非常感谢老师 , 第一次接触python 已经会下载图片啦 , 分享出来大家共同学习
老师的代码稍加修改已经可以爬图片啦
main
from baike_spider import html_downloader from baike_spider import html_outputer from baike_spider import html_parser from baike_spider import img_downloader from baike_spider import url_manager 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() self.imgdownloader = img_downloader.ImgDownloader() 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() print(count, new_url) html_count = self.downloader.download(new_url) new_urls, new_data, img_urls = self.parser.parser(new_url, html_count) self.urls.add_new_urls(new_urls) #加入新的url self.outputer.collect_data(new_data) #输出html文件 self.imgdownloader.downImg(img_urls) #下载图片 if count == 100: break count += 1 except: print(count, "出现异常") self.outputer.output_html() if __name__ == "__main__": root_url = "http://www.lunvshen.org/t-600" obj_spider = SpiderMain() obj_spider.craw(root_url)
HtmlOutputer
class HtmlOutputer(object):
def __init__(self):
self.datas = []
def collect_data(self, new_data):
if new_data is None:
return
self.datas.append(new_data)
def output_html(self):
fout = open('yu.html', 'w')
fout.write("<html>")
fout.write("<body>")
fout.write("<table>")
count = 1
for data in self.datas:
fout.write("<tr>")
fout.write("<td>")
fout.write('<a target="_blank" href ="')
fout.write(data['url'])
fout.write('">')
fout.write(data['url'])
fout.write("</a>")
fout.write("</td>")
fout.write("<td>%s</td>" % (str(count)+"-"+ data['title']))
count+=1
fout.write("</tr>")
fout.write("</table>")
fout.write("</body>")
fout.write("</html>")
fout.close()HtmlParser
import re
import urllib
from bs4 import BeautifulSoup
from urllib import parse
class HtmlParser(object):
def parser(self, new_url, html_count):
if new_url is None or html_count is None:
return
soup = BeautifulSoup(html_count, 'html.parser', from_encoding='utf-8')
new_urls = self._get_new_urls(soup)
new_data = self._get_new_data(new_url, soup)
new_imgs = self._get_img(soup)
return new_urls, new_data, new_imgs
@staticmethod
def _get_new_urls(soup):
new_urls = set()
links = soup.find_all('a', href=re.compile(r"/t-\d+"))
for link in links:
new_url = link['href']
new_full_url = urllib.parse.urljoin('http://www.lunvshen.org/', new_url)
new_urls.add(new_full_url)
return new_urls
@staticmethod
def _get_new_data(new_url, soup):
res_data = {}
res_data['url'] = new_url
# < dd class ="lemmaWgt-lemmaTitle-title" >< h1 > Python < / h1 >
title_node = soup.find('div', class_='topic-title-main').find('h1')
res_data['title'] = title_node.get_text()
# < div class ="lemma-summary" label-module="lemmaSummary" >
# < divclass ="para" label-module="para" > Python < sup >
# summary_node = soup.find('div', class_='topic-content').find('img')
# res_data['summary'] = summary_node.getsrc()
return res_data
@staticmethod
def _get_img(soup):
new_imgurls = set()
imgLinks = soup.find_all('img', src=re.compile(r"http://ww\d\.sinaimg"))
for imgLink in imgLinks:
# print("图片:::", imgLink)
new_imgurls.add(imgLink)
return new_imgurlsImgDownloader
import urllib.request
class ImgDownloader(object):
def downImg(self, img_urls):
if img_urls is None:
return
count = 1
for imgLink in img_urls:
trueImgUrl = imgLink.get('src')
urllen = len(trueImgUrl)
a = urllen - 18
b = urllen - 4
imgName = trueImgUrl[a: b] + "-" + str(count)
filesavepath = '/Users/lucky/Downloads/img/%s.jpg' % imgName #mac的文件地址
# 下载图片
urllib.request.urlretrieve(trueImgUrl, filesavepath)
count += 1
print("下载成功::", filesavepath)UrlManager
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
HtmlDownloader
from urllib import request class HtmlDownloader(object): @staticmethod def download(url): if url is None: return None response = request.urlopen(url) if response.getcode() != 200: return None return response.read()
