forked from coldfreeboy/spider
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathspider_main.py
75 lines (45 loc) · 1.7 KB
/
spider_main.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
#coding:utf-8
# 爬虫调度主程序
import url_manager,html_downloader,html_parser,html_outputer
class SpiderMain():
def __init__(self):
# 初始化各模块
# url管理器
self.urls = url_manager.UrlManager()
# 下载器
self.downloader = html_downloader.HtmlDownloader()
# 解析器
self.parser = html_parser.HtmlParser()
# 输出器
self.outputer = html_outputer.HtmlOutputer()
def craw(self,root_url):
count = 0
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)
count=count+1
if count == 100:
break
except Exception as e:
print("craw 失败:%s" % e)
self.outputer.output_html()
print(self.urls.get_count())
if __name__=="__main__":
# 入口url
root_url = "http://baike.baidu.com/view/21087.htm"
# 主类
obj_spider = SpiderMain()
# 开爬
obj_spider.craw(root_url)
# 爬虫构架
# 主程序 程序入口 spider_main.py 入口参数url
# url调度 url_manager.py 负责url存储与提供
# 页面解析 html_parser.py 解析页面 提取url title 简介
# 页面下载 html_downloader.py 根据url下载页面
# 页面输出 html_outputer.py 输出数据