python爬虫运行不出结果，debug运行pydev debugger: starting (pid: 6420)

Python版本2.7.12

#coding:utf8
from baike_spider import url_manager, html_downloader, html_parser,\
    html_outputer

class SpiderMain(object):
    #构造函数，初始化各个对象
    def __init__(self):
        #url管理器
        self.urls = url_manager.UrlManager()
        #url下载器
        self.downloader = html_downloader.HtmlDownloader()
        #url解析器
        self.parser = html_parser.HtmlParser()
        #url输出器
        self.outputer =html_outputer.HtmlOutputer()

    #爬虫的调度程序
    def craw(self, root_url):
        #count记录当前爬取的是第几个url
        count = 1
        #1.首先将入口url添加入管理器
        self.urls.add_new_url(root_url)
        #启动爬虫循环，当管理器中有url时
        while self.urls.has_new_url():
            try:
                #获取一个待爬取的url
                new_url = self.urls.get_new_url()
                print ('craw %d : %s' % (count,new_url))
                #启动下载器下载页面
                html_cont = self.downloader.download(new_url)
                #调用解析器解析页面数据，返回新的url列表和新的数据
                new_urls,new_data = self.parser.parse(new_url,html_cont)
                #将新的url补充到管理器
                self.urls.add_new_urls(new_urls)
                #收集数据
                self.outputer.collect_data(new_data)
                #爬取1000个目标
                if count == 1000:
                    break

                count = count + 1
            except:
                print 'craw failed'
            #输出收集好的数据
            self.outputer.output_html()


#1.首先编写main函数
if __name__=="_main_":
    #2.编写入口的url
    root_url = "http://baike.baidu.com/view/21087.htm"
    obj_spider = SpiderMain()
    #3.启动爬虫
    obj_spider.craw(root_url)

7 个解决方案

#1

报什么错呢，写清楚吧

#2

baike_spider是不是没有这个库

#3

pydev debugger: starting (pid: 4200)
Traceback (most recent call last):
  File "F:\eclipse\eclipse\plugins\org.python.pydev_5.1.2.201606231256\pysrc\_pydevd_bundle\pydevd_comm.py", line 1080, in do_it
    result = pydevd_vars.evaluate_expression(self.thread_id, self.frame_id, self.expression, self.doExec)
  File "F:\eclipse\eclipse\plugins\org.python.pydev_5.1.2.201606231256\pysrc\_pydevd_bundle\pydevd_vars.py", line 344, in evaluate_expression
    expression = str(expression.replace('@LINE@', '\n'))
UnicodeEncodeError: 'ascii' codec can't encode characters in position 2-6: ordinal not in range(128)

Traceback (most recent call last):
  File "F:\eclipse\eclipse\plugins\org.python.pydev_5.1.2.201606231256\pysrc\_pydevd_bundle\pydevd_comm.py", line 1080, in do_it
    result = pydevd_vars.evaluate_expression(self.thread_id, self.frame_id, self.expression, self.doExec)
  File "F:\eclipse\eclipse\plugins\org.python.pydev_5.1.2.201606231256\pysrc\_pydevd_bundle\pydevd_vars.py", line 344, in evaluate_expression
    expression = str(expression.replace('@LINE@', '\n'))

#4

麻烦你贴的时候注意下格式，看得头好晕

#5

编码问题，ASCII标准来解码只能解码特殊的128个字符，而遇到128字符以外的就会出现编码错误

#6

编码解码问题，老问题了。

#7

参考一下：http://brucedone.com/archives/43

#1