def url_manager_proc(self, url_q: Queue, conn_q: Queue, root_url):
print('url manager process start...')
url_manager = UrlManager()
url_manager.add_new_url(root_url)
print('url manager process started...')
while True:
while url_manager.has_new_url():
new_url = url_manager.get_new_url()
print('new_url', new_url)
# 将新的URL发给工作节点
url_q.put(new_url)
# 加一个判断条件, 当爬取2000个链接后就关闭, 并保存进度
if url_manager.old_url_size() > 2000:
# 通知爬行节点工作结束
url_q.put('end')
print('控制节点发起结束通知')
# 关闭管理节点, 同事存储set状态
url_manager.save_process(path.join('dist', 'new_urls.txt'),
url_manager.new_urls)
url_manager.save_process(path.join('dist', 'old_urls.txt'),
url_manager.old_urls)
return
# 将从result_solve_proc 获取到的URL添加到URL管理器
try:
if not conn_q.empty():
urls = conn_q.get()
url_manager.add_new_urls(urls)
except BaseException as e:
time.sleep(0.1)
class SpiderMain(object):
def __init__(self):
self.urls = UrlManager()
self.downloader = HtmlDownloader()
self.parser = HtmlParser()
self.outputer = HtmlOutputer()
def craw(self, url):
count = 1
self.urls.add_new_url(url)
while self.urls.has_new_url():
try:
new_url = self.urls.get_new_url()
html_cont = self.downloader.download(new_url)
new_urls, html_data = self.parser.parse(new_url, html_cont)
self.urls.add_new_urls(new_urls)
self.outputer.collect_data(html_data)
print "%d craw success : %s" % (count, new_url)
if count >= 10:
break
count = count + 1
except Exception as e:
print str(e)
print "%d craw failed : %s" % (count, new_url)
self.outputer.output()
class SpiderMain(object):
def __init__(self):
self.urls = UrlManager()
self.downloader = HtmlDownloader()
self.parser = HtmlParser()
self.output = HtmlOutputer()
def craw(self, root_url, page_amount=5, time_sleep=None):
count = 1
# 添加第一个待爬取url
self.urls.add_new_url(root_url)
# 如果集合中有url, 就取出一个url 请求， 没有链接则跳出。
while self.urls.has_new_url():
try:
# 开始爬取
new_url = self.urls.get_new_url()
print(f'craw{count}:{new_url}')
# 请求url, 返回html
html_content = self.downloader.download(new_url)
# xpath 解析html，得到需要的数据
new_urls, new_data = self.parser.parse(html_content)
# 一个词条页面上关联的a 链表列表加入到url 管理器中待爬取
self.urls.add_new_urls(new_urls)
self.output.collect_data(new_url, new_data)
count += 1
if count > page_amount:
break
time.sleep(2)
except Exception as e:
print(e)
print(f'抓取失败:{new_url}')
self.output.output_html()
class Scheduler(object):
def __init__(self):
self.url_manager = UrlManager()
self.downloader = Downloader()
self.parser = Parser()
self.data_output = DadaOutput()
def crawl(self, start_url, max_page):
self.url_manager.add_new_url(start_url)
while self.url_manager.has_url(
) and self.url_manager.old_url_size() < max_page:
page_url = self.url_manager.get_new_url()
page_html = self.downloader.down(page_url)
new_urls, new_data = self.parser.parse(start_url, page_html)
self.url_manager.add_new_urls(new_urls)
self.data_output.store_data(new_data)
self.data_output.output_html()
print('第%s条数据写入' % (self.url_manager.old_url_size()))
class Spider():
def __init__(self):
self.manager = UrlManager()
self.downloader = HTMLDownloader()
self.parser = HTMLParser()
self.output = DataOutput()
def crawl(self, root_url):
self.manager.add_new_url(root_url)
while (self.manager.has_new_url()
and self.manager.old_urls_size() < 50):
try:
new_url = self.manager.get_new_url()
html = self.downloader.download(new_url)
new_urls, data = self.parser.parser(new_url, html)
self.manager.add_new_urls(new_urls)
self.output.store_data(data)
print("已经抓取%s个链接" % self.manager.old_urls_size())
except Exception as e:
print(e)
self.output.output_html()
class SpiderMain:
def __init__(self):
self.url_manager = UrlManager()
self.html_downloader = HtmlDownloader()
self.html_parser = HtmlParser()
self.data_storage = DataStorage()
def start(self):
"""
爬虫的主启动方法
:return:
"""
self.url_manager.add_new_url(
"http://127.0.0.1:8848/xiaomi-master/index.html")
# 从url管理器获取url
url = self.url_manager.get_new_url()
# 将获取到的url使用下载器进行下载
html = self.html_downloader.download(url)
# 将html进行解析
res = self.html_parser.parser(html)
# 数据存储
self.data_storage.storage(res)
def url_manager_proc(self, url_q, conn_q, root_url):
url_manager = UrlManager()
url_manager.add_new_url(root_url)
print(url_q)
while True:
while (url_manager.has_new_url()):
new_url = url_manager.get_new_url()
url_q.put(new_url)
print('old_url=%s' % url_manager.old_url_size())
if (url_manager.old_url_size() > 2000):
url_q.put('end')
print('控制节点发起结束通知！')
url_manager.save_progress('new_urls.txt',
url_manager.new_urls)
url_manager.save_progress('old_urls.txt',
url_manager.old_urls)
return
try:
if not conn_q.empty():
urls = conn_q.get()
url_manager.add_new_urls(urls)
except BaseException as e:
time.sleep(0.1)
class SpiderMain(object):
def __init__(self):
self.urls = UrlManager()
self.downloader = HtmlDownloader()
self.parser = HtmlParser()
self.outputer = HtmlOutputer()
def craw(self, root_url):
count = 1
self.urls.add_new_url(root_url)
while self.urls.has_new_url():
try:
new_url = self.urls.get_new_url() # 获取新url
html_cont = self.downloader.download(new_url) # 下载url内容
new_urls, new_data = self.parser.parse(new_url,
html_cont) # 解析url内容
self.urls.add_new_urls(new_urls) # 将解析到的新url存入url管理器
self.outputer.collect_data(new_data) # 收集解析到的数据
if count == 200:
break
count = count + 1
except:
print("craw failed")
self.outputer.output_html()
class SpiderMain():
"""爬虫程序主模块"""
def __init__(self):
"""构造函数，初始化属性"""
self.urls = UrlManager()
self.log = MyLog("spider_main", "logs")
self.downloader = HtmlDownloader()
self.parser = HtmlParser()
self.outputer = HtmlOutputer()
#self.util=utill.DBConn()
def craw(self, root_url):
"""爬虫入口函数"""
areas = {
"gulou": 100,
"jianye": 72,
"qinhuai": 100,
"xuanwu": 67,
"yuhuatai": 32,
"qixia": 62,
"baijiahu": 33,
"chalukou1": 26,
"jiangningqita11": 3,
"dongshanzhen": 29,
"jiangningdaxuecheng": 15,
"jiulonghu": 12,
"jiangjundadao11": 22,
"kexueyuan": 9,
"qilinzhen": 42,
"tiexinqiao": 9,
"pukou": 100,
"liuhe": 1,
}
#areas = {"gulou":1}
#1、抓取所有二手房详情界面链接，并将所有连接放入URL管理模块
for area, pg_sum in areas.items():
for num in range(1, pg_sum + 1):
#1.1 拼接页面地址: https://nj.lianjia.com/ershoufang/gulou/pg2/
pg_url = root_url + area + "/pg" + str(num) + "/"
self.log.logger.info("1.1 拼接页面地址：" + pg_url)
print("1.1 拼接页面地址：" + pg_url)
#1.2 启动下载器,下载页面.
try:
html_cont = self.downloader.download(pg_url)
except Exception as e:
self.log.logger.error("1.2 下载页面出现异常:" + repr(e))
time.sleep(60 * 30)
else:
#1.3 解析PG页面，获得二手房详情页面的链接,并将所有链接放入URL管理模块
try:
ershoufang_urls = self.parser.get_erhoufang_urls(
html_cont)
except Exception as e:
self.log.logger.error("1.3 页面解析出现异常:" + repr(e))
else:
self.urls.add_new_urls(ershoufang_urls)
#暂停0~3秒的整数秒，时间区间：[0,3]
time.sleep(random.randint(0, 3))
time.sleep(60 * 20)
#2、解析二手房具体细心页面
id = 1
stop = 1
while self.urls.has_new_url():
#2.1 获取url
try:
detail_url = self.urls.get_new_url()
self.log.logger.info("2.1 二手房页面地址：" + detail_url)
print("2.1 二手房页面地址：" + detail_url)
except Exception as e:
print("2.1 拼接地址出现异常")
self.log.logger.error("2.1 拼接地址出现异常:" + detail_url)
#2.2 下载页面
try:
detail_html = self.downloader.download(detail_url)
except Exception as e:
self.log.logger.error("2.2 下载页面出现异常:" + repr(e))
self.urls.add_new_url(detail_url)
time.sleep(60 * 30)
else:
#2.3 解析页面
try:
ershoufang_data = self.parser.get_ershoufang_data(
detail_html, id)
except Exception as e:
self.log.logger.error("2.3 解析页面出现异常:" + repr(e))
else:
#2.4 输出数据
try:
self.outputer.collect_data(ershoufang_data)
except Exception as e:
self.log.logger.error("2.4 输出数据出现异常:" + repr(e))
else:
print(id)
id = id + 1
stop = stop + 1
#暂停0~3秒的整数秒，时间区间：[0,3]
time.sleep(random.randint(0, 3))
if stop == 2500:
stop = 1
time.sleep(60 * 20)
class spider_main():
def __init__(self):
self.urls = UrlManager()
self.parser = HtmlParser()
self.downloader = UrlDownloader()
self.log = MyLog("spider", "logs")
self.output = HtmlOutPut()
# 主模块中开始爬虫
def Crawling(self, root_url):
# 用字典存放地区名和网页数
areas = {
"gulou": 100,
"jianye": 100,
"qinhuai": 100,
"xuanwu": 100,
"yuhuatai": 100,
"qixia": 100,
"baijiahu": 64,
"jiangningqita11": 5,
"chalukou1": 63,
"dongshanzhen": 42,
"jiangningdaxuecheng": 28,
"jiulonghu": 28,
"jiangjundadao11": 50,
"kexueyuan": 16,
"pukou": 100,
"liuhe": 13,
"lishui": 9,
"jiangning": 100,
"qilinzhen": 83,
"tangshanzhen": 2,
"fenghuangxijie1": 82,
"xianlin2": 33,
"yaohuamen": 4,
"maigaoqiao1": 33,
"maqun1": 31,
"qixiaqita1": 5,
"xiaozhuang": 9,
"yanziji": 2,
"yueyuan": 15,
"wanshou1": 5,
"hongshan1": 16,
"caochangmendajie": 27,
"dinghuaimendajie": 37,
"fujianlu": 9,
"hanzhongmendajie": 19,
"huxijie": 15,
"jiangdong2": 8,
"nanhu4": 38,
"nanyuan2": 38,
"shuiximen1": 13,
"wandaguangchang1": 25,
"xiaoxing": 13,
"yuhuaxincun": 15,
"lukou": 14,
"dingshanjiedao": 8,
"gaoxinqu2": 12,
"jiangpujiedao": 29,
"pukouqita11": 8,
"qiaobei": 100,
"taishanjiedao": 12
}
# 通过拼接形成所有的url地址,将所有的url连接保存
for area, num in areas.items():
for n in range(1, num + 1):
# 拼接url: https://nj.lianjia.com/ershoufang/
splice_url = root_url + area + "/pg" + str(n) + "/"
# 将拼接url写入日志
self.log.logger.info("url地址拼接" + splice_url)
# 控制台打印
print("url地址拼接" + splice_url)
# 拼接完成后开始进行网页下载
try:
html_down = self.downloader.download(splice_url)
except Exception as e:
# 将错误信息写入日志
self.log.logger.error("html下载出现错误" + repr(e))
# 挂起进程
time.sleep(60)
else:
# 如果下载页面不出现错误，进行网页解析
try:
secondhome_urls = self.parser.get_secondhandhome_urls(
html_down)
except Exception as e:
# 将错误信息写入日志
self.log.logger.error("html页面解析错误" + repr(e))
else:
# 页面解析正常
self.urls.add_new_urls(secondhome_urls)
# time.sleep(random.randint(0,3))
time.sleep(60)
# 具体解析html 获取需要的数据集
id = 1 # 起始
stop = 1
while self.urls.isEmpty_new_urls():
# 取出url
try:
temp_url = self.urls.get_new_url()
# 控制台打印
print("html页面地址" + temp_url)
# 日志写入
self.log.logger.info("html页面地址" + temp_url)
except Exception as e:
# 错误信息写入日志
# 控制台打印
print("html页面地址获取失败" + temp_url)
self.log.logger.error("获取url错误" + repr(e))
# url获取正常进行下载
try:
temp_data = self.downloader.download(temp_url)
except Exception as e:
# 控制台打印
print("页面下载失败" + temp_url)
# 错误写入日志
self.log.logger.error("页面下载失败" + repr(e))
self.urls.add_new_url(temp_url)
time.sleep(10)
else: # 正常下载后 进行页面解析
try:
temp_parser = self.parser.get_secondhandhome_data(
temp_data, id)
except Exception as e:
self.log.logger.error("html页面解析错误" + repr(e))
print("html页面解析错误" + repr(e))
else:
# 页面解析正常 进行写出
try:
self.output.write_data(temp_parser)
except Exception as e:
self.log.logger.error("数据集写出错误" + repr(e))
print("数据集写出错误" + repr(e))
else:
print(id)
id = id + 1
stop = stop + 1
time.sleep(0.2)
if stop == 2500:
stop = 1
time.sleep(60)
class NewsCrawler:
def __init__(self):
self.seed = ['', 'http://news.163.com/' ] # 网易新闻首页
self.downloader = multiThreadDownloader.downloader()
self.analyze = HtmlAnalyze()
self.craw_url_man = UrlManager()
self.page_url_man = UrlManager()
self.conn = MySQLdb.connect(
host='localhost', user='******', passwd='toor',
db='newsGather', charset='utf8')
self.cur = self.conn.cursor()
# 将数据库中已下载的url加入url管理器的old_urls中
self.cur.execute("select url from news_info;")
results = self.cur.fetchall()
exist_urls = list()
if results == ():
pass
else:
for i in results:
exist_urls.append(i[0])
self.page_url_man.add_old_urls(exist_urls)
def get_news(self, website): # 处理url管理器中的新的新闻url
news = list()
dic = dict()
count = 0
new_urls = self.page_url_man.get_new_urls(len(self.page_url_man.new_urls))
print "获取新闻网页："
pages = self.downloader.download(new_urls, 6)
print "分析新闻网页并存储新闻...."
for page in pages:
dic = self.analyze.Content(website, page['content'])
if dic:
dic['url'] = page['url']
news.append(dic)
try:
print 'save ',dic['url']
sql_raw = "INSERT IGNORE INTO news_info (url, post_time, title, keywords, content, source, origin) VALUES ('%s', '%s', '%s', '%s', '%s', '%s', \"%s\")" % (dic['url'], dic['post_time'], dic['title'], dic['keywords'], raw(dic['content']), dic['source'], dic['origin'])
spider.cur.execute(sql_raw)
spider.conn.commit()
count += 1
except:
print "save error!"
print '抓取新闻数：%d' % count
return news
def craw(self, news_num, website, expand_patt, news_patt): # 新闻抓取
# print "hello"
self.craw_url_man.add_new_url(self.seed[website])
news = list()
dic = dict()
count = 0
i = 0
while self.craw_url_man.has_new_url:
print "第%d次扩展：" % i
#print "获取待扩展页面："
craw_num = len(self.craw_url_man.new_urls)
if craw_num < 60:
new_urls = self.craw_url_man.get_new_urls(craw_num)
else:
new_urls = self.craw_url_man.get_new_urls(60)
pages = self.downloader.download(new_urls, 6)
print "分析待扩展页面....."
for page in pages:
craw_new_urls = self.analyze.getUrl(page['content'], expand_patt)
self.craw_url_man.add_new_urls(craw_new_urls)
page_new_urls = self.analyze.getUrl(page['content'], news_patt)
#count = count + len(page_new_urls)
self.page_url_man.add_new_urls(page_new_urls)
count = len(self.page_url_man.new_urls)
if count > news_num:
news += self.get_news(website)
break
else:
i = i + 1
news += self.get_news(website)
continue
break
return news
class SpiderMain():
def __init__(self):
self.urlDownLoader = HtmlDownloader()
self.htmlParser = HtmlParser()
self.urlManager = UrlManager()
self.jsondataParser = JsonData_Parser()
self.htmlOutPuter = HtmlOutPuter()
def _get_from_discover_toplist(self, url):
urls = self.htmlParser.parse(
htmlContent=self.urlDownLoader.download(url),
type='discover_toplist')
self.urlManager.add_new_urls(urls)
def _get_from_discover_artist(self, url):
urls = self.htmlParser.parse(
htmlContent=self.urlDownLoader.download(url),
type='discover_artist')
self.urlManager.add_new_urls(urls)
def _get_from_artist(self, url):
results = self.htmlParser.parse(
htmlContent=self.urlDownLoader.download(url), type='artist')
for name, urls in results.items():
print(name)
self.urlManager.add_new_urls(urls)
def _get_from_song(self, url):
tmp = {}
name = self.htmlParser.parse(
htmlContent=self.urlDownLoader.download(url), type='song')
print("正收集：" + name)
comments = self.jsondataParser.parse(
self.urlDownLoader.downloadJsonData(url))
tmp[name] = comments
self.htmlOutPuter.collect_datas(tmp)
def _parse_url(self, url):
res = ''
SONG = 'song'
DISCOVER = 'discover'
ARTIST = 'artist'
TOPLIST = 'toplist'
if (url.find(DISCOVER) != -1):
res += DISCOVER
if (url.find(ARTIST) != -1):
if (res != ''):
res += '_' + ARTIST
else:
res += ARTIST
if (url.find(TOPLIST) != -1):
if (res != ''):
res += '_' + TOPLIST
else:
res += TOPLIST
if (url.find(SONG) != -1):
res += SONG
return res
def craw(self, rootUrl, direction=""):
if (rootUrl.find('#') != -1):
pos = rootUrl.find('#')
rootUrl = rootUrl[:pos] + rootUrl[pos + 2:]
self.urlManager.add_new_url(rootUrl)
while self.urlManager.has_new_url():
url = self.urlManager.get_url()
methodName = '_get_from_' + self._parse_url(url)
method = getattr(self, methodName)
if (method != None):
method(url)
self.htmlOutPuter.output_html(direction=direction)
