from bs4 import BeautifulSoup #BeautifulSoup最主要的功能是從網(wǎng)頁抓取數(shù)據(jù)，Beautiful Soup自動將輸入文檔轉(zhuǎn)換為Unicode編碼
import requests #requests是python實現(xiàn)的最簡單易用的HTTP庫
import requests.exceptions
import urllib.parse
from collections import deque #deque 是一個雙端隊列, 如果要經(jīng)常從兩端append 的數(shù)據(jù), 選擇這個數(shù)據(jù)結(jié)構(gòu)就比較好了, 如果要實現(xiàn)隨機(jī)訪問,不建議用這個,請用列表. 
import re #是一個正則表達(dá)式的庫

user_url=str(input('[+] Enter Target URL to Scan:'))
urls =deque([user_url]) #把目標(biāo)地址放入deque對象列表

scraped_urls= set()#set() 函數(shù)創(chuàng)建一個無序不重復(fù)元素集，可進(jìn)行關(guān)系測試，刪除重復(fù)數(shù)據(jù)，還可以計算交集、差集、并集等。
emails = set()

count=0
try:
  while len(urls):  #如果urls有長度的話進(jìn)行循環(huán)
    count += 1		#添加計數(shù)器來記錄爬取鏈接的條數(shù) 
    if count ==101:
      break
    url = urls.popleft() #popleft（）會刪除urls里左邊第一條數(shù)據(jù)并傳給url
    scraped_urls.add(url)

    parts = urllib.parse.urlsplit(url) # 打印 parts會顯示：SplitResult(scheme='http', netloc='www.baidu.com', path='', query='', fragment='')
    base_url = '{0.scheme}://{0.netloc}'.format(parts)#scheme：協(xié)議；netloc：域名 

    path = url[:url.rfind('/')+1] if '/' in parts.path else url#提取路徑
    print('[%d] Processing %s' % (count,url))
   
    try:
      head = {'User-Agent':"Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; en) Presto/2.8.131 Version/11.11"}
      response = requests.get(url,headers = head)
    except(requests.exceptions.MissingSchema,requests.exceptions.ConnectionError):
      continue
    new_emails = set(re.findall(r'[a-z0-0\.\-+_]+@[a-z0-9\.\-+_]+\.[a-z]+', response.text ,re.I))#通過正則表達(dá)式從獲取的網(wǎng)頁中提取郵箱，re.I表示忽略大小寫
    emails.update(new_emails)#將獲取的郵箱地址存在emalis中。

    soup = BeautifulSoup(response.text, features='lxml')

    for anchor in soup.find_all('a'):  #尋找錨點。在html中，a>標(biāo)簽代表一個超鏈接，herf屬性就是鏈接地址
      link = anchor.attrs['href'] if 'href' in anchor.attrs else '' #如果，我們找到一個超鏈接標(biāo)簽，并且該標(biāo)簽有herf屬性，那么herf后面的地址就是我們需要錨點鏈接。
      if link.startswith('/'):#如果該鏈接以/開頭，那它只是一個路徑，我們就需要加上協(xié)議和域名，base_url就是剛才分離出來的協(xié)議+域名
        link = base_url + link
      elif not link.startswith('http'):#如果不是以/和http開頭的話，就要加上路徑。
        link =path + link
      if not link in urls and not link in scraped_urls:#如果該鏈接在之前沒還有被收錄的話，就把該鏈接進(jìn)行收錄。
        urls.append(link)
except KeyboardInterrupt:
  print('[+] Closing')

for mail in emails:
  print(mail)

from bs4 import BeautifulSoup
import requests
import requests.exceptions
import urllib.parse
from collections import deque
import re

user_url=str(input('[+] Enter Target URL to Scan:'))
urls =deque([user_url])

scraped_urls= set()
emails = set()


count=0
try:
  while len(urls):
    count += 1
    if count ==100:
      break
    url = urls.popleft()
    scraped_urls.add(url)

    parts = urllib.parse.urlsplit(url)
    base_url = '{0.scheme}://{0.netloc}'.format(parts)

    path = url[:url.rfind('/')+1] if '/' in parts.path else url

    print('[%d] Processing %s' % (count,url))
    try:
      head = {'User-Agent':"Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; en) Presto/2.8.131 Version/11.11"}
      response = requests.get(url,headers = head)
    except(requests.exceptions.MissingSchema,requests.exceptions.ConnectionError):
      continue
    new_emails = set(re.findall(r'[a-z0-0\.\-+_]+@[a-z0-9\.\-+_]+\.[a-z]+', response.text ,re.I))
    emails.update(new_emails)

    soup = BeautifulSoup(response.text, features='lxml')

    for anchor in soup.find_all('a'):
      link = anchor.attrs['href'] if 'href' in anchor.attrs else ''
      if link.startswith('/'):
        link = base_url + link
      elif not link.startswith('http'):
        link =path + link
      if not link in urls and not link in scraped_urls:
        urls.append(link)
except KeyboardInterrupt:
  print('[+] Closing')

for mail in emails:
  print(mail)