爬取百度百科1000个页面的数据

释放双眼,带上耳机,听听看~!

package : baike_spider

spider_main.py
from baike_spider import url_manager, html_downloader, html_parser, html_outputer
import urllib.parse

coding:utf-8

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():
        try:
            new_url = self.urls.get_new_url()
            html_cont = self.downloader.download(new_url)
            print("craw %d:%s" % (count,urllib.parse.unquote(new_url,encoding='utf-8')))
            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 += 1
        except:
            print("spider failed")

    self.outputer.output_html()        

if name == “main“:
root_url = “https://baike.baidu.com/item/Python/407313?fr=aladdin
obj_spider = SpiderMain()
obj_spider.craw(root_url)

url_manager.py

coding:utf-8

class UrlManager(object):
def init(self):
self.new_urls = set()
self.old_urls = set()

def add_new_url(self, 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 add_new_urls(self, urls):
    if urls is None or len(urls) == 0:
        return

    for url in urls:
        self.add_new_url(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)
    return new_url

html_downloader.py
import urllib.request

coding:utf-8

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_parser.py

coding:utf-8

from bs4 import BeautifulSoup
import re
import urllib.request
from urllib.parse import urljoin

class HtmlParser(object):
def _get_new_urls(self, page_url, soup):
new_urls = set()
links = soup.find_all(‘a’, href=re.compile(r’/item//w+’))
for link in links:
new_url = link[‘href’]
new_full_url = urljoin(page_url, new_url)
new_urls.add(new_full_url)
return new_urls

def _get_new_data(self, page_url, soup):
    res_data = {}
    res_data['url'] = page_url
    title_node = soup.find('dd', class_='lemmaWgt-lemmaTitle-title').find('h1')
    res_data['title'] = title_node.get_text()
    summary_node = soup.find('div', class_='lemma-summary')
    res_data['summary'] = summary_node.get_text()
    return res_data

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)
    new_data = self._get_new_data(page_url, soup)
    return new_urls, new_data

html_outputer.py

coding:utf-8

import urllib.parse

class HtmlOutputer(object):
def init(self):
self.datas = []

def collect_data(self, data):
    if data is None:
        return

    self.datas.append(data)

def output_html(self):
    fout = open('output.html', 'w', encoding='utf-8')
    fout.write('<html>')
    fout.write("<head><meta http-equiv='content-type' content='text/html;charset=utf-8'></head>")
    fout.write('<body>')
    fout.write('<table>')
    for data in self.datas:
        fout.write('<td>%s</td>' % (urllib.parse.unquote(data['url'],encoding='utf-8')))
        fout.write('<td>%s</td>' % (urllib.parse.unquote(data['title'],encoding='utf-8')))
        fout.write('<td>%s</td>' % (urllib.parse.unquote(data['summary'],encoding='utf-8')))
        fout.write('</tr>')
    fout.write('</table>')
    fout.write('</body>')
    fout.write('</html>')

【转自慕课】https://www.imooc.com

Python

可以用 Python 编程语言做哪些神奇好玩的事情?

2022-3-3 13:52:18

Python

Python入门到实践-元组

2022-3-3 13:54:29

搜索