Python Data Scraper - python

I wrote the following line of code
#!/usr/bin/python
#weather.scraper
from bs4 import BeautifulSoup
import urllib
def main():
"""weather scraper"""
r = urllib.urlopen("https://www.wunderground.com/history/airport/KPHL/2016/1/1/MonthlyHistory.html?&reqdb.zip=&reqdb.magic=&reqdb.wmo=&MR=1").read()
soup = BeautifulSoup(r, "html.parser")
table = soup.find_all("table", class_="responsive airport-history-summary-table")
tr = soup.find_all("tr")
td = soup.find_all("td")
print table
if __name__ == "__main__":
main()
When I print the table i get all the html (td, tr, span, etc.) as well. How can I print the content of the table (tr, td) without the html?
THANKS!

You have to use .getText() method when you want to get a content. Since find_all returns a list of elements, you have to choose one of them (td[0]).
Or you can do for example:
for tr in soup.find_all("tr"):
print '>>>> NEW row <<<<'
print '|'.join([x.getText() for x in tr.find_all('td')])
The loop above prints for each row cell next to cell.
Note that you do find all td's and all tr's your way but you probably want to get just those in table.
If you want to look for elements inside the table, you have to do this:
table.find('tr') instead of soup.find('tr) so the BeautifulSoup will be looking for trs in the table instead of whole html.
YOUR CODE MODIFIED (according to your comment that there are more tables):
#!/usr/bin/python
#weather.scraper
from bs4 import BeautifulSoup
import urllib
def main():
"""weather scraper"""
r = urllib.urlopen("https://www.wunderground.com/history/airport/KPHL/2016/1/1/MonthlyHistory.html?&reqdb.zip=&reqdb.magic=&reqdb.wmo=&MR=1").read()
soup = BeautifulSoup(r, "html.parser")
tables = soup.find_all("table")
for table in tables:
print '>>>>>>> NEW TABLE <<<<<<<<<'
trs = table.find_all("tr")
for tr in trs:
# for each row of current table, write it using | between cells
print '|'.join([x.get_text().replace('\n','') for x in tr.find_all('td')])
if __name__ == "__main__":
main()

Related

Unable to print once to get all the data altogether

I've written a script in python to scrape the tablular content from a webpage. In the first column of the main table there are the names. Some names have links to lead another page, some are just the names without any link. My intention is to parse the rows when a name has no link to another page. However, when the name has link to another page then the script will first parse the concerning rows from the main table and then follow that link to parse associated information of that name from the table located at the bottom under the title Companies. Finally, write them in a csv file.
site link
I've tried so far:
import requests
from urllib.parse import urljoin
from bs4 import BeautifulSoup
link = "https://suite.endole.co.uk/insight/company/ajax_people.php?ajax_url=ajax_people&page=1&company_number=03512889"
base = "https://suite.endole.co.uk"
res = requests.get(link)
soup = BeautifulSoup(res.text,"lxml")
for item in soup.select("table tr")[1:]:
if not item.select_one("td a[href]"):
first_table = [i.text for i in item.select("td")]
print(first_table)
else:
first_table = [i.text for i in item.select("td")]
print(first_table)
url = urljoin(base,item.select_one("td a[href]").get("href"))
resp = requests.get(url)
soup_ano = BeautifulSoup(resp.text,"lxml")
for elems in soup_ano.select(".content:contains(Companies) table tr")[1:]:
associated_info = [elem.text for elem in elems.select("td")]
print(associated_info)
My above script can do almost everything but I can't create any logic to print once rather than printing thrice to get all the data atltogether so that I can write them in a csv file.
Put all your scraped data into a list, here I've called the list associated_info then all the data is in one place & you can iterate over the list to print it out to a CSV if you like...
import requests
from urllib.parse import urljoin
from bs4 import BeautifulSoup
link = "https://suite.endole.co.uk/insight/company/ajax_people.php?ajax_url=ajax_people&page=1&company_number=03512889"
base = "https://suite.endole.co.uk"
res = requests.get(link)
soup = BeautifulSoup(res.text,"lxml")
associated_info = []
for item in soup.select("table tr")[1:]:
if not item.select_one("td a[href]"):
associated_info.append([i.text for i in item.select("td")])
else:
associated_info.append([i.text for i in item.select("td")])
url = urljoin(base,item.select_one("td a[href]").get("href"))
resp = requests.get(url)
soup_ano = BeautifulSoup(resp.text,"lxml")
for elems in soup_ano.select(".content:contains(Companies) table tr")[1:]:
associated_info.append([elem.text for elem in elems.select("td")])
print(associated_info)

Beautiful Soup scrape table with table breaks

I'm trying to scrape a table into a dataframe. My attempt only returns the table name and not the data within rows for each region.
This is what i have so far:
from bs4 import BeautifulSoup as bs4
import requests
url = 'https://www.eia.gov/todayinenergy/prices.php'
r = requests.get(url)
soup = bs4(r.text, "html.parser")
table_regions = soup.find('table', {'class': "t4"})
regions = table_regions.find_all('tr')
for row in regions:
print row
ideal outcome i'd like to get:
region | price
---------------|-------
new england | 2.59
new york city | 2.52
Thanks for any assistance.
If you check your html response (soup) you will see that the table tag you get in this line table_regions = soup.find('table', {'class': "t4"}) its closed up before the rows that contain the information you need (the ones that contain the td's with the class names: up dn d1 and s1.
So how about using the raw td tags like this:
from bs4 import BeautifulSoup as bs4
import requests
import pandas as pd
url = 'https://www.eia.gov/todayinenergy/prices.php'
r = requests.get(url)
soup = bs4(r.text, "html.parser")
a = soup.find_all('tr')
rows = []
subel = []
for tr in a[42:50]:
b = tr.find_all('td')
for td in b:
subel.append(td.string)
rows.append(subel)
subel = []
df = pd.DataFrame(rows, columns=['Region','Price_1', 'Percent_change_1', 'Price_2', 'Percent_change_2', 'Spark Spread'])
Notice that I use just the a[42:50] slice of the results because a contains all the td's of the website. You can use the rest too if you need to.

Beautiful Soup:Scrape Table Data

I'm looking to extract table data from the url below. Specifically I would like to extract the data in first column. When I run the code below, the data in the first column repeats multiple times. How can I get the values to show only once as it appears in the table?
from urllib.request import urlopen
from bs4 import BeautifulSoup
html = urlopen('http://www.pythonscraping.com/pages/page3.html').read()
soup = BeautifulSoup(html, 'lxml')
table = soup.find('table',{'id':'giftList'})
rows = table.find_all('tr')
for row in rows:
data = row.find_all('td')
for cell in data:
print(data[0].text)
Try this:
from urllib.request import urlopen
from bs4 import BeautifulSoup
html = urlopen('http://www.pythonscraping.com/pages/page3.html').read()
soup = BeautifulSoup(html, 'lxml')
table = soup.find('table',{'id':'giftList'})
rows = table.find_all('tr')
for row in rows:
data = row.find_all('td')
if (len(data) > 0):
cell = data[0]
print(cell.text)
Using requests module in combination with selectors you can try like the following as well:
import requests
from bs4 import BeautifulSoup
link = 'http://www.pythonscraping.com/pages/page3.html'
soup = BeautifulSoup(requests.get(link).text, 'lxml')
for table in soup.select('table#giftList tr')[1:]:
cell = table.select_one('td').get_text(strip=True)
print(cell)
Output:
Vegetable Basket
Russian Nesting Dolls
Fish Painting
Dead Parrot
Mystery Box

BeautifulSoup: Can't Access Info Within TD

I'm looking at the following website:
https://modules.ussquash.com/ssm/pages/leagues/League_Information.asp?leagueid=1859
I want to extract the name of each university and the href associated with it. So for the first entry, I'd like to get Stanford and https://modules.ussquash.com/ssm/pages/leagues/Team_Information.asp?id=18564
I've gotten to the point where I have all of the TDs, using BeautifulSoup. I'm just having difficulty extracting the school and its href.
Here's my attempt:
def main():
r = requests.get('https://modules.ussquash.com/ssm/pages/leagues/League_Information.asp?leagueid=1859')
data = r.text
soup = BeautifulSoup(data)
table = soup.find_all('table')[1]
rows = table.find_all('tr')[1:]
for row in rows:
cols = row.find_all('td')
print(cols)
When I try to access cols[0], I get:
IndexError: list index out of range
Any idea how to fix this would be awesome!
Thanks
The first two tr's are in the thead which have no td tags, you want to skip the first two tr's:
rows = table.find_all('tr')[2:]
To get what you want, we can simplify using css selectors:
table = soup.find_all('table', limit=2)[1]
# skip first two tr's
rows = table.select("tr + tr + tr")
for row in rows:
# anchor we want is inside the first td
a = row.select_one("td a") # or a = row.find("td").a
print(a.text,a["href"])
Also the href is a relative path so you need to join it to a base url:
import requests
from bs4 import BeautifulSoup
from urllib.urlparse import urljoin
def main():
base = "https://modules.ussquash.com/ssm/pages/leagues/"
r = requests.get('https://modules.ussquash.com/ssm/pages/leagues/League_Information.asp?leagueid=1859')
data = r.text
soup = BeautifulSoup(data)
table = soup.find_all('table', limit=2)[1]
# skip first two tr's
rows = table.select("tr + tr + tr")
for row in rows:
a = row.select_one("td a")
print(a.text, urljoin(base, a["href"]))

I do not quite understand how to parse the Yahoo NHL Page

Here is my code so far:
from bs4 import BeautifulSoup
from urllib.request import urlopen
url = urlopen("http://sports.yahoo.com/nhl/scoreboard?d=2013-04-01")
content = url.read()
soup = BeautifulSoup(content)
print (soup.prettify)
table = soup.find('table')
rows = table.findAll('tr')
for tr in rows:
cols = tr.findAll('td')
for td in cols:
text = td.findAll('yspscores')
for yspscores in td:
print (yspscores)
The problem I've been having is that the HTML for that yahoo page has the table data in this context: <td class="yspscores">
I do not quite understand how to reference it in my code. My goal is to print out the scores and name of the teams that the score corresponds to.
You grabbed the first table, but there is more than one table on that page. In fact, there are 46 tables.
You want to find the tables with the scores class:
for table in soup.find_all('table', class_='scores'):
for row in table.find_all('tr'):
for cell in row.find_all('td', class_='yspscores'):
print(cell.text)
Note that searching for a specific class is done with the class_ keyword argument.

Categories

Resources