Python 2.7 BeautifulSoup email scraping stops before end of full database

Question

Hope you are all well! I'm new and using Python 2.7! I'm tring to extract emails from a public available directory website that does not seems to have API: this is the site: http://www.tecomdirectory.com/companies.php?segment=&activity=&search=category&submit=Search
, the code stop gathering email where on the page at the bottom where it says "load more"! Here is my code:

import requests
import re
from bs4 import BeautifulSoup
file_handler = open('mail.txt','w')

soup  = BeautifulSoup(requests.get('http://www.tecomdirectory.com/companies.php?segment=&activity=&search=category&submit=Search').content)
tags = soup('a') 
list_new =[]
for tag in tags:
    if (re.findall(r'href="mailto:([^"@]+@[^"]+)">\1</a>',('%s'%tag))): list_new = list_new +(re.findall(r'href="mailto:([^"@]+@[^"]+)">\1</a>', ('%s'%tag)))

for x in list_new:
    file_handler.write('%s\n'%x)
file_handler.close()

How can i make sure that the code goes till the end of the directory and does not stop where it shows load more? Thanks. Warmest regards

Answer 1

You just need to post some data, in particular incrementing group_no to simulate clicking the load more button:

from bs4 import BeautifulSoup
import requests

# you can set whatever here to influence the results
data = {"group_no": "1",
        "search": "category",
        "segment": "",
        "activity": "",
        "retail": "",
        "category": "",
        "Bpark": "",
        "alpha": ""} 

post = "http://www.tecomdirectory.com/getautocomplete_keyword.php"

with requests.Session() as s:
    soup = BeautifulSoup(
        s.get("http://www.tecomdirectory.com/companies.php?segment=&activity=&search=category&submit=Search").content,
        "html.parser")
    print([a["href"] for a in soup.select("a[href^=mailto:]")])
    for i in range(1, 5):
        data["group_no"] = str(i)
        soup = BeautifulSoup(s.post(post, data=data).content, "html.parser")
        print([a["href"] for a in soup.select("a[href^=mailto:]")])

To go until the end, you can loop until the post returns no html, that signifies we cannot load any more pages:

def yield_all_mails():
    data = {"group_no": "1",
            "search": "category",
            "segment": "",
            "activity": "",
            "retail": "",
            "category": "",
            "Bpark": "",
            "alpha": ""}

    post = "http://www.tecomdirectory.com/getautocomplete_keyword.php"
    start = "http://www.tecomdirectory.com/companies.php?segment=&activity=&search=category&submit=Search"
    with requests.Session() as s:
        resp = s.get(start)
        soup = BeautifulSoup(s.get(start).content, "html.parser")
        yield (a["href"] for a in soup.select("a[href^=mailto:]"))
        i = 1
        while resp.content.strip():
            data["group_no"] = str(i)
            resp = s.post(post, data=data)
            soup = BeautifulSoup(resp.content, "html.parser")
            yield (a["href"] for a in soup.select("a[href^=mailto:]"))
            i += 1

So if we ran the function like below setting "alpha": "Z" to just iterate over the Z's:

from itertools import chain
for mail in chain.from_iterable(yield_all_mails()):
    print(mail)

We would get:

mailto:info@10pearls.com
mailto:fady@24group.ae
mailto:pepe@2heads.tv
mailto:2interact@2interact.us
mailto:gc@worldig.com
mailto:marilyn.pais@3i-infotech.com
mailto:3mgulf@mmm.com
mailto:venkat@4gid.com
mailto:info@4power.biz
mailto:info@4sstudyabroad.com
mailto:fouad@622agency.com
mailto:sahar@7quality.com
mailto:mike.atack@8ack.com
mailto:zyara@emirates.net.ae
mailto:aokasha@zynx.com

Process finished with exit code 0

You should put a sleep in between requests so you don't hammer the server and get yourself blocked.