python 小爬虫爬取博客文章初体验

最近学习 python 走火入魔，趁着热情继续初级体验一下下爬虫，以前用 java也写过，这里还是最初级的爬取html，都没有用html解析器，正则等。。。而且一直在循环效率肯定### 很低下

import urllib.request as urllib2

import random
ua_list = [
        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv2.0.1) Gecko/20100101 Firefox/4.0.1",
        "Mozilla/5.0 (Windows NT 6.1; rv2.0.1) Gecko/20100101 Firefox/4.0.1",
        "Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; en) Presto/2.8.131 Version/11.11",
        "Opera/9.80 (Windows NT 6.1; U; en) Presto/2.8.131 Version/11.11",
        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11"
    ]

ua_agent = random.choice(ua_list)

# ua_agent_dict = {'User-Agent':ua_agent}

# print(ua_agent_dict)
# request = urllib2.Request(url=url)
# request.add_header(**ua_agent_dict)

def checkPageExists(url,ua_agent):
    request = urllib2.Request(url=url)
    request.add_header('User_Agent',ua_agent)
    try:
        code = urllib2.urlopen(request).code
    except IOError as httperr:
        return False
    return True if code == 200 else False
checkPageExists('https://www.cnblogs.com/Frank99/p/91111024.html',ua_agent=ua_agent)
url_prefix = 'https://www.cnblogs.com/Frank99/p/'
url_subfix = '.html'
# https://www.cnblogs.com/Frank99/p/
def getHtml(url,ua_agent):
    request = urllib2.Request(url=url)
    request.add_header('User_Agent',ua_agent)
    print('正在从页面 {} 读取数据......'.format(url))
    response = urllib2.urlopen(request)
    print('从页面 {} 读取数据完成......'.format(url))
    return response.read()

def write_html2file(html,file_name):
    with open(file_name,'w',encoding='utf-8') as f:
        print('开始保存文件{}......'.format(file_name))
        f.write(html.decode())
        print('保存文件{}完成......'.format(file_name))

if __name__ == '__main__':
    list(map(lambda i:write_html2file(getHtml(url_prefix+str(i)+url_subfix,ua_agent=ua_agent),str(i)+url_subfix),[i for i in range(9111123,9111125) if checkPageExists(url_prefix+str(i)+url_subfix,ua_agent=ua_agent)]))
    
# for i in range(9111123,9111125):
#     url = url_prefix+str(i)+url_subfix
#     file_name = str(i)+url_subfix
#     if checkPageExists(url,ua_agent=ua_agent):
#         html = getHtml(url,ua_agent=ua_agent)
#         write_html2file(html,file_name)

import urllib.request as urllib2

import random
ua_list = [
        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv2.0.1) Gecko/20100101 Firefox/4.0.1",
        "Mozilla/5.0 (Windows NT 6.1; rv2.0.1) Gecko/20100101 Firefox/4.0.1",
        "Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; en) Presto/2.8.131 Version/11.11",
        "Opera/9.80 (Windows NT 6.1; U; en) Presto/2.8.131 Version/11.11",
        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11"
    ]

ua_agent = random.choice(ua_list)

# ua_agent_dict = {'User-Agent':ua_agent}

# print(ua_agent_dict)
# request = urllib2.Request(url=url)
# request.add_header(**ua_agent_dict)

def checkPageExists(url,ua_agent):
    request = urllib2.Request(url=url)
    request.add_header('User_Agent',ua_agent)
    try:
        code = urllib2.urlopen(request).code
    except IOError as httperr:
        return False
    return True if code == 200 else False
# checkPageExists('https://www.cnblogs.com/Frank99/p/91111024.html',ua_agent=ua_agent)

# https://www.cnblogs.com/Frank99/p/
def getHtml(url,ua_agent):
    request = urllib2.Request(url=url)
    request.add_header('User_Agent',ua_agent)
    print('正在从页面 {} 读取数据......'.format(url))
    response = urllib2.urlopen(request)
    print('从页面 {} 读取数据完成......'.format(url))
    return response.read()

def write_html2file(html,file_name):
    with open(file_name,'w',encoding='utf-8') as f:
        print('开始保存文件{}......'.format(file_name))
        f.write(html.decode())
        print('保存文件{}完成......'.format(file_name))

if __name__ == '__main__':
#     url_prefix = 'https://www.cnblogs.com/Frank99/p/'
#     url_subfix = '.html'
    url_prefix = input('请输入要被爬取的资源地址前缀...')
    url_subfix = input('请输入要被爬取的资源地址后缀...')
    list(map(lambda i:write_html2file(getHtml(url_prefix+str(i)+url_subfix,ua_agent=ua_agent),str(i)+url_subfix),(i for i in range(5400017,9111125) if checkPageExists(url_prefix+str(i)+url_subfix,ua_agent=ua_agent))))
    
for i in range(9111123,9111125):
    url = url_prefix+str(i)+url_subfix
    file_name = str(i)+url_subfix
    if checkPageExists(url,ua_agent=ua_agent):
        html = getHtml(url,ua_agent=ua_agent)
        write_html2file(html,file_name)

刚虾米。。。。

# https://tieba.baidu.com/f?kw=%E5%B8%83%E8%A2%8B%E6%88%8F&ie=utf-8&pn=100
# https://tieba.baidu.com/f?kw=%E5%B8%83%E8%A2%8B%E6%88%8F&ie=utf-8&pn=10
import urllib.request as urllib2
from urllib import parse
import random
class TieBa(object):
    def __init__(self,**kw):
        for key in kw:
            if key == 'name':
                self.__name = kw[key]
            elif key == 'start':
                self.__start = kw[key]
            elif key == 'end':
                self.__end = kw[key]
#             elif key == 'url':
#                 self.__url = kw[key]
    def set_name(self,name):
        self.__name = name
    def get_name(self):
        return self.__name
    def set_start(self,start):
        self.__start = start
    def get_start(self):
        return self.__start
    def set_end(self,end):
        self.__end = end
    def get_end(self):
        return self.__end
   
    def spider_html(self):
        '''
        爬取网页信息
        '''
        name=self.__name
        start=self.__start
        end=self.__end
        words ={'kw':name}
        name = parse.urlencode(words)
        url_prefix = r'https://tieba.baidu.com/f?'
        url_suffix =r'&ie=utf-8&pn='
        url = url_prefix+name+url_suffix
        start = int(start)
        end = int(end)
        for page in range(start,end):
            url = url+str(page)
            print(url)
            html = self.__get_html(page,url)
            file_name = '{}-{}.html'.format(words['kw'],page)
            self.__write2file(file_name,html)
            
    def __get_html(self,page,url):
        ua_list = ["Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv2.0.1) Gecko/20100101 Firefox/4.0.1",
                    "Mozilla/5.0 (Windows NT 6.1; rv2.0.1) Gecko/20100101 Firefox/4.0.1",
                    "Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; en) Presto/2.8.131 Version/11.11",
                    "Opera/9.80 (Windows NT 6.1; U; en) Presto/2.8.131 Version/11.11",
                    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11"]
        request = urllib2.Request(url)
        request.add_header('User-Agent',random.choice(ua_list))
        response = urllib2.urlopen(request)
        print('第 {} 正在爬取'.format(page))
        html = response.read()
        print('第 {} 爬取完成'.format(page))
        return html
    
    def __write2file(self,file_name,html):
        print('开始保存html为文件...')
        with open(file_name,'w',encoding='utf-8') as f:
            f.write(html.decode())
            print('保存html为文件成功...')
if __name__ =='__main__':
    tb = TieBa()
    tb.set_name(input('请输入贴吧名!'))
    tb.set_start(input('请输入从第几页开始: '))
    tb.set_end(input('请输入从第几页结束: '))
    tb.spider_html()

Condition ，用来同步 线程 ， 底部还是 Lock , RLock （在一个线程中可以多次重入）

from threading import (Thread,Condition)

class XiaoAI(Thread):
    def __init__(self,cond,name='小爱'):
        super().__init__(name=name)
        self.cond = cond

    def run(self):
        with self.cond:
            self.cond.wait()
            print('{name}: 在'.format(name=self.name))
            self.cond.notify()

            self.cond.wait()
            print('{name}: 好啊!'.format(name=self.name))
            self.cond.notify()
class TianMao(Thread):
    def __init__(self,cond,name='天猫'):
        super().__init__(name=name)
        self.cond = cond

    def run(self):
        with cond:
            print('{name}:小爱同学'.format(name=self.name))
            self.cond.notify()
            self.cond.wait()
            print('{name}: 我们来对古诗吧。'.format(name=self.name))
            self.cond.notify()
            self.cond.wait()


if __name__ == '__main__':
    cond = Condition()
    xiao = XiaoAI(cond)
    tian = TianMao(cond)

    xiao.start()  # 这里 start 顺序千万要注意
    tian.start()
    xiao.join()
    tian.join()

from threading import (Thread,Semaphore)
from urllib.parse import urlencode
import requests
import chardet
import logging
from os import path
import random
import re
logging.basicConfig(level=logging.DEBUG)
# https://tieba.baidu.com/f?kw=%E5%B8%83%E8%A2%8B%E6%88%8F&ie=utf-8&pn=100

class TieBaSpider(Thread):
    def __init__(self,url,sem,name='TieBaSpider'):
        super(TieBaSpider,self).__init__(name=name)
        self.url = url
        self.sem = sem

    def _save(self,text):
        parent_dir = r'D:\tieba'
        file_name = path.join(parent_dir,path.split(re.sub(r'[%|=|&|?]','',self.url))[1])+'.html'
        with open(file_name,'w',encoding='utf-8') as fw:
            fw.write(text)
            fw.flush()
        return 1


    def run(self):
        # ua_list = ["Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv2.0.1) Gecko/20100101 Firefox/4.0.1",
        #            "Mozilla/5.0 (Windows NT 6.1; rv2.0.1) Gecko/20100101 Firefox/4.0.1",
        #            "Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; en) Presto/2.8.131 Version/11.11",
        #            "Opera/9.80 (Windows NT 6.1; U; en) Presto/2.8.131 Version/11.11",
        #            "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11"]
        # header = {'User-Agent':random.choice(ua_list)}
        response = requests.get(self.url)#header=header)
        content = response.content
        logging.info(response.encoding)
        # result = chardet.detect(content)
        # logging.info(result)
        # code = result.get('encoding','utf-8')
        self._save(content.decode(response.encoding))
        self.sem.release()

class UrlProducer(Thread):
    def __init__(self,tb_name,sem,pages_once=3,start_index=1,end_index=9):# end-start % pages_once == 0
        super(UrlProducer,self).__init__(name=tb_name)
        self.tb_name = urlencode(tb_name)
        self.sem = sem
        logging.info(self.tb_name)
        self.pages_once = pages_once
        self.start_index = start_index
        self.end_index = end_index

    def run(self):
        for page_idx in range(self.start_index,self.end_index+1):
            self.sem.acquire()
            url_prefix = r'https://tieba.baidu.com/f?'
            url_suffix = r'&fr=ala0&tpl='
            self.url = url_prefix+self.tb_name+url_suffix+str(page_idx)
            tb_spider = TieBaSpider(self.url,self.sem)
            tb_spider.start()


if __name__ == '__main__':
    kw_dict = dict(kw=r'国家地理')
    sem = Semaphore(3) # 控制一次并发 3 个线程
    url_producer = UrlProducer(kw_dict,sem=sem)
    url_producer.start()

    url_producer.join()

免费 ip 代理池

站大爷