多线程爬取笔趣阁免费小说全站爬取

Posted 2020-11-23 duanlinxiao

import threading,os,time,requests,pymongo,re
from queue import Queue
from lxml import etree
from bs4 import BeautifulSoup as BP
client = pymongo.MongoClient(host=‘localhost‘,port=27017)
mg = client[‘biquge‘]
def get_fenlei():
    """
    爬取图书全部分类
    :return:
    """
    collection = mg[‘biquge_info‘]
    url = ‘http://www.xxbqg5200.com/‘
    sp = requests.get(url=url,headers = headers,cookies=cookies)
    soup = BP(sp.text,‘lxml‘)
    fenlei_url = soup.select(‘#wrapper > div.nav > ul > li > a‘)
    list1 = []
    for i in fenlei_url:
        href_url = i[‘href‘]
        fenlei_name = i.get_text()
        if ‘‘.join(href_url).split(‘/‘)[1] != ‘sort‘:
            continue
        else:
            fenlei_href_url = ‘{}‘.format(‘http://www.xxbqg5200.com‘)+str(href_url)
            list1.append(fenlei_href_url)
            try:
                date = {‘fenlei_name‘:fenlei_name,‘fenlei_url‘:fenlei_href_url}
                collection.insert(date)
                print(‘{}{}‘.format(fenlei_name,‘》》》》》存储成功‘))
            except :
                print(‘{}‘.format(fenlei_name,‘存储失败‘))
    return list1
def get_page():
    """
    爬取全部分类的分页链接
    :return:
    """
    list1_url = get_fenlei()
    list_page = []
    a = 0
    for i in list1_url:
        a+=1
        page_url = ‘‘.join(i).split(‘/‘)[3]
        page_href_url = ‘{}‘.format(‘http://www.xxbqg5200.com/‘)+str(page_url)+str(‘/‘)+str(a)+str(‘_‘)
        for page in range(1,190):
            page_url = "{}".format(page_href_url)+str(page)+str(‘/‘)
            list_page.append(page_url)
    return list_page
def get_tushu_url():
    """
    爬取所有图书的链接
    :return:
    """
    global q,lock
    while not q.empty():
        lock.acquire()
        url = q.get()
        lock.release()
        print(url,‘###################################‘)
        collection = mg[‘biquge_info‘]
        list1 = []
        sp = requests.get(url=url,headers=headers,cookies=cookies)
        soup = BP(sp.text,‘lxml‘)
        tushu_url = soup.select(‘#newscontent > div.l > ul > li > span.s2 > a‘)
        if tushu_url:
            for tushu_href_url in tushu_url:
                tushu_name_url = tushu_href_url[‘href‘]
                tushu_name = tushu_href_url.get_text()
                list1.append(tushu_name_url)
                try:
                    date = {‘tushu_name‘:tushu_name,‘tushu_name_url‘:tushu_name_url}
                    collection.insert(date)
                    print(‘{}{}‘.format(tushu_name, ‘》》》》》存储成功‘))
                except :
                    print(‘{}‘.format(tushu_name,‘存储失败‘))
        else:
            pass
        """
        爬取章节所有链接
        """
        list2 = []
        for zhang_url in list1:
            response = requests.get(zhang_url,headers=headers,cookies=cookies)
            soup_zhang = BP(response.text,‘lxml‘)
            zhangjie_url = soup_zhang.select(‘#list > dl > dd > a‘)
            for zhang_href in zhangjie_url:
                zhangjie_href = zhang_href[‘href‘]
                zhangjie_name = zhang_href.get_text()
                # print(zhangjie_name,‘)))))))))))‘,zhangjie_href)
                content_url = ‘{}‘.format(‘http://www.xxbqg5200.com‘)+str(zhangjie_href)
                list2.append(content_url)
                try:
                    date_zhangjie = {‘zhangjie_name‘:zhangjie_name,‘zhangjie_href‘:zhangjie_href}
                    collection.insert(date_zhangjie)
                    print(‘{}{}‘.format(zhangjie_name, ‘》》》》》存储成功‘))
                except :
                    print(‘{}‘.format(zhangjie_name,‘存储失败‘))
        """
        爬取章节下的所有内容
        """
        content_sql = mg[‘tushu_content‘]
        for content_list_url in list2:
            response1 = requests.get(content_list_url,headers=headers,cookies=cookies)
            soup_content = BP(response1.text,‘lxml‘)
            content_nei = soup_content.select(‘#content‘)
            for text_content in content_nei:
                filter_content = re.findall(‘[u4e00-u9fa5a-zA-Z0-9]+‘, text_content, re.S)  # 只要字符串中的中文，字母，数字
                filter_text_content = "".join(filter_content)
                try:
                    date_content = {‘content‘:filter_text_content}
                    content_sql.insert(date_content)
                    print(‘{}‘.format( ‘》》》》》存储成功‘))
                except :
                    print(‘{}‘.format(‘存储失败‘))
if __name__ == ‘__main__‘:
    headers = {
        ‘User-Agent‘: ‘Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (Khtml, like Gecko) Chrome/75.0.3770.142 Safari/537.36‘,
        ‘Referer‘: ‘http://www.xxbqg5200.com/register.php?do=submit‘,

    }
    cookies = {
        ‘Cookie‘: ‘Hm_lvt_bbb2110ecd75330bec79c7868b24e681=1575524043; PHPSESSID=03pt092b5nb8qsdl6pk425kh87; jieqiUserInfo=jieqiUserId%3D1912%2CjieqiUserName%3Dduanyibo%2CjieqiUserGroup%3D3%2CjieqiUserName_un%3Dduanyibo%2CjieqiUserLogin%3D1575524132; jieqiVisitInfo=jieqiUserLogin%3D1575524132%2CjieqiUserId%3D1912; Hm_lpvt_bbb2110ecd75330bec79c7868b24e681=1575524140‘,

    }
    q = Queue()
    lock = threading.Lock()
    list_url = get_page()
    for i in list_url:
        q.put(i)
    for i in range(10):
        t = threading.Thread(target=get_tushu_url)
        t.start()