I am just a beginner at Python.
I am trying to scrape data from a site and have managed to write the below code.
However, I am not sure how to proceed ahead as I am unable to get the href tags so that I can go to each listing & get the data. I am also not very well aware of HTML Tags, so I suspect that I have not identified the tags properly.
Here is my code :
import requests
from bs4 import BeautifulSoup
urls = []
for i in range(1,5):
pages = "https://directory.singaporefintech.org/?p={0}&category=0&zoom=15&is_mile=0&directory_radius=0&view=list&hide_searchbox=0&hide_nav=0&hide_nav_views=0&hide_pager=0&featured_only=0&feature=1&perpage=20&sort=random".format(i)
urls.append(pages)
Data = []
for info in urls:
page = requests.get(info)
soup = BeautifulSoup(page.content, 'html.parser')
links = soup.find_all('a', attrs ={'class' :'sabai-directory-title'})
hrefs = [link['href'] for link in links]
The above code is producing hrefs as a blank list.
Any help would be highly appreciated!!
Thanks!!!
Code is fine, the class that you're looking for just doesn't exist on those pages. For example, substituted sabai-directory-title class with comment-reply-link after inspecting https://directory.singaporefintech.org/hello-world/?category=0&zoom=15&is_mile=0&directory_radius=0&view=list&hide_searchbox=0&hide_nav=0&hide_nav_views=0&hide_pager=0&featured_only=0&feature=1&perpage=20&sort=random and got results when i added print statements
You can scrap links using CSS selector. Selector div.sabai-directory-title a will find any <a> tags inside <div> tag with class sabai-directory-title (I updated the URL, yours was giving me error pages):
from bs4 import BeautifulSoup
import requests
from pprint import pprint
r = requests.get('https://directory.singaporefintech.org/')
soup = BeautifulSoup(r.text, 'lxml')
hrefs = [a['href'] for a in soup.select('div.sabai-directory-title a')]
pprint(hrefs)
This will print:
['https://directory.singaporefintech.org/directory/listing/silent-eight',
'https://directory.singaporefintech.org/directory/listing/incomlend',
'https://directory.singaporefintech.org/directory/listing/bizgrow',
'https://directory.singaporefintech.org/directory/listing/makerscut',
'https://directory.singaporefintech.org/directory/listing/soho-fintech',
'https://directory.singaporefintech.org/directory/listing/dxmarkets',
'https://directory.singaporefintech.org/directory/listing/fundrevo',
'https://directory.singaporefintech.org/directory/listing/money4money',
'https://directory.singaporefintech.org/directory/listing/onelyst',
'https://directory.singaporefintech.org/directory/listing/hearti-lab',
'https://directory.singaporefintech.org/directory/listing/samurai-fintech-singapore-pte-ltd',
'https://directory.singaporefintech.org/directory/listing/ceo-1',
'https://directory.singaporefintech.org/directory/listing/arcadier',
'https://directory.singaporefintech.org/directory/listing/plmp-fintech-pte-ltd',
'https://directory.singaporefintech.org/directory/listing/cash-in-asia',
'https://directory.singaporefintech.org/directory/listing/grc-systems',
'https://directory.singaporefintech.org/directory/listing/sendexpense',
'https://directory.singaporefintech.org/directory/listing/jinjerjade',
'https://directory.singaporefintech.org/directory/listing/hatcher',
'https://directory.singaporefintech.org/directory/listing/fintech-consortium']
Hi I have made few changes to code:
import requests
from bs4 import BeautifulSoup
from pprint import pprint
urls = []
for i in range(1,5):
pages = "https://directory.singaporefintech.org"
urls.append(pages)
Data = []
hrefs = []
for info in urls:
page = requests.get(info)
soup = BeautifulSoup(page.content, 'html.parser')
links = soup.find_all('div', attrs ={'class' :'sabai-directory-title'})
for link in links:
Data.extend([a['href'].encode('ascii') for a in link.find_all('a', href=True) if a.text])
pprint (Data)
output:
['https://directory.singaporefintech.org/directory/listing/silent-eight',
'https://directory.singaporefintech.org/directory/listing/moolahsense',
'https://directory.singaporefintech.org/directory/listing/myfinb',
'https://directory.singaporefintech.org/directory/listing/wefinance',
'https://directory.singaporefintech.org/directory/listing/quber',
'https://directory.singaporefintech.org/directory/listing/ayondo-asia-pte-ltd',
'https://directory.singaporefintech.org/directory/listing/ceo-1',
'https://directory.singaporefintech.org/directory/listing/acekards',
'https://directory.singaporefintech.org/directory/listing/paper-ink-pte-ltd',
'https://directory.singaporefintech.org/directory/listing/alpha-payments-cloud',
'https://directory.singaporefintech.org/directory/listing/samurai-fintech-singapore-pte-ltd',
'https://directory.singaporefintech.org/directory/listing/corris-asset-management-pte-ltd',
'https://directory.singaporefintech.org/directory/listing/fundmylife',
'https://directory.singaporefintech.org/directory/listing/mooments',
'https://directory.singaporefintech.org/directory/listing/venture-capital-network-pte-ltd',
'https://directory.singaporefintech.org/directory/listing/junotele_',
'https://directory.singaporefintech.org/directory/listing/mobilecover',
'https://directory.singaporefintech.org/directory/listing/cherrypay',
'https://directory.singaporefintech.org/directory/listing/toast',
'https://directory.singaporefintech.org/directory/listing/cashdab',
'https://directory.singaporefintech.org/directory/listing/silent-eight',
'https://directory.singaporefintech.org/directory/listing/moolahsense',
'https://directory.singaporefintech.org/directory/listing/myfinb',
'https://directory.singaporefintech.org/directory/listing/wefinance',
'https://directory.singaporefintech.org/directory/listing/quber',
'https://directory.singaporefintech.org/directory/listing/ayondo-asia-pte-ltd',
'https://directory.singaporefintech.org/directory/listing/ceo-1',
'https://directory.singaporefintech.org/directory/listing/acekards',
'https://directory.singaporefintech.org/directory/listing/paper-ink-pte-ltd',
'https://directory.singaporefintech.org/directory/listing/alpha-payments-cloud',
'https://directory.singaporefintech.org/directory/listing/samurai-fintech-singapore-pte-ltd',
'https://directory.singaporefintech.org/directory/listing/corris-asset-management-pte-ltd',
'https://directory.singaporefintech.org/directory/listing/fundmylife',
'https://directory.singaporefintech.org/directory/listing/mooments',
'https://directory.singaporefintech.org/directory/listing/venture-capital-network-pte-ltd',
'https://directory.singaporefintech.org/directory/listing/junotele_',
'https://directory.singaporefintech.org/directory/listing/mobilecover',
'https://directory.singaporefintech.org/directory/listing/cherrypay',
'https://directory.singaporefintech.org/directory/listing/toast',
'https://directory.singaporefintech.org/directory/listing/cashdab',
'https://directory.singaporefintech.org/directory/listing/silent-eight',
'https://directory.singaporefintech.org/directory/listing/moolahsense',
'https://directory.singaporefintech.org/directory/listing/myfinb',
'https://directory.singaporefintech.org/directory/listing/wefinance',
'https://directory.singaporefintech.org/directory/listing/quber',
'https://directory.singaporefintech.org/directory/listing/ayondo-asia-pte-ltd',
'https://directory.singaporefintech.org/directory/listing/ceo-1',
'https://directory.singaporefintech.org/directory/listing/acekards',
'https://directory.singaporefintech.org/directory/listing/paper-ink-pte-ltd',
'https://directory.singaporefintech.org/directory/listing/alpha-payments-cloud',
'https://directory.singaporefintech.org/directory/listing/samurai-fintech-singapore-pte-ltd',
'https://directory.singaporefintech.org/directory/listing/corris-asset-management-pte-ltd',
'https://directory.singaporefintech.org/directory/listing/fundmylife',
'https://directory.singaporefintech.org/directory/listing/mooments',
'https://directory.singaporefintech.org/directory/listing/venture-capital-network-pte-ltd',
'https://directory.singaporefintech.org/directory/listing/junotele_',
'https://directory.singaporefintech.org/directory/listing/mobilecover',
'https://directory.singaporefintech.org/directory/listing/cherrypay',
'https://directory.singaporefintech.org/directory/listing/toast',
'https://directory.singaporefintech.org/directory/listing/cashdab',
'https://directory.singaporefintech.org/directory/listing/silent-eight',
'https://directory.singaporefintech.org/directory/listing/moolahsense',
'https://directory.singaporefintech.org/directory/listing/myfinb',
'https://directory.singaporefintech.org/directory/listing/wefinance',
'https://directory.singaporefintech.org/directory/listing/quber',
'https://directory.singaporefintech.org/directory/listing/ayondo-asia-pte-ltd',
'https://directory.singaporefintech.org/directory/listing/ceo-1',
'https://directory.singaporefintech.org/directory/listing/acekards',
'https://directory.singaporefintech.org/directory/listing/paper-ink-pte-ltd',
'https://directory.singaporefintech.org/directory/listing/alpha-payments-cloud',
'https://directory.singaporefintech.org/directory/listing/samurai-fintech-singapore-pte-ltd',
'https://directory.singaporefintech.org/directory/listing/corris-asset-management-pte-ltd',
'https://directory.singaporefintech.org/directory/listing/fundmylife',
'https://directory.singaporefintech.org/directory/listing/mooments',
'https://directory.singaporefintech.org/directory/listing/venture-capital-network-pte-ltd',
'https://directory.singaporefintech.org/directory/listing/junotele_',
'https://directory.singaporefintech.org/directory/listing/mobilecover',
'https://directory.singaporefintech.org/directory/listing/cherrypay',
'https://directory.singaporefintech.org/directory/listing/toast',
'https://directory.singaporefintech.org/directory/listing/cashdab']
Is this the data output you are expecting.
Hope it helps!!
Related
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)
So I am trying to extract all the article URLs from this link.
However I only get ['https://mn.usembassy.gov/mn/2020-naadam-mn/', 'https://mn.usembassy.gov/mn/06272020-presidential-proclamation-mn/', 'https://mn.usembassy.gov/mn/pr-060320-mn/', 'https://mn.usembassy.gov/mn/dv-2021-status-check-mn/', 'https://mn.usembassy.gov/mn/pr-050120-mn/']
below is my code currently.
The website has 52 pages and I am trying to get all the URLs, why does it only give me a few URLs instead of all the URLS?
import requests
from bs4 import BeautifulSoup
url = 'https://mn.usembassy.gov/mn/news-events-mn/'
reqs = requests.get(url)
soup = BeautifulSoup(reqs.text, 'lxml')
urls = []
for h in soup.find_all('h2'):
a = h.find('a')
urls.append(a.attrs['href'])
print(urls)
The page contains only 5 links to articles, you need to go to next page to load next 5 links. This script will get all links from the page:
import requests
from bs4 import BeautifulSoup
url = 'https://mn.usembassy.gov/mn/news-events-mn/page/{page}/'
urls = []
for page in range(1, 53):
soup = BeautifulSoup(requests.get(url.format(page=page)).content, 'html.parser')
for h in soup.find_all('h2'):
a = h.find('a')
print(a['href'])
urls.append(a.attrs['href'])
from pprint import pprint
pprint(urls)
Prints:
https://mn.usembassy.gov/mn/2020-naadam-mn/
https://mn.usembassy.gov/mn/06272020-presidential-proclamation-mn/
https://mn.usembassy.gov/mn/pr-060320-mn/
https://mn.usembassy.gov/mn/dv-2021-status-check-mn/
https://mn.usembassy.gov/mn/pr-050120-mn/
https://mn.usembassy.gov/mn/pr-042320-mca-website-mn/
https://mn.usembassy.gov/mn/2020-pr-us-mongolia-cpc-mn/
https://mn.usembassy.gov/mn/lead-2020-in-country-mn/
https://mn.usembassy.gov/mn/press-release-usaid-mar-24-2020-mn/
https://mn.usembassy.gov/mn/event-suspension-of-nonimmigrant-and-immigrant-visa-services-due-to-local-covid-19-related-preventative-measures-and-limited-staffing-mn/
https://mn.usembassy.gov/mn/2020-best-program-pr-mn/
https://mn.usembassy.gov/mn/2020-ncov-info-for-visa-mn/
...and so on.
I have this code
import requests
from bs4 import BeautifulSoup
result = requests.get("http://www.cvbankas.lt/")
src = result.content
soup = BeautifulSoup(src, 'lxml')
urls = []
for article_tag in soup.find_all("article"):
a_tag = article_tag.find('a')
urls.append(a_tag.attrs['href'])
div_tag = article_tag.find('span')
urls.append(div_tag.attrs['class'])
print(urls)
Can anyone explane me how to get the data marked in red?
You can get span with the class label "salary_amount"
salary_object = article_tag.find("span", class_= "salary_amount")
and then extract the text with the .text attribute of the created object.
I'm trying to scrape the urls of the ads on "Marktplaats" website (link is provided below).
As you can see I'm looking for 30 URLs. These URLs are placed inside a 'href' field and all start with "/a/auto-s/". Unfortunately, I only keep getting the first few URLs. I found out that on this sites all the data is places within "<li class = "mp-Listing mp-Listing--list-item"> ... </li>". Does anyone have an idea how to fix it? (you can see that you won't find all the URLs of the ads when you run my code)
Link:
https://www.marktplaats.nl/l/auto-s/#f:10882,10898|PriceCentsTo:350000|constructionYearFrom:2001|offeredSince:TODAY|searchInTitleAndDescription:true
My code:
import requests
from bs4 import BeautifulSoup
url = "https://www.marktplaats.nl/l/auto-s/#f:10882,10898|PriceCentsTo:350000|constructionYearFrom:2001|offeredSince:TODAY|searchInTitleAndDescription:true"
response = requests.get(url)
soup = BeautifulSoup(response.text, 'html.parser')
url_list = soup.find_all(class_ = 'mp-Listing mp-Listing--list-item')
print(url_list)
You can try something like this:
import requests
from bs4 import BeautifulSoup
def parse_links(url):
links = []
response = requests.get(url)
soup = BeautifulSoup(response.text, 'html.parser')
for li in soup.find_all(class_="mp-Listing mp-Listing--list-item"):
links.append(li.a.get('href'))
return links
url = "https://www.marktplaats.nl/l/auto-s/#f:10882,10898|PriceCentsTo:350000|constructionYearFrom:2001|offeredSince:TODAY|searchInTitleAndDescription:true"
links = parse_links(url)
print('\n'.join(map(str, links)))
Output
/a/auto-s/oldtimers/a1302359148-allis-chalmers-ed40-1965.html
/a/auto-s/bestelauto-s/a1258166221-opel-movano-2-3-cdti-96kw-2018.html
/a/auto-s/oldtimers/a1302359184-chevrolet-biscayne-bel-air-1960.html
/a/auto-s/renault/a1240974413-ruim-aanbod-rolstoelauto-s-www-autoland-nl.html
/a/auto-s/volkswagen/m1457703674-golf-6-1-2tsi-comfortline-bluemotion-77kw-2de-eigenaar.html
/a/auto-s/peugeot/m1457564187-peugeot-208-1-6-e-hdi-68kw-92pk-5-d-2014-zwart.html
/a/auto-s/volkswagen/m1457124365-volkswagen-touareg-3-2-v6-177kw-4motion-aut-2004-grijs.html
/a/auto-s/volkswagen/m1456753596-volkswagen-golf-vii-2-0-tdi-highline-150pk-xenon-trekhaak.html
/a/auto-s/bestelauto-s/a1001658686-200-nw-en-gebruikte-bestelwagens-personenbusjes-pick-ups.html
/a/auto-s/bestelauto-s/m940111355-bus-verkopen-bestelauto-inkoop-bestelwagen-opkoper-rdw.html
/a/auto-s/volkswagen/m1456401063-volkswagen-golf-1-6-74kw-2000-zwart.html
/a/auto-s/renault/m1456242548-renault-espace-2-0-dci-110kw-e4-2006-zwart.html
/a/auto-s/nissan/m1448699345-nissan-qashqai-1-5-dci-connect-2011-grijs-panoramadak.html
/a/auto-s/bestelauto-s/a1212708374-70-x-kleine-bestelwagens-lage-km-scherpe-prijzen.html
/a/auto-s/bmw/m1452641019-bmw-5-serie-2-0-520d-touring-aut-2014-grijs.html
/a/auto-s/mercedes-benz/m1448671698-mercedes-benz-a-klasse-a250-amg-224pk-7g-dct-panoramadak-wid.html
/a/auto-s/bmw/m1455671862-bmw-3-serie-2-0-i-320-cabrio-aut-2007-bruin.html
/a/auto-s/bestelauto-s/m1455562699-volkswagen-transporter-kmstand-151-534-2-5-tdi-65kw-2002.html
/a/auto-s/bestelauto-s/a1295698562-35-x-renault-kangoo-2013-t-m-2015-v-a-25000-km.html
/a/auto-s/infiniti/m1458111256-infiniti-q50-3-5-hybrid-awd-2016-grijs.html
/a/auto-s/ford/m1458111166-ford-ka-1-3-i-44kw-2007-zwart.html
/a/auto-s/bestelauto-s/m1457499260-renault-master-l3h2-2018-airco-camera-cruise-laadruimte-12.html
/a/auto-s/land-rover/m1458110209-land-rover-discovery-4-3-0-tdv6-2010-grijs.html
/a/auto-s/dodge/a1279463634-5-jaar-ram-dealer-garantie-lage-bijtelling.html
/a/auto-s/bmw/m1455389317-bmw-320i-e46-sedan-bieden.html
/a/auto-s/ford/m1457306473-ford-galaxy-2-0-tdci-85kw-dpf-2011-blauw.html
/a/auto-s/peugeot/m1456912876-peugeot-407-2-0-16v-sw-2006-grijs.html
/a/auto-s/bestelauto-s/m1457161395-renault-master-t35-2-3-dci-l3h2-130-pk-navi-airco-camera-pdc.html
/a/auto-s/bestelauto-s/a1299134880-citroen-berlingo-1-6-hdi-2017-airco-sd-3-zits-v-a-179-p-m.html
/a/auto-s/hyundai/m1458105451-hyundai-atos-gezocht-hoge-prijs-tel-0653222206.html
/a/auto-s/volkswagen/m1458103618-volkswagen-polo-1-4-tsi-132kw-dsg-2012-wit.html
/a/auto-s/vrachtwagens/m1458101965-scania-torpedo.html
/a/auto-s/toyota/m1458101624-toyota-yaris-1-0-12v-vvt-i-aspiration-5dr-2012.html
/a/auto-s/dodge/a1279447576-5-jaar-ram-dealer-garantie-en-historie-bekijk-onze-website.html
You can also build the actual url of the page by appending 'https://www.marktplaats.nl' to li.a.get('href'). So, your whole code should look like this:
import requests
from bs4 import BeautifulSoup
def parse_links(url):
links = []
response = requests.get(url)
soup = BeautifulSoup(response.text, 'html.parser')
for li in soup.find_all(class_="mp-Listing mp-Listing--list-item"):
links.append('https://www.marktplaats.nl' + li.a.get('href'))
return links
url = "https://www.marktplaats.nl/l/auto-s/#f:10882,10898|PriceCentsTo:350000|constructionYearFrom:2001|offeredSince:TODAY|searchInTitleAndDescription:true"
links = parse_links(url)
print('\n'.join(map(str, links)))
It should produce the output like this:
https://www.marktplaats.nl/a/auto-s/renault/a1302508082-mooi-renault-megane-scenic-1-6-16v-aut-2005-2003-groen-airco.html
https://www.marktplaats.nl/a/auto-s/oldtimers/a1302359157-morris-minor-cabriolet-1970.html
https://www.marktplaats.nl/a/auto-s/oldtimers/a1302743902-online-veiling-oldtimers-en-classic-cars-zedelgem-vavato.html
https://www.marktplaats.nl/a/auto-s/oldtimers/a1302359138-mercedes-benz-g-500-guard-pantzer-1999.html
https://www.marktplaats.nl/a/auto-s/volkswagen/m1457703674-golf-6-1-2tsi-comfortline-bluemotion-77kw-2de-eigenaar.html
https://www.marktplaats.nl/a/auto-s/peugeot/m1457564187-peugeot-208-1-6-e-hdi-68kw-92pk-5-d-2014-zwart.html
https://www.marktplaats.nl/a/auto-s/volkswagen/m1457124365-volkswagen-touareg-3-2-v6-177kw-4motion-aut-2004-grijs.html
https://www.marktplaats.nl/a/auto-s/volkswagen/m1456753596-volkswagen-golf-vii-2-0-tdi-highline-150pk-xenon-trekhaak.html
https://www.marktplaats.nl/a/auto-s/volkswagen/a1279696849-vw-take-up-5-d-radio-airco-private-lease.html
https://www.marktplaats.nl/a/auto-s/bestelauto-s/m940111355-bus-verkopen-bestelauto-inkoop-bestelwagen-opkoper-rdw.html
https://www.marktplaats.nl/a/auto-s/volkswagen/m1456401063-volkswagen-golf-1-6-74kw-2000-zwart.html
https://www.marktplaats.nl/a/auto-s/renault/m1456242548-renault-espace-2-0-dci-110kw-e4-2006-zwart.html
https://www.marktplaats.nl/a/auto-s/nissan/m1448699345-nissan-qashqai-1-5-dci-connect-2011-grijs-panoramadak.html
https://www.marktplaats.nl/a/auto-s/citroen/a1277007710-citroen-c1-feel-5-d-airco-private-lease-vanaf-189-euro-mnd.html
https://www.marktplaats.nl/a/auto-s/bmw/m1452641019-bmw-5-serie-2-0-520d-touring-aut-2014-grijs.html
https://www.marktplaats.nl/a/auto-s/mercedes-benz/m1448671698-mercedes-benz-a-klasse-a250-amg-224pk-7g-dct-panoramadak-wid.html
https://www.marktplaats.nl/a/auto-s/bmw/m1455671862-bmw-3-serie-2-0-i-320-cabrio-aut-2007-bruin.html
https://www.marktplaats.nl/a/auto-s/bestelauto-s/m1455562699-volkswagen-transporter-kmstand-151-534-2-5-tdi-65kw-2002.html
https://www.marktplaats.nl/a/auto-s/peugeot/a1298813052-private-lease-occasion-outlet-prive-lease.html
https://www.marktplaats.nl/a/auto-s/audi/m1458114563-audi-a4-2-0-tfsi-132kw-avant-multitronic-nl-auto.html
https://www.marktplaats.nl/a/auto-s/mercedes-benz/m1452983872-mercedes-a-klasse-2-0-cdi-a200-5drs-aut-2007-grijs.html
https://www.marktplaats.nl/a/auto-s/bestelauto-s/m1457499260-renault-master-l3h2-2018-airco-camera-cruise-laadruimte-12.html
https://www.marktplaats.nl/a/auto-s/infiniti/m1458111256-infiniti-q50-3-5-hybrid-awd-2016-grijs.html
https://www.marktplaats.nl/a/auto-s/bestelauto-s/a1001658686-200-nw-en-gebruikte-bestelwagens-personenbusjes-pick-ups.html
https://www.marktplaats.nl/a/auto-s/ford/m1458111166-ford-ka-1-3-i-44kw-2007-zwart.html
https://www.marktplaats.nl/a/auto-s/land-rover/m1458110209-land-rover-discovery-4-3-0-tdv6-2010-grijs.html
https://www.marktplaats.nl/a/auto-s/bmw/m1455389317-bmw-320i-e46-sedan-bieden.html
https://www.marktplaats.nl/a/auto-s/bestelauto-s/m1457161395-renault-master-t35-2-3-dci-l3h2-130-pk-navi-airco-camera-pdc.html
https://www.marktplaats.nl/a/auto-s/renault/a1302508082-mooi-renault-megane-scenic-1-6-16v-aut-2005-2003-groen-airco.html
https://www.marktplaats.nl/a/auto-s/ford/m1457306473-ford-galaxy-2-0-tdci-85kw-dpf-2011-blauw.html
https://www.marktplaats.nl/a/auto-s/peugeot/m1456912876-peugeot-407-2-0-16v-sw-2006-grijs.html
https://www.marktplaats.nl/a/auto-s/hyundai/m1458105451-hyundai-atos-gezocht-hoge-prijs-tel-0653222206.html
https://www.marktplaats.nl/a/auto-s/volkswagen/m1458103618-volkswagen-polo-1-4-tsi-132kw-dsg-2012-wit.html
https://www.marktplaats.nl/a/auto-s/oldtimers/a1302743902-online-veiling-oldtimers-en-classic-cars-zedelgem-vavato.html
Good luck!
Please bear with me. I am quite new at Python - but having a lot of fun. I am trying to code a web crawler that crawls through election results from the last referendum in Denmark. I have managed to extract all the relevant links from the main page. And now I want Python to follow each of the 92 links and gather 9 pieces of information from each of those pages. But I am so stuck. Hope you can give me a hint.
Here is my code:
import requests
import urllib2
from bs4 import BeautifulSoup
# This is the original url http://www.kmdvalg.dk/
soup = BeautifulSoup(urllib2.urlopen('http://www.kmdvalg.dk/').read())
my_list = []
all_links = soup.find_all("a")
for link in all_links:
link2 = link["href"]
my_list.append(link2)
for i in my_list[1:93]:
print i
# The output shows all the links that I would like to follow and gather information from. How do I do that?
Here is my solution using lxml. It's similar to BeautifulSoup
import lxml
from lxml import html
import requests
page = requests.get('http://www.kmdvalg.dk/main')
tree = html.fromstring(page.content)
my_list = tree.xpath('//div[#class="LetterGroup"]//a/#href') # grab all link
print 'Length of all links = ', len(my_list)
my_list is a list consist of all links. And now you can use for loop to scrape information inside each page.
We can for loop through each links. Inside each page, you can extract information as example. This is only for the top table.
table_information = []
for t in my_list:
page_detail = requests.get(t)
tree = html.fromstring(page_detail.content)
table_key = tree.xpath('//td[#class="statusHeader"]/text()')
table_value = tree.xpath('//td[#class="statusText"]/text()') + tree.xpath('//td[#class="statusText"]/a/text()')
table_information.append(zip([t]*len(table_key), table_key, table_value))
For table below the page,
table_information_below = []
for t in my_list:
page_detail = requests.get(t)
tree = html.fromstring(page_detail.content)
l1 = tree.xpath('//tr[#class="tableRowPrimary"]/td[#class="StemmerNu"]/text()')
l2 = tree.xpath('//tr[#class="tableRowSecondary"]/td[#class="StemmerNu"]/text()')
table_information_below.append([t]+l1+l2)
Hope this help!
A simple approach would be to iterate through your list of urls and parse them each individually:
for url in my_list:
soup = BeautifulSoup(urllib2.urlopen(url).read())
# then parse each page individually here
Alternatively, you could speed things up significantly using Futures.
from requests_futures.sessions import FuturesSession
def my_parse_function(html):
"""Use this function to parse each page"""
soup = BeautifulSoup(html)
all_paragraphs = soup.find_all('p')
return all_paragraphs
session = FuturesSession(max_workers=5)
futures = [session.get(url) for url in my_list]
page_results = [my_parse_function(future.result()) for future in results]
This would be my solution for your problem
import requests
from bs4 import BeautifulSoup
def spider():
url = "http://www.kmdvalg.dk/main"
source_code = requests.get(url)
plain_text = source_code.text
soup = BeautifulSoup(plain_text, 'html.parser')
for link in soup.findAll('div', {'class': 'LetterGroup'}):
anc = link.find('a')
href = anc.get('href')
print(anc.getText())
print(href)
# spider2(href) call a second function from here that is similar to this one(making url = to herf)
spider2(href)
print("\n")
def spider2(linktofollow):
url = linktofollow
source_code = requests.get(url)
plain_text = source_code.text
soup = BeautifulSoup(plain_text, 'html.parser')
for link in soup.findAll('tr', {'class': 'tableRowPrimary'}):
anc = link.find('td')
print(anc.getText())
print("\n")
spider()
its not done... i only get a simple element from the table but you get the idea and how its supposed to work.
Here is my final code that works smooth. Please let me know if I could have done it smarter!
import urllib2
from bs4 import BeautifulSoup
import codecs
f = codecs.open("eu2015valg.txt", "w", encoding="iso-8859-1")
soup = BeautifulSoup(urllib2.urlopen('http://www.kmdvalg.dk/').read())
liste = []
alle_links = soup.find_all("a")
for link in alle_links:
link2 = link["href"]
liste.append(link2)
for url in liste[1:93]:
soup = BeautifulSoup(urllib2.urlopen(url).read().decode('iso-8859-1'))
tds = soup.findAll('td')
stemmernu = soup.findAll('td', class_='StemmerNu')
print >> f, tds[5].string,";",tds[12].string,";",tds[14].string,";",tds[16].string,";", stemmernu[0].string,";",stemmernu[1].string,";",stemmernu[2].string,";",stemmernu[3].string,";",stemmernu[6].string,";",stemmernu[8].string,";",'\r\n'
f.close()