示例#1
0
import extract_emails

url = 'http://' +  'www.ihq.com'
# print(url)
em = extract_emails.ExtractEmails(url, depth=10, print_log=True, ssl_verify=True, user_agent='Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:66.0) Gecko/20100101 Firefox/66.0', request_delay=0.0)

print(em.emails)


# http://ww1.ihq.com/?sub1=157c433a-6694-11ea-9bd6-d94c5237a6de

# http://ww1.ihq.com/?sub1=157c433a-6694-11ea-9bd6-d94c5237a6de
示例#2
0
        'www.wyndhamhotels.com', 'bravodjs.ca', 'www.cceventcentre.ca',
        'skytek.ca', 'www.signaturesrestaurant.com', 'orangeartgallery.ca',
        'www.theaerieateaglelanding.com', 'wabano.com', 'www.marriott.com',
        'www.kingsarmsoakville.com', 'www.turnberrygolf.ca',
        'www.marriott.com', 'www.riverbendinn.ca', 'hewwine.com',
        'www.mecknc.gov', 'www.ramadainnlondon.com',
        'www.brooksidebanquetcentre.ca', 'www.hilton.com', 'losolemio.com',
        'kitchenerportugueseclub.com', 'www.indiantrailsgc.org',
        'www.experiencegr.com', 'www.lafontsee.us', 'www.buffalowildwings.com',
        'www.newvintageplace.com', 'www.jusushi.com', 'thebullsheadtavern.com',
        'pietrosgr.com', 'wheelhousegrandrapids.com', 'oldgoatgr.com',
        'reservegr.com', 'riograndsteakhouse.com', 'speakezlounge.com',
        'www.mainstpub.com'
    ]

    for url in urls:
        url = 'http://' + url
        try:
            em = extract_emails.ExtractEmails(url,
                                              depth=20,
                                              print_log=True,
                                              ssl_verify=True,
                                              user_agent=None,
                                              request_delay=0.0)
            emails = em.emails
        except:
            if KeyboardInterrupt:
                sys.exit()
            print('error occured')
        print(url)
        print(emails)