I have already searched for an answer here and spent a long time on google, but nothing...
I've already tried opening the file with 'w' instead of 'r' or 'a' but I still can't get my code to overwrite the current results I have originally written to the CSV file. I'm basically scraping information from a website and I want to first search for a term, scrape that data, save it to the CSV file AND THEN, search for another term and scrape that data and overwrite the current CSV file with the new data.
#!/usr/bin/python3
#from pyvirtualdisplay import Display
import csv
from bs4 import BeautifulSoup
import urllib.request
def getPageSource(current_page):
hdr = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.84 Safari/537.36',
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.3',
'Accept-Encoding': 'none',
'Accept-Language': 'en-US,en;q=0.8',
'Connection': 'keep-alive'}
req = urllib.request.Request(current_page, headers=hdr)
page = urllib.request.urlopen(req)
soup = BeautifulSoup(page, "html5lib")
return(soup)
def get_length(file_path):
with open("data.csv", 'r', encoding='utf8') as csvfile:
reader = csv.reader(csvfile)
reader_list = list(reader)
return len(reader_list)
def write_data(file_path, company_name, role, full_url, date):
fieldnames = ['ID', 'Company','Role', 'URL', 'Date']
next_id = get_length(file_path)
with open(file_path, "w", encoding='utf8') as csvfile:
writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
#writer.writeheader()
writer.writerow({
"ID": next_id,
"Company": company_name,
"Role": role,
"URL": full_url,
"Date": date
})
csvfile.close()
def find_data(source):
base_url = 'https://www.irishjobs.ie'
for a in source.find_all(attrs={"itemtype" : "https://schema.org/JobPosting"}):
job_info = a.find('h2').find('a')
company_name = a.find('h3').find('a').get_text()
url = job_info['href']
full_url = (base_url + url)
role = (job_info.get_text())
date = a.find('li',class_='updated-time').get_text().replace('Updated','').strip()
write_data("data.csv", company_name, role, full_url, date)
if __name__ == '__main__':
query = input('Enter role to search: ')
source = getPageSource('https://www.irishjobs.ie/ShowResults.aspx?Keywords='+query+'&Location=102&Category=3&Recruiter=All&SortBy=MostRecent&PerPage=100')
find_data(source)
You need to keep the file open until you have finished writing it. Also, it is easier to keep a count of the rows written (using enumerate()
) than to keep trying to read the file back in:
import csv
from bs4 import BeautifulSoup
import urllib.request
def getPageSource(current_page):
hdr = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.84 Safari/537.36',
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.3',
'Accept-Encoding': 'none',
'Accept-Language': 'en-US,en;q=0.8',
'Connection': 'keep-alive'}
req = urllib.request.Request(current_page, headers=hdr)
page = urllib.request.urlopen(req)
return (BeautifulSoup(page, "html5lib"))
def find_data(source):
base_url = 'https://www.irishjobs.ie'
fieldnames = ['ID', 'Company','Role', 'URL', 'Date']
with open('data.csv', 'w', encoding='utf8', newline='') as csvfile:
writer = csv.writer(csvfile)
writer.writerow(fieldnames)
for id, a in enumerate(source.find_all(attrs={"itemtype" : "https://schema.org/JobPosting"}), start=1):
job_info = a.find('h2').find('a')
company_name = a.find('h3').find('a').get_text()
url = job_info['href']
full_url = (base_url + url)
role = (job_info.get_text())
date = a.find('li',class_='updated-time').get_text().replace('Updated','').strip()
writer.writerow([id, company_name, role, full_url, date])
if __name__ == '__main__':
query = input('Enter role to search: ')
source = getPageSource('https://www.irishjobs.ie/ShowResults.aspx?Keywords='+query+'&Location=102&Category=3&Recruiter=All&SortBy=MostRecent&PerPage=100')
find_data(source)
This would give you data.csv
starting:
ID,Company,Role,URL,Date
1,Computer Futures,Xamarin Developer,https://www.irishjobs.ie/Jobs/Xamarin-Developer-8143810.aspx,06/03/2018
2,Wallace Myers International,New Business Development Manager,https://www.irishjobs.ie/Jobs/New-Business-Development-Manager-8143989.aspx,06/03/2018
3,Reperio Human Capital Ltd,Senior Software Developer - Dublin,https://www.irishjobs.ie/Jobs/Senior-Software-Developer-Dublin-8150128.aspx,20/03/2018
In your case, it is probably easier to just use a plain csv.writer()
rather than a Dictwriter()
.
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.