Python实现爬虫从网络上下载文档的实例代码_Python

最近在学习Python，自然接触到了爬虫，写了一个小型爬虫软件，从初始Url解析网页，使用正则获取待爬取链接，使用beautifulsoup解析获取文本，使用自己写的输出器可以将文本输出保存，具体代码如下：

Spider_main.py

									# coding:utf8

									from baike_spider import url_manager, html_downloader, html_parser, html_outputer

									class SpiderMain(object):

									  def __init__(self):

									    self.urls = url_manager.UrlManager()

									    self.downloader = html_downloader.HtmlDownloader()

									    self.parser = html_parser.HtmlParser()

									    self.outputer = html_outputer.HtmlOutputer()

									  def craw(self, root_url):

									    count = 1

									    self.urls.add_new_url(root_url)

									    while self.urls.has_new_url():

									      print("self.urls.has %s" % self.urls.new_urls)

									      try:

									        new_url = self.urls.get_new_url()

									        print("craw %d : %s"%(count, new_url))

									        html_cont = self.downloader.download(new_url)

									        new_urls, new_data = self.parser.parse(new_url, html_cont)

									        self.urls.add_new_urls(new_urls)

									        self.outputer.collect_data(new_data)

									        if count == 1000:

									          break

									        count = count + 1

									      except:

									        print("craw failed")

									    self.outputer.output_html()

									    self.outputer.output_txt()

									if __name__ == '__main__':

									  root_url = "http://www.shushu8.com/jiangnan/longzu2qianzhuan/1"

									  obj_spider = SpiderMain()

									  obj_spider.craw(root_url)

url_manager.py

									class UrlManager(object):

									  def __init__(self):

									    self.new_urls = set()

									    self.old_urls = set()

									  def add_new_url(self, url):

									    print(url)

									    if url is None:

									      return

									    if url not in self.new_urls and url not in self.old_urls:

									      self.new_urls.add(url)

									  def has_new_url(self):

									    return len(self.new_urls) != 0

									  def get_new_url(self):

									    new_url = self.new_urls.pop()

									    self.old_urls.add(new_url)

									    # print('new url is %s' % new_url)

									    return new_url

									  def add_new_urls(self, urls):

									    print("add_new_urls %s" % urls)

									    if urls is None or len(urls) == 0:

									      return

									    for url in urls:

									      self.add_new_url(url)

									      print(url)

html_parser.py

									import re

									import urllib.parse

									from bs4 import BeautifulSoup

									class HtmlParser(object):

									  def parse(self, page_url, html_cont):

									    if page_url is None or html_cont is None:

									      return

									    soup = BeautifulSoup(html_cont, 'html.parser', from_encoding='utf-8')

									    new_urls = self._get_new_urls(page_url, soup)

									    print("parse new_urls %s" % new_urls)

									    new_data = self._get_new_data(page_url, soup)

									    return new_urls, new_data

									  def _get_new_data(self, page_url, soup):

									    res_data = {}

									    res_data['url'] = page_url

									    print(page_url)

									    title_node = soup.find(class_="title").find("h1")

									    print(title_node.get_text())

									    res_data['title'] = title_node.get_text()

									    print("_get_new_data")

									    summary_node = soup.find('pre')

									    print(summary_node.get_text())

									    res_data['summary'] = summary_node.get_text()

									    return res_data

									  def _get_new_urls(self, page_url, soup):

									    new_urls = set()

									    links = soup.find_all('a', href=re.compile(r"/jiangnan/"))

									    print(links)

									    for link in links:

									      new_url = link['href']

									      new_full_url = urllib.parse.urljoin(page_url, new_url)

									      new_urls.add(new_full_url)

									      # print(new_full_url)

									    return new_urls

html_downloader.py

									import urllib.request

									class HtmlDownloader(object):

									  def download(self, url):

									    if url is None:

									      return None

									    response = urllib.request.urlopen(url)

									    if response.getcode() != 200:

									      return None

									    return response.read()

html_outputer.py

									class HtmlOutputer(object):

									  def __init__(self):

									    self.datas = []

									  def collect_data(self, data):

									    if data is None:

									      return

									    self.datas.append(data)

									  def output_txt(self):

									    fout = open('output.txt', 'w', encoding='utf-8')

									    for data in self.datas:

									      fout.write('%s \n' % data['title'])

									      fout.write('%s \n' % data['summary'])

									  def output_html(self):

									    fout = open('output.html', 'w', encoding='utf-8')

									    fout.write('<html>')

									    fout.write('<body>')

									    fout.write('<table>')

									    for data in self.datas:

									      fout.write('<tr>')

									      fout.write('<td>%s</td>' % data['url'])

									      fout.write('<td>%s</td>' % data['title'])

									      fout.write('<td>%s</td>' % data['summary'])

									      fout.write('</tr>')

									    fout.write('</table>')

									    fout.write('</body>')

									    fout.write('</html>')

									    fout.close()

总结

以上所述是小编给大家介绍的Python实现爬虫从网络上下载文档的实例代码，希望对大家有所帮助，如果大家有任何疑问请给我留言，小编会及时回复大家的。在此也非常感谢大家对服务器之家网站的支持！

原文链接：https://www.cnblogs.com/hasan/archive/2018/06/12/9175592.html

Python实现爬虫从网络上下载文档的实例代码

相关文章

热门资讯