从python中的网页中提取电子邮件[关闭]

Question

我发现以下代码可以抓取网站（我认为是所有网站）以获取电子邮件

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

# starting url. replace google with your own url.
starting_url = 'http://www.miet.ac.in'

# a queue of urls to be crawled
unprocessed_urls = deque([starting_url])

# set of already crawled urls for email
processed_urls = set()

# a set of fetched emails
emails = set()

# process urls one by one from unprocessed_url queue until queue is empty
while len(unprocessed_urls):

    # move next url from the queue to the set of processed urls
    url = unprocessed_urls.popleft()
    processed_urls.add(url)

    # extract base url to resolve relative links
    parts = urlsplit(url)
    base_url = "{0.scheme}://{0.netloc}".format(parts)
    path = url[:url.rfind('/')+1] if '/' in parts.path else url

    # get url's content
    print("Crawling URL %s" % url)
    try:
        response = requests.get(url)
    except (requests.exceptions.MissingSchema, requests.exceptions.ConnectionError):
        # ignore pages with errors and continue with next url
        continue

    # extract all email addresses and add them into the resulting set
    # You may edit the regular expression as per your requirement
    new_emails = set(re.findall(r"[a-z0-9\.\-+_]+@[a-z0-9\.\-+_]+\.[a-z]+", response.text, re.I))
    emails.update(new_emails)
    print(emails)
    # create a beutiful soup for the html document
    soup = BeautifulSoup(response.text, 'lxml')

    # Once this document is parsed and processed, now find and process all the anchors i.e. linked urls in this document
    for anchor in soup.find_all("a"):
        # extract link url from the anchor
        link = anchor.attrs["href"] if "href" in anchor.attrs else ''
        # resolve relative links (starting with /)
        if link.startswith('/'):
            link = base_url + link
        elif not link.startswith('http'):
            link = path + link
        # add the new url to the queue if it was not in unprocessed list nor in processed list yet
        if not link in unprocessed_urls and not link in processed_urls:
            unprocessed_urls.append(link)

如何修改这样的代码以仅提取一个网页..？我只需要定位一个网页而不是整个网站。

Answer 1

只需删除从for anchor in soup.find_all("a"): 开始的所有行。您的文档应如下所示：

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

# starting url. replace google with your own url.
starting_url = 'http://www.miet.ac.in'

# a queue of urls to be crawled
unprocessed_urls = deque([starting_url])

# set of already crawled urls for email
processed_urls = set()

# a set of fetched emails
emails = set()

# process urls one by one from unprocessed_url queue until queue is empty
while len(unprocessed_urls):

    # move next url from the queue to the set of processed urls
    url = unprocessed_urls.popleft()
    processed_urls.add(url)

    # extract base url to resolve relative links
    parts = urlsplit(url)
    base_url = "{0.scheme}://{0.netloc}".format(parts)
    path = url[:url.rfind('/')+1] if '/' in parts.path else url

    # get url's content
    print("Crawling URL %s" % url)
    try:
        response = requests.get(url)
    except (requests.exceptions.MissingSchema, requests.exceptions.ConnectionError):
        # ignore pages with errors and continue with next url
        continue

    # extract all email addresses and add them into the resulting set
    # You may edit the regular expression as per your requirement
    new_emails = set(re.findall(r"[a-z0-9\.\-+_]+@[a-z0-9\.\-+_]+\.[a-z]+", response.text, re.I))
    emails.update(new_emails)
    print(emails)
    # create a beutiful soup for the html document
    soup = BeautifulSoup(response.text, 'lxml')

使用 Python 生成随机电子邮件地址：

from faker import Faker

faker = Faker()

for i in range(12):
    print(f'{faker.email()}')