新手菜鸟python2.7爬虫出现问题，找了好久不知道问题在哪，求大神帮忙

西门吹瓶哥 2017-10-19 02:54:14

# -*- coding: utf-8 -*-
"""
Spyder Editor

This is a temporary script file.
"""
import urllib2
from bs4 import BeautifulSoup
import re
import urlparse

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

class HtmlDownloader(object):
def download(self,url):
if url is None:
return None

response = urllib2.urlopen(url)

if response.getcode() != 200:
return None

return response.read()

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

def _get_new_data(self,page_url,soup):
res_data = {}

#url
res_data['url'] = page_url

# <dd class="lemmaWgt-lemmaTitle-title"><h1>Python</h1>
title_node = soup.find('dd',class_ ="lemmaWgt-lemmaTitle-title").find("h1")
res_data['title'] = title_node.get_text()

#<div class="lemma-summary" label-module="lemmaSummary">
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

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')

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'].encode('utf-8'))
fout.write("<td>%s</td>"% data['summary'].encode('utf-8'))
fout.write("</tr>")

fout.write("</table>")
fout.write("</body>")
fout.write("</html>")

fout.close()

class SpiderMain(object):
def __init__(self):
self.urls = UrlManager()
self.downloader = HtmlDownloader()
self.parser = HtmlParser()
self.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()
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 == 100:
break
count = count + 1

except:
print 'craw 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)

#提示：
#runfile('C:/Users/sun/.spyder/temp.py', wdir='C:/Users/sun/.spyder')
#craw 1 : https://baike.baidu.com/item/Python/407313?fr=aladdin
#craw failed

...全文

193 1 打赏收藏转发到动态举报

写回复

用AI写文章

1 条回复

切换为时间正序

请发表友善的回复…

发表回复

Cyouno 2017-10-20

打赏
举报

soup = BeautifulSoup(html_cont, 'html_parser', from_encoding='utf-8') 改成： soup = BeautifulSoup(html_cont, 'html.parser', from_encoding='utf-8') 或者： soup = BeautifulSoup(html_cont, 'lxml', from_encoding='utf-8')