I've written a script in python to fetch some links from a webpage. There are two functions within my script. The first function collect links to the local businesses from a webpage and the second function traverses those links and collect urls to the various events.
When I try with the script found here, I get desired results.
How can I return all the results complying the below design?
The following script return the results of individual links whereas I wish to return all the result at once keeping the design as it is (logic may vary).
import requests
from bs4 import BeautifulSoup
from urllib.parse import urljoin
linklist = []
def collect_links(link):
res = requests.get(link)
soup = BeautifulSoup(res.text, "lxml")
items = [urljoin(url,item.get("href")) for item in soup.select(".business-listings-category-list .field-content a[hreflang]")]
return items
def fetch_info(ilink):
res = requests.get(ilink)
soup = BeautifulSoup(res.text, "lxml")
for item in soup.select(".business-teaser-title a[title]"):
linklist.append(urljoin(url,item.get("href")))
return linklist
if __name__ == '__main__':
url = "https://www.parentmap.com/atlas"
for itemlink in collect_links(url):
print(fetch_info(itemlink))
First of all I removed the global linklist
as it is returned from the function anyway, and keeping global creates overlapping results. Next I added a function to "assemble" the links the way you wanted. I used a set to prevent duplicate links.
#!/usr/bin/python
import requests
from bs4 import BeautifulSoup
from urllib.parse import urljoin
def collect_links(link):
res = requests.get(link)
soup = BeautifulSoup(res.text, "lxml")
items = [urljoin(url,item.get("href")) for item in soup.select(".business-listings-category-list .field-content a[hreflang]")]
return items
def fetch_info(ilink):
linklist = []
res = requests.get(ilink)
soup = BeautifulSoup(res.text, "lxml")
for item in soup.select(".business-teaser-title a[title]"):
linklist.append(urljoin(url,item.get("href")))
return linklist
def fetch_all_links(url):
links = set()
for itemlink in collect_links(url):
links.update(fetch_info(itemlink))
return list(links)
if __name__ == '__main__':
url = "https://www.parentmap.com/atlas"
print(fetch_all_links(url))