1.【实用工具系列之爬虫】python实现爬取代理IP(防 ‘反爬虫’)
2.【实用工具系列之爬虫】python爬取资讯数据
在大数据架构中,数据收集与数据存储占据了极为重要的地位,可以说是大数据的核心基础。而爬虫技术在这两大核心技术层次中占有了很大的比例。
本文实现一种简单快速的爬虫方法,其中用了代理ip,代理ip的获取可以参考我的这篇文章 【实用工具系列之爬虫】python实现爬取代理IP(防 ‘反爬虫’)。
szZack的文章
代理IP网站:xicidaili
具体方法详见 【实用工具系列之爬虫】python实现爬取代理IP(防 ‘反爬虫’) 。
输出的代理ip数据保存到 ‘proxy_ip.pkl’
本文以爬取小量财经数据为例子。
网站
地址:http://xxx
爬取内容
url,title,click_number,html_content
保存数据为csv,格式如下:
url,title,click_number,html_content,crawl_time
szZack的文章
实战
环境
import crawl_proxy_ip
import pandas as pd
import re, time, sys, os, random
import telnetlib
import requests
global url_set
url_set = {}
def crawl_finance_news(start_url):
#提取数据格式:url,title,click_number,html_content,crawl_time
proxy_ip_list = crawl_proxy_ip.load_proxy_ip('proxy_ip.pkl')
#爬取首页
start_html = crawl_web_data(start_url, proxy_ip_list)
#open('tmp.txt', 'w').write(start_html)
global url_set
url_set[start_url] = 0
#提取第一层web
web_content_list = extract_web_content(start_html, proxy_ip_list)
#提取第二层web
length = len(web_content_list)
for i in range(length):
if len(web_content_list[i][2]) == 0:
html = crawl_web_data(web_content_list[i][0], proxy_ip_list)
web_content_list += extract_web_content(html, proxy_ip_list)
if len(web_content_list) > 1000:#仅仅是测试
break
#提取第3层web
length = len(web_content_list)
for i in range(length):
if len(web_content_list[i][2]) == 0:
html = crawl_web_data(web_content_list[i][0], proxy_ip_list)
web_content_list += extract_web_content(html, proxy_ip_list)
if len(web_content_list) > 1000:#仅仅是测试
break
#保存数据
columns = ['url', 'title', 'click_number', 'html_content', 'crawl_time']
df = pd.DataFrame(columns = columns, data = web_content_list)
df.to_csv('finance_data.csv', encoding='utf-8')
print('data_len:', len(web_content_list))
def crawl_web_data(url, proxy_ip_list):
proxy_ip_dict = random.choice(proxy_ip_list)
if len(proxy_ip_list) == 0:
return ''
proxy_ip_dict = proxy_ip_list[0]
try:
html = download_by_proxy(url, proxy_ip_dict)
print(url, 'ok')
except Exception as e:
#print('50 e', e)
#删除无效的ip
index = proxy_ip_list.index(proxy_ip_dict)
proxy_ip_list.pop(index)
print('proxy_ip_list', len(proxy_ip_list))
return crawl_web_data(url, proxy_ip_list)
return html
def download_by_proxy(url, proxies):
headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.103 Safari/537.36', 'Connection':'close'}
response = requests.get(url=url, proxies=proxies, headers=headers, timeout=10)
response.encoding = 'utf-8'
html = response.text
return html
def extract_web_content(html, proxy_ip_list):
#提取数据格式:url,title,click_number,html_content, crawl_time
web_content_list = []
html_content = html
html = html.replace(' target ="_blank"', '')
html = html.replace(' ', '')
html = html.replace('\r', '')
html = html.replace('\n', '')
html = html.replace('\t', '')
html = html.replace('"target="_blank', '')
#证监会:拟对证券违法行为提高刑期上限
res = re.search('href="(http[^"><]*finance[^"><]*)">([^<]*)<', html)#finance 必须是金融资讯
while res is not None:
url, title = res.groups()
#print('url, title', url, title)
global url_set
if url in url_set:#防止重复
html = html.replace('href="%s">%s<' %(url, title), '')
res = re.search('href="(http[^"><]*finance[^"><]*)">([^<]*)<', html)
continue
else:
url_set[url] = 0
click_number = get_click_number(url, proxy_ip_list)
#print('click_number', click_number)
now_time = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())
if len(click_number) == 0:#仅保留正文
html_content = ''
web_content_list.append([url, title, click_number, html_content, now_time])
if len(web_content_list) > 200:#test 每页最多爬取200条
break
html = html.replace('href="%s">%s<' %(url, title), '')
res = re.search('href="(http[^"><]*finance[^"><]*)">([^<]*)<', html)
return web_content_list
[szZack的文章](https://blog.csdn.net/zengNLP?type=blog)
def get_click_number(url, proxy_ip_list):
html = crawl_web_data(url, proxy_ip_list)
#4297
res = re.search('(\d{1,})', html)
if res is not None:
return res.groups()[0]
return ''
if __name__ == '__main__':
#xx网:xxx/
#用法:python crawl_finance_news.py 'xxx/'
if len(sys.argv) == 2:
crawl_finance_news(sys.argv[1])
5.代码说明
1、先爬取代理ip:python crawl_proxy_ip.py
2、爬取财经新闻:python crawl_finance_news.py ‘xxx/’
3、这里仅仅是测试,爬取1000条就结束
4、数据保存到:finance_data.csv
szZack的文章
szZack的文章