.aspx?'
game_logs = 'http://www.fangraphs.com/statsd.aspx?'
split_pp = []
gamel = []
years = ['2017','2016','2015']
for i in pos_players:
for year in years:
split_pp.append(splits + i[12:]+'&season='+ year)
gamel.append(game_logs+ i[12:] + '&type=&gds=&gde=&season=' + year)
split_pitcher = []
gl_pitcher = []
for i in pitchers:
for year in years:
split_pitcher.append(splits + i[12:]+'&season=' + year)
gl_pitcher.append(game_logs + i[12:] + '&type=&gds=&gde=&season=' + year)
# Splits for Pitcher Data
row_sp = []
rows_sp = []
try:
for i in split_pitcher:
sauce = urlopen(i)
soup = BeautifulSoup(sauce, "html.parser")
table1 = soup.find_all('strong', {"style":"font-size:15pt;"})
row_sp = []
for name in table1:
nam = name.get_text()
row_sp.append(nam)
table = soup.find_all('table', {"class":"rgMasterTable"})
for h in table:
he = h.find_all('tr')
for i in he:
td = i.find_all('td')
for j in td:
row_sp.append(j.get_text())
rows_sp.append(row_sp)
except(RuntimeError, TypeError, NameError, URLError, socket.gaierror):
pass
try:
with open('SplitsPitchingData2.csv', 'w') as fp:
writer = csv.writer(fp)
writer.writerows(rows_sp)
except(RuntimeError, TypeError, NameError):
pass
I'm guessing your main problem was that you - without any sleep what so ever - queried the site for a huge amount of invalid urls (you create 3 urls for the years 2015-2017 for 22880 pitchers in total, but most of these do not fall within that scope so you have tens of thousands of queries that return errors).
I'm surprised your IP wasn't banned by site admin. That said: It would be better to do some filtering so you avoid all those error queries...
The filter I applied is not perfect. It checks if the years in the list either appears in the start or end the years given on the site (e.g. '2004 - 2015'). This also creates error links but no way near the amount the original script did.
In code it could look like this:
from urllib.request import urlopen
from bs4 import BeautifulSoup
from time import sleep
import csv
base_url = 'http://www.fangraphs.com/'
years = ['2017','2016','2015']
# Getting Links for letters
letter_links = []
data = urlopen('http://www.fangraphs.com/players.aspx')
soup = BeautifulSoup(data, "html.parser")
for link in soup.find_all('a'):
try:
link = base_url + link['href']
if 'players.aspx?letter=' in link:
letter_links.append(link)
except:
pass
print("[*] Retrieved {} links. Now fetching content for each...".format(len(letter_links)))
# the data resides in two different base_urls:
splits_url = 'http://www.fangraphs.com/statsplits.aspx?'
game_logs_url = 'http://www.fangraphs.com/statsd.aspx?'
# we need (for some reason) players in two lists - pitchers_split and pitchers_game_log - and the rest of the players in two different, pos_players_split and pis_players_game_log
pos_players_split = []
pos_players_game_log = []
pitchers_split = []
pitchers_game_log = []
# and if we wanted to do something with the data from the letter_queries, lets put that in a list for safe keeping:
ind_player_urls = []
current_letter_count = 0
for link in letter_links:
current_letter_count +=1
data = urlopen(link)
soup = BeautifulSoup(data, "html.parser")
trs = soup.find('div', class_='search').find_all('tr')
for player in trs:
player_data = [tr.text for tr in player.find_all('td')]
# To prevent tons of queries to fangraph with invalid years - check if elements from years list exist with the player stat:
if any(year in player_data[1] for year in years if player_data[1].startswith(year) or player_data[1].endswith(year)):
href = player.a['href']
player_data.append(base_url + href)
# player_data now looks like this:
# ['David Aardsma', '2004 - 2015', 'P', 'http://www.fangraphs.com/statss.aspx?playerid=1902&position=P']
ind_player_urls.append(player_data)
# build the links for game_log and split
for year in years:
split = '{}{}&season={}'.format(splits_url,href[12:],year)
game_log = '{}{}&type=&gds=&gde=&season={}'.format(game_logs_url, href[12:], year)
# checking if the player is pitcher or not. We're append both link and name (player_data[0]), so we don't need to extract name later on
if 'P' in player_data[2]:
pitchers_split.append([player_data[0],split])
pitchers_game_log.append([player_data[0],game_log])
else:
pos_players_split.append([player_data[0],split])
pos_players_game_log.append([player_data[0],game_log])
print("[*] Done extracting data for players for letter {} out of {}".format(current_letter_count, len(letter_links)))
sleep(2)
# CONSIDER INSERTING CSV-PART HERE....
# Extracting and writing pitcher data to file
with open('SplitsPitchingData2.csv', 'a') as fp:
writer = csv.writer(fp)
for i in pitchers_split:
try:
row_sp = []
rows_sp = []
# all elements in the pitchers_split are lists. Player name is i[1]
data = urlopen(i[1])
soup = BeautifulSoup(data, "html.parser")
# append name to row_sp from pitchers_split
row_sp.append(i[0])
# the page has 3 tables with the class rgMasterTable, the first i Standard, the second Advanced, the 3rd Batted Ball
# we're only grabbing standard
table_standard = soup.find_all('table', {"class":"rgMasterTable"})[0]
trs = table_standard.find_all('tr')
for tr in trs:
td = tr.find_all('td')
for content in td:
row_sp.append(content.get_text())
rows_sp.append(row_sp)
writer.writerows(rows_sp)
sleep(2)
except Exception as e:
print(e)
pass
Since I'm not sure precisely how you wanted the data formatted on output you need some work on that.
If you want to avoid waiting for all letter_links to be extracted before you retrieve the actual pitcher stats (and fine tune your output) you can move the csv writer part up, so it runs as a part of the letter loop. If you do this don't forget to empty the pitchers_split list before grabbing another letter_link...

Resources