爬虫代理池Python3WebSpider源代码测试过程解析
这篇文章主要介绍了爬虫代理池Python3WebSpider源代码测试过程解析,文中通过示例代码介绍的非常详细,对大家的学习或者工作具有一定的参考学习价值,需要的朋友可以参考下
元类属性的使用
主要关于元类的使用
通过获取由元类生成的爬虫抓取类的部分属性.这里为抓取函数,以相同的字符开头的抓取函数,生成属性列表,这样可以持续调用.目的是可以仅仅添加不同的抓取函数抓取不同的网站,而类的其他部分不用做调整.
部分代码:
class ProxyMetaclass(type): def __new__(cls, name, bases, attrs): count = 0 attrs['__CrawlFunc__'] = [] for k, v in attrs.items(): if 'crawl_' in k: attrs['__CrawlFunc__'].append(k) count += 1 attrs['__CrawlFuncCount__'] = count return type.__new__(cls, name, bases, attrs) class Crawler(object, metaclass=ProxyMetaclass): def get_proxies(self, callback): proxies = [] for proxy in eval("self.{}()".format(callback)): print('成功获取到代理', proxy) proxies.append(proxy) return proxies def crawl_daili66(self, page_count=4): """ 获取代理66 :param page_count: 页码 :return: 代理 """ start_url = 'http://www.66ip.cn/{}.html' urls = [start_url.format(page) for page in range(1, page_count + 1)] for url in urls: print('Crawling', url) html = get_page(url) if html: doc = pq(html) trs = doc('.containerbox table tr:gt(0)').items() for tr in trs: ip = tr.find('td:nth-child(1)').text() port = tr.find('td:nth-child(2)').text() yield ':'.join([ip, port])
测试方法
#!/usr/bin/env python # -*- coding: utf-8 -*- # @Time : 12/19/19 4:10 PM # @Author : yon # @Email : @qq.com # @File : test import json import re from pyquery import PyQuery as pq class ProxyMetaclass(type): def __new__(cls, name, bases, attrs): count = 0 attrs['__CrawlFunc__'] = [] for k, v in attrs.items(): print("打印k") print(k) print("打印v") print(v) if 'crawl_' in k: attrs['__CrawlFunc__'].append(k) count += 1 attrs['__CrawlFuncCount__'] = count return type.__new__(cls, name, bases, attrs) class Crawler(object, metaclass=ProxyMetaclass): def get_proxies(self, callback): proxies = [] for proxy in eval("self.{}()".format(callback)): print('成功获取到代理', proxy) proxies.append(proxy) return proxies def crawl_daili66(self, page_count=4): """ 获取代理66 :param page_count: 页码 :return: 代理 """ start_url = 'http://www.66ip.cn/{}.html' urls = [start_url.format(page) for page in range(1, page_count + 1)] for url in urls: print('Crawling', url) html = get_page(url) if html: doc = pq(html) trs = doc('.containerbox table tr:gt(0)').items() for tr in trs: ip = tr.find('td:nth-child(1)').text() port = tr.find('td:nth-child(2)').text() yield ':'.join([ip, port]) def crawl_ip3366(self): for page in range(1, 4): start_url = 'http://www.ip3366.net/free/?stype=1&page={}'.format(page) html = get_page(start_url) ip_address = re.compile('<tr>\s*<td>(.*?)</td>\s*<td>(.*?)</td>') # \s * 匹配空格,起到换行作用 re_ip_address = ip_address.findall(html) for address, port in re_ip_address: result = address + ':' + port yield result.replace(' ', '') def crawl_kuaidaili(self): for i in range(1, 4): start_url = 'http://www.kuaidaili.com/free/inha/{}/'.format(i) html = get_page(start_url) if html: ip_address = re.compile('<td data-title="IP">(.*?)</td>') re_ip_address = ip_address.findall(html) port = re.compile('<td data-title="PORT">(.*?)</td>') re_port = port.findall(html) for address, port in zip(re_ip_address, re_port): address_port = address + ':' + port yield address_port.replace(' ', '') def crawl_xicidaili(self): for i in range(1, 3): start_url = 'http://www.xicidaili.com/nn/{}'.format(i) headers = { 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8', 'Cookie': '_free_proxy_session=BAh7B0kiD3Nlc3Npb25faWQGOgZFVEkiJWRjYzc5MmM1MTBiMDMzYTUzNTZjNzA4NjBhNWRjZjliBjsAVEkiEF9jc3JmX3Rva2VuBjsARkkiMUp6S2tXT3g5a0FCT01ndzlmWWZqRVJNek1WanRuUDBCbTJUN21GMTBKd3M9BjsARg%3D%3D--2a69429cb2115c6a0cc9a86e0ebe2800c0d471b3', 'Host': 'www.xicidaili.com', 'Referer': 'http://www.xicidaili.com/nn/3', 'Upgrade-Insecure-Requests': '1', } html = get_page(start_url, options=headers) if html: find_trs = re.compile('<tr class.*?>(.*?)</tr>', re.S) trs = find_trs.findall(html) for tr in trs: find_ip = re.compile('<td>(\d+\.\d+\.\d+\.\d+)</td>') re_ip_address = find_ip.findall(tr) find_port = re.compile('<td>(\d+)</td>') re_port = find_port.findall(tr) for address, port in zip(re_ip_address, re_port): address_port = address + ':' + port yield address_port.replace(' ', '') def crawl_ip3366(self): for i in range(1, 4): start_url = 'http://www.ip3366.net/?stype=1&page={}'.format(i) html = get_page(start_url) if html: find_tr = re.compile('<tr>(.*?)</tr>', re.S) trs = find_tr.findall(html) for s in range(1, len(trs)): find_ip = re.compile('<td>(\d+\.\d+\.\d+\.\d+)</td>') re_ip_address = find_ip.findall(trs[s]) find_port = re.compile('<td>(\d+)</td>') re_port = find_port.findall(trs[s]) for address, port in zip(re_ip_address, re_port): address_port = address + ':' + port yield address_port.replace(' ', '') def crawl_iphai(self): start_url = 'http://www.iphai.com/' html = get_page(start_url) if html: find_tr = re.compile('<tr>(.*?)</tr>', re.S) trs = find_tr.findall(html) for s in range(1, len(trs)): find_ip = re.compile('<td>\s+(\d+\.\d+\.\d+\.\d+)\s+</td>', re.S) re_ip_address = find_ip.findall(trs[s]) find_port = re.compile('<td>\s+(\d+)\s+</td>', re.S) re_port = find_port.findall(trs[s]) for address, port in zip(re_ip_address, re_port): address_port = address + ':' + port yield address_port.replace(' ', '') def crawl_data5u(self): start_url = 'http://www.data5u.com/free/gngn/index.shtml' headers = { 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8', 'Accept-Encoding': 'gzip, deflate', 'Accept-Language': 'en-US,en;q=0.9,zh-CN;q=0.8,zh;q=0.7', 'Cache-Control': 'max-age=0', 'Connection': 'keep-alive', 'Cookie': 'JSESSIONID=47AA0C887112A2D83EE040405F837A86', 'Host': 'www.data5u.com', 'Referer': 'http://www.data5u.com/free/index.shtml', 'Upgrade-Insecure-Requests': '1', 'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.108 Safari/537.36', } html = get_page(start_url, options=headers) if html: ip_address = re.compile('<span><li>(\d+\.\d+\.\d+\.\d+)</li>.*?<li class=\"port.*?>(\d+)</li>', re.S) re_ip_address = ip_address.findall(html) for address, port in re_ip_address: result = address + ':' + port yield result.replace(' ', '') class Getter(): def __init__(self): self.crawler = Crawler() def run(self): print('获取器开始执行') for callback_label in range(self.crawler.__CrawlFuncCount__): print(callback_label) callback = self.crawler.__CrawlFunc__[callback_label] print(callback) # # 获取代理 # proxies = self.crawler.get_proxies(callback) # sys.stdout.flush() # for proxy in proxies: # self.redis.add(proxy) if __name__ == '__main__': get = Getter() get.run()
测试结果
/home/baixiaoxu/PycharmProjects/pytthon-tt/venv/bin/python /home/baixiaoxu/PycharmProjects/pytthon-tt/proxypool/test.py 打印k __module__ 打印v __main__ 打印k __qualname__ 打印v Crawler 打印k get_proxies 打印v <function Crawler.get_proxies at 0x7f905ca5a598> 打印k crawl_daili66 打印v <function Crawler.crawl_daili66 at 0x7f905ca5a620> 打印k crawl_ip3366 打印v <function Crawler.crawl_ip3366 at 0x7f905ca5a840> 打印k crawl_kuaidaili 打印v <function Crawler.crawl_kuaidaili at 0x7f905ca5a730> 打印k crawl_xicidaili 打印v <function Crawler.crawl_xicidaili at 0x7f905ca5a7b8> 打印k crawl_iphai 打印v <function Crawler.crawl_iphai at 0x7f905ca5a6a8> 打印k crawl_data5u 打印v <function Crawler.crawl_data5u at 0x7f905ca5a8c8> 打印k __CrawlFunc__ 打印v ['crawl_daili66', 'crawl_ip3366', 'crawl_kuaidaili', 'crawl_xicidaili', 'crawl_iphai', 'crawl_data5u'] 获取器开始执行 0 crawl_daili66 1 crawl_ip3366 2 crawl_kuaidaili 3 crawl_xicidaili 4 crawl_iphai 5 crawl_data5u 进程完成,退出码 0
以上就是本文的全部内容,希望对大家的学习有所帮助,也希望大家多多支持我们。
赞 (0)