currently i am printing the data.now rather than printing i want to export to
excel./csv new to python pls help.
import requests from urllib3.exceptions import InsecureRequestWarning requests.packages.urllib3.disable_warnings(InsecureRequestWarning) from bs4 import BeautifulSoup as bs def scrape_bid_data(): page_no = 1 #initial page number while True: print('Hold on creating URL to fetch data...') URL = 'https://bidplus.gem.gov.in/bidlists?bidlists&page_no=' + str(page_no) #create dynamic URL print('URL cerated: ' + URL) scraped_data = requests.get(URL,verify=False) # request to get the data soup_data = bs(scraped_data.text, 'lxml') #parse the scraped data using lxml extracted_data = soup_data.find('div',{'id':'pagi_content'}) #find divs which contains required data if len(extracted_data) == 0: # **if block** which will check the length of extracted_data if it is 0 then quit and stop the further execution of script. break else: for idx in range(len(extracted_data)): # loops through all the divs and extract and print data if(idx % 2 == 1): #get data from odd indexes only because we have required data on odd indexes bid_data = extracted_data.contents[idx].text.strip().split('\\n') print('-' * 100) print(bid_data[0]) #BID number print(bid_data[5]) #Items print(bid_data[6]) #Quantitiy Required print(bid_data[10] + bid_data[12].strip()) #Department name and address print(bid_data[16]) #Start date print(bid_data[17]) #End date print('-' * 100) page_no +=1 #increments the page number by 1 scrape_bid_data()
I think you should start by returning the extract_data object containing your data at the end of your function.
page_no = 1
def scrap_bid_data(page):
print('Hold on creating URL to fetch data...')
URL = 'https://bidplus.gem.gov.in/bidlists?bidlists&page_no=' + str(page)
print('URL cerated: ' + URL)
scraped_data = requests.get(URL,verify=False) # request to get the data
soup_data = bs(scraped_data.text, 'lxml') #parse the scraped data using lxml
extracted_data = soup_data.find('div',{'id':'pagi_content'})
return extracted_data
Then use it to create a dataframe
extract_data = scrap_bid_data(page_no)
import pandas as pd
df = pd.DataFrame(extract_data)
and then export this fataframe.
df.to_csv ('file_name_{}'.format(page_no))
here you go...
import requests
from urllib3.exceptions import InsecureRequestWarning
import csv
requests.packages.urllib3.disable_warnings(InsecureRequestWarning)
from bs4 import BeautifulSoup as bs
f = csv.writer(open('gembid.csv', 'w'))
f.writerow(['Bidnumber', 'Items', 'Quantitiy', 'Department', 'Enddate'])
def scrap_bid_data():
page_no = 1
while page_no < 911:
print('Hold on creating URL to fetch data...')
url = 'https://bidplus.gem.gov.in/bidlists?bidlists&page_no=' + str(page_no)
print('URL created: ' + url)
scraped_data = requests.get(url, verify=False)
soup_data = bs(scraped_data.text, 'lxml')
extracted_data = soup_data.find('div', {'id': 'pagi_content'})
if len(extracted_data) == 0:
break
else:
for idx in range(len(extracted_data)):
if (idx % 2 == 1):
bid_data = extracted_data.contents[idx].text.strip().split('\n')
bidno = bid_data[0].split(":")[-1]
items = bid_data[5].split(":")[-1]
qnty = int(bid_data[6].split(':')[1].strip())
dept = (bid_data[10] + bid_data[12].strip()).split(":")[-1]
edate = bid_data[17].split("End Date:")[-1]
f.writerow([bidno, items, qnty, dept, edate])
page_no=page_no+1
scrap_bid_data()
The technical post webpages of this site follow the CC BY-SA 4.0 protocol. If you need to reprint, please indicate the site URL or the original address.Any question please contact:yoyou2525@163.com.