出现SyntaxError: invalid syntax（语法解析失败）
# coding:utf8
from baidu import url_manager,html_downloader,html_parser,html_outputer
class SpiderMain(object):
def __int__(self):
self.urls = url_mansger.UrlManager()
self.downloader = htaml_downloader.HtmlDownloader()
self.parser = html_parser.HtmlParser()
self.outputer = htaml_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_url,new_data = self.parser.parser(new_url,html_cont)
self.urls.add_new_url(new_urls)
self.outputer.collect_data(new_data)
if count == 1000:
break
count = count + 1
except:
print 'craw failed'
self.outputer.output_html()
if __name__=="__main__":
root_url = "http://http://baike.baidu.com/view/21087.htm"
obj_spider = SpiderMain()
obj_spider.craw(root_url)
—————————分———————割———————线————————————
# coding:utf8
class UrlManager(object):
def __int__(self):
self.new_urls = set()
self.old_urls = set()
def add_new_url(self):
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):
if urls is None or len(urls) == 0:
return
for url in urls:
self.add_new_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
—————————分———————割———————线————————————
# coding:utf8
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()
—————————分———————割———————线————————————
# coding:utf8
class HtmlParser(object):
def _get_new_urls(self,page_url,soup):
new_urls = set()
links = soup.find_all('a',href=re.compile(r"/view/\d+\.htaml"))
for link in links
new_url = link['href']
new_full_url = urlparse.urljoin(page_url,new_url)
return new_urls
def _get_new_data(self,page_url,soup):
res_data = {}
res_data['url'] = page_url
#Python
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 htaml_cont is None:
return
soup = BeatuifulSoup(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
—————————分———————割———————线————————————
# coding:utf8
class HtmlOutputerr(object):
def __int__(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("")
fout.write("")
fout.write("")
for data in self.datas:
fout.write("")
fout.write("%s" % data['data'])
fout.write("%s" % data['title'].encode('utf=8'))
fout.write("%s" % data['summary'].encode('utf=8'))
fout.write("")
fout.write("")
fout.write("")
fout.write("[/table]")
|
免责声明：本内容仅代表回答会员见解不代表天盟观点，请谨慎对待。
版权声明：作者保留权利，不代表天盟立场。
|
|
|
|
|
|
|
|
天盟APP下载
