日爬百万数据的域名限制、url的清洗和管理

一、域名去重
1、检测开头：link.startswith('http')

txt = "Hello, welcome to my world."

x = txt.startswith("Hello")

print(x)
#如果字符串以指定的值开头，则 startswith() 方法返回 True，否则返回 False。

string.startswith(value, start, end)

2、tldextract模块准确获取域名和后缀

　　tldextract是一个第三方模块,意思就是Top Level Domain extract，即顶级域名提取
　　使用时 需要安装,命令如下
　　pip install tldextract
　　URL的结构，news.baidu.com 里面的news.baidu.com叫做host，它是注册域名baidu.com的子域名，而com就是顶级域名TLD。

　　

　　　　 tld = tldextract.extract(link)
        if tld.domain == 'baidu':
            continue
        news_links.append(link)

 参考链接：https://www.yuanrenxue.com/crawler/news-crawler.html

二、url的清洗

　　1、判断网页种类（静态网页？图片？等等的内容）
　　2、去除外部的链接（广告）
　 　
　　

#Python find() 方法检测字符串中是否包含子字符串 str ，如果指定 beg（开始） 和 end（结束） 范围，则检查是否包含在指定范围内，如果包含子字符串返回开始的索引值，否则返回-1。

g_bin_postfix = set([
    'exe', 'doc', 'docx', 'xls', 'xlsx', 'ppt', 'pptx',
    'pdf',
    'jpg', 'png', 'bmp', 'jpeg', 'gif',
    'zip', 'rar', 'tar', 'bz2', '7z', 'gz',
    'flv', 'mp4', 'avi', 'wmv', 'mkv',
    'apk',
])

g_news_postfix = [
    '.html?', '.htm?', '.shtml?',
    '.shtm?',
]

def clean_url(url):
    # 1. 是否为合法的http url
    if not url.startswith('http'):
        return ''
    # 2. 去掉静态化url后面的参数
    for np in g_news_postfix:
        p = url.find(np)
        if p > -1:
            p = url.find('?')
            url = url[:p]
            return url
    # 3. 不下载二进制类内容的链接
    up = urlparse.urlparse(url)
    path = up.path
    if not path:
        path = '/'
    postfix = path.split('.')[-1].lower()
    if postfix in g_bin_postfix:
        return ''

    # 4. 去掉标识流量来源的参数
    # badquery = ['spm', 'utm_source', 'utm_source', 'utm_medium', 'utm_campaign']
    good_queries = []
    for query in up.query.split('&'):
        qv = query.split('=')
        if qv[0].startswith('spm') or qv[0].startswith('utm_'):
            continue
        if len(qv) == 1:
            continue
        good_queries.append(query)
    query = '&'.join(good_queries)
    url = urlparse.urlunparse((
        up.scheme,
        up.netloc,
        path,
        up.params,
        query,
        ''  #  crawler do not care fragment
    ))
    return url

　　3、url的管理（urlpool）
　　

mport pickle
import leveldb
import time
import urllib.parse as urlparse

class UrlPool:
    '''URL Pool for crawler to manage URLs
    '''

    def __init__(self, pool_name):
        self.name = pool_name
        self.db = UrlDB(pool_name)

        self.waiting = {}  # {host: set([urls]), } 按host分组，记录等待下载的URL
        self.pending = {}  # {url: pended_time, } 记录已被取出（self.pop()）但还未被更新状态（正在下载）的URL
        self.failure = {}  # {url: times,} 记录失败的URL的次数
        self.failure_threshold = 3
        self.pending_threshold = 10  # pending的最大时间，过期要重新下载
        self.waiting_count = 0  # self.waiting 字典里面的url的个数
        self.max_hosts = ['', 0]  # [host: url_count] 目前pool中url最多的host及其url数量
        self.hub_pool = {}  # {url: last_query_time, }  存放hub url
        self.hub_refresh_span = 0
        self.load_cache()

    def __del__(self):
        self.dump_cache()

    def load_cache(self,):
        path = self.name + '.pkl'
        try:
            with open(path, 'rb') as f:
                self.waiting = pickle.load(f)
            cc = [len(v) for k, v in self.waiting.items()]
            print('saved pool loaded! urls:', sum(cc))
        except:
            pass

    def dump_cache(self):
        path = self.name + '.pkl'
        try:
            with open(path, 'wb') as f:
                pickle.dump(self.waiting, f)
            print('self.waiting saved!')
        except:
            pass

    def set_hubs(self, urls, hub_refresh_span):
        self.hub_refresh_span = hub_refresh_span
        self.hub_pool = {}
        for url in urls:
            self.hub_pool[url] = 0

    def set_status(self, url, status_code):
        if url in self.pending:
            self.pending.pop(url)

        if status_code == 200:
            self.db.set_success(url)
            return
        if status_code == 404:
            self.db.set_failure(url)
            return
        if url in self.failure:
            self.failure[url] += 1
            if self.failure[url] > self.failure_threshold:
                self.db.set_failure(url)
                self.failure.pop(url)
            else:
                self.add(url)
        else:
            self.failure[url] = 1
            self.add(url)

    def push_to_pool(self, url):
        host = urlparse.urlparse(url).netloc
        if not host or '.' not in host:
            print('try to push_to_pool with bad url:', url, ', len of ur:', len(url))
            return False
        if host in self.waiting:
            if url in self.waiting[host]:
                return True
            self.waiting[host].add(url)
            if len(self.waiting[host]) > self.max_hosts[1]:
                self.max_hosts[1] = len(self.waiting[host])
                self.max_hosts[0] = host
        else:
            self.waiting[host] = set([url])
        self.waiting_count += 1
        return True

    def add(self, url, always=False):
        if always:
            return self.push_to_pool(url)
        pended_time = self.pending.get(url, 0)
        if time.time() - pended_time < self.pending_threshold:
            print('being downloading:', url)
            return
        if self.db.has(url):
            return
        if pended_time:
            self.pending.pop(url)
        return self.push_to_pool(url)

    def addmany(self, urls, always=False):
        if isinstance(urls, str):
            print('urls is a str !!!!', urls)
            self.add(urls, always)
        else:
            for url in urls:
                self.add(url, always)

    def pop(self, count, hub_percent=50):
        print('\n\tmax of host:', self.max_hosts)

        # 取出的url有两种类型：hub=1, 普通=0
        url_attr_url = 0
        url_attr_hub = 1
        # 1. 首先取出hub，保证获取hub里面的最新url.
        hubs = {}
        hub_count = count * hub_percent // 100
        for hub in self.hub_pool:
            span = time.time() - self.hub_pool[hub]
            if span < self.hub_refresh_span:
                continue
            hubs[hub] = url_attr_hub # 1 means hub-url
            self.hub_pool[hub] = time.time()
            if len(hubs) >= hub_count:
                break

        # 2. 再取出普通url
        left_count = count - len(hubs)
        urls = {}
        for host in self.waiting:
            if not self.waiting[host]:
                continue
            url = self.waiting[host].pop()
            urls[url] = url_attr_url
            self.pending[url] = time.time()
            if self.max_hosts[0] == host:
                self.max_hosts[1] -= 1
            if len(urls) >= left_count:
                break
        self.waiting_count -= len(urls)
        print('To pop:%s, hubs: %s, urls: %s, hosts:%s' % (count, len(hubs), len(urls), len(self.waiting)))
        urls.update(hubs)
        return urls

    def size(self,):
        return self.waiting_count

    def empty(self,):
        return self.waiting_count == 0

　　来自猿人学官网