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()
class SpiderMan(object):
def __init__(self):
self.downloader = HtmlDownloader()
self.parser = HtmlParser()
self.output = DataOutput()
def crawl(self, root_url):
content = self.downloader.download(root_url)
urls = self.parser.parser_url(root_url, content)
for url in urls:
try:
t = time.strftime("%Y%m%d%H%M%S3282", time.localtime())
rank_url = 'http://service.library.mtime.com/Movie.api' \
'?Ajax_CallBack=true' \
'&Ajax_CallBackType=Mtime.Library.Services' \
'&Ajax_CallBackMethod=GetMovieOverviewRating' \
'&Ajax_CrossDomain=1' \
'&Ajax_RequestUrl=%s' \
'&t=%s' \
'&Ajax_CallBackArgument0=%s' % (url[0],t,url[1])
rank_content = self.downloader.download(rank_url)
data = self.parser.parser_json(rank_url, rank_content)
self.output.store_data(data)
except Exception as e:
print('Crawl failed')
self.output.output_end()
print('Crawl finish')
class SpiderMain:
def __init__(self):
"""
初始化方法，主要是将其他组件实例化
"""
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:
"""
""" 页码 """
title = set()
for a in range(2, 10):
html = self.html_downloader.download(
'http://ggzy.foshan.gov.cn/jyxx/fss/zfcg_1108551/zbxx/index_'+str(a)+'.html?1')
_title = self.html_parser.titleParer(html)
for i in _title:
title.add(i)
for i in title:
print(i)
html = self.html_downloader.download(i)
_product = self.html_parser.contextParer(html)
self.data_storage.storage(_product)
def __init__(self):
"""
初始化方法，主要是将其他组件实例化
"""
self.url_manager = UrlManager()
self.html_downloader = HtmlDownloader()
self.html_parser = HtmlParser()
self.data_storage = DataStorage()
def __init__(self):
# URL 管理器
# self.urls = UrlManager.UrlManager()
self.urls = UrlManager()
# URL 下载器
# self.downloader = HtmlDownloader.HtmlDownloader()
self.downloader = HtmlDownloader()
# URL 解析器
# self.parser = html_parser.HtmlParser()
self.parser = HtmlParser()
# self.outputer = html_outputer.HtmlOutputer()
self.outputer = HtmlOutputer()
def __init__(self):
BaseManager.register('get_task_queue')
BaseManager.register('get_result_queue')
server_addr = '127.0.0.1'
print('Connect to server %s...' % server_addr)
self.m = BaseManager(address=(server_addr,8001),authkey=b'baike')
self.m.connect()
self.task = self.m.get_task_queue()
print(self.task.qsize())
self.result = self.m.get_result_queue()
self.downloader = HtmlDownloader()
self.parser = HtmlParser()
print('init finish')
class SpiderWork(object):
def __init__(self):
BaseManager.register('get_task_queue')
BaseManager.register('get_result_queue')
server_addr = '127.0.0.1'
print('Connect to server %s...' % server_addr)
self.m = BaseManager(address=(server_addr,8001),authkey=b'baike')
self.m.connect()
self.task = self.m.get_task_queue()
print(self.task.qsize())
self.result = self.m.get_result_queue()
self.downloader = HtmlDownloader()
self.parser = HtmlParser()
print('init finish')
def crawl(self):
import time
while(True):
try:
if not self.task.empty():
url = self.task.get()
if url == 'end':
print('控制节点通知爬虫节点停止工作...')
self.result.put({'new_urls':'end', 'data':'end'})
return
print('爬虫节点正在解析：%s' % url.encode('utf-8'))
content = self.downloader.download(url)
new_urls,data = self.parser.parser(url,content)
self.result.put({'new_urls':new_urls, 'data':data})
except EOFError as e:
print('连接工作节点失败')
return
except Exception as e:
print(e)
print('Crawl fail')
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 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()
def __init__(self):
# 实例化其他模块类
self.mysql_handler = MysqlHandler()
self.html_downloader = HtmlDownloader()
self.html_parser = HtmlParser()
# 爬取起点url
self.root_url = 'http://www.stats.gov.cn/tjsj/tjbz/tjyqhdmhcxhfdm/2017/index.html'
# 用于后续url的拼接
self.split_url = 'http://www.stats.gov.cn/tjsj/tjbz/tjyqhdmhcxhfdm/2017/'
# 省页面列表
self.province_url_list = []
# 市页面列表
self.city_url_list = []
# 区页面列表
self.county_url_list = []
# 乡镇、街道页面列表
self.town_url_list = []
def __init__(self, address='127.0.0.1', port=8001, authkey=b'baike'):
"""初始化分布式进程中工作节点的连接工作"""
# 注册用于获取Queue的方法名称
BaseManager.register('get_task_queue')
BaseManager.register('get_result_queue')
# 连接到服务器
print('Connect to server %s:%s...' % (address, port))
self.manager = BaseManager(address=(address, port), authkey=authkey)
# 开始连接
self.manager.connect()
# 获取Queue对象
self.task_q = self.manager.get_task_queue()
self.result_q = self.manager.get_result_queue()
# 初始化下载器和解析器
self.downloader = HtmlDownloader()
self.parser = HtmlParser()
print('init finish')
def __init__(self):
args = ArgumentParser()
index_start = 1
try:
with open(args.index_end_path, 'r', encoding='utf-8') as f:
index_end = int(f.readline().strip('\n'))
except Exception as e:
print(e)
sys.exit(-1)
self.new_urls = set()
print("Adding all urls ...")
for index in range(index_start, index_end):
url = "https://baike.baidu.com/view/" + str(index)
self.new_urls.add(url)
print("Done.")
self.old_urls = set()
self.fail_urls = set()
self.fail_url_mark = True
self.downloader = HtmlDownloader()
def craw(self):
# 下载
downloader = HtmlDownloader()
root_cont = downloader.download(self.url)
parser = HtmlParser()
urls, data = parser.parse(self.url, root_cont, True)
result = ""
for url in urls:
cont = downloader.download(url)
newurls, month = parser.parse(url, cont, False)
if month != None:
result += month.getMonthly()
month = None
#print(month.getMonthly())
f = open("阿里巴巴数据库内核组月报.md", "w+", encoding='utf-8')
result = "## 阿里巴巴数据库内核月报\n\n" + result
f.write(result)
f.close()
pass
class Spider:
def __init__(self):
self.downloader = HtmlDownloader()
self.parser = HtmlParser()
self.output = DataOutput()
def crawl(self, root_url):
content = self.downloader.download(root_url)
urls = self.parser.parse_url(root_url, content)
for url in urls:
try:
# http://service.library.mtime.com/Movie.api
# ?Ajax_CallBack=true
# &Ajax_CallBackType=Mtime.Library.Services
# &Ajax_CallBackMethod=GetMovieOverviewRating
# &Ajax_CrossDomain=1
# &Ajax_RequestUrl=http%3A%2F%2Fmovie.mtime.com%2F246526%2F&t=201710117174393728&Ajax_CallBackArgument0=246526
t = time.strftime('%Y%m%d%H%M%S3282', time.localtime())
rank_url = 'http://service.library.mtime.com/Movie.api' \
'?Ajax_CallBack=true' \
'&Ajax_CallBackType=Mtime.Library.Services' \
'&Ajax_CallBackMethod=GetMovieOverviewRating' \
'&Ajax_CrossDomain=1' \
'&Ajax_RequestUrl=%s' \
'&t=%s' \
'&Ajax_CallbackArgument0=%s' % (url[0].replace('://', '%3A%2F%2F')[:-1], t, url[1])
rank_content = self.downloader.download(rank_url)
if rank_content is None:
print('None')
data = self.parser.parse_json(rank_url, rank_content)
self.output.store_data(data)
except Exception as e:
raise e
# print(e)
# print('Crawl failed')
self.output.output_end()
print('Crawl finish')
class SpiderWorker:
def __init__(self, address='127.0.0.1', port=8001, authkey=b'baike'):
"""初始化分布式进程中工作节点的连接工作"""
# 注册用于获取Queue的方法名称
BaseManager.register('get_task_queue')
BaseManager.register('get_result_queue')
# 连接到服务器
print('Connect to server %s:%s...' % (address, port))
self.manager = BaseManager(address=(address, port), authkey=authkey)
# 开始连接
self.manager.connect()
# 获取Queue对象
self.task_q = self.manager.get_task_queue()
self.result_q = self.manager.get_result_queue()
# 初始化下载器和解析器
self.downloader = HtmlDownloader()
self.parser = HtmlParser()
print('init finish')
def crawl(self):
while True:
try:
if not self.task_q.empty():
url = self.task_q.get()
if url == 'end':
print('控制节点通知爬虫节点停止工作...')
# 接着通知其他节点停止工作
self.result_q.put({'new_urls': 'end', 'data': 'end'})
return
print('爬虫节点正在解析: %s' % url)
content = self.downloader.download(url)
new_urls, data = self.parser.parse(url, content)
self.result_q.put({'new_urls': new_urls, 'data': data})
else:
print('task queue is empty', self.task_q.empty())
except EOFError:
print('连接工作节点失败')
return
except Exception as e:
print(e)
print('crawl fail')
class SpiderMain():
def __init__(self):
# URL 管理器
# self.urls = UrlManager.UrlManager()
self.urls = UrlManager()
# URL 下载器
# self.downloader = HtmlDownloader.HtmlDownloader()
self.downloader = HtmlDownloader()
# URL 解析器
# self.parser = html_parser.HtmlParser()
self.parser = HtmlParser()
# self.outputer = html_outputer.HtmlOutputer()
self.outputer = HtmlOutputer()
def craw(self, root_url):
count = 1
originSet = set()
originSet.add(root_url)
self.urls.add_new_urls(originSet)
while self.urls.has_new_rul():
try:
new_url = self.urls.get_new_url()
print "craw %d : %s" % (count, new_url)
html_cont = self.downloader.downloader(new_url)
# 输出信息
downStat = "ERROR"
if html_cont != None:
downStat = "SUCCESS"
print "[Page ID : %d downloader %s!]" % (count, downStat)
new_urls, new_data = self.parser.parser(new_url, html_cont)
# print "\nnew_urls[%s], new_data[%s]" % (new_urls, new_data)
self.urls.add_new_urls(new_urls)
self.outputer.collect_data(new_data)
if count == 15:
break
count = count + 1
except Exception as err:
print "craw failed! ERROR infomation : %s" % err
self.outputer.output_html()
class CodeSpider(object):
def __init__(self):
# 实例化其他模块类
#self.mysql_handler = MysqlHandler()
self.html_downloader = HtmlDownloader()
self.html_parser = HtmlParser()
self.path = "/Users/spike/python_项目/get_cd_school/"
# # 爬取起点url
# self.root_url = 'http://infomap.cdedu.gov.cn/Home/Index?all=1&pages=1'
# # 用于后续url的拼接
# self.split_url = 'http://infomap.cdedu.gov.cn/Home/Index?all=1&pages='
# school info
# self.school_infos = []
def craw(self, downloading_url):
try:
# 记录正在下载、解析的url，便于分析错误
# downloading_url = self.root_url
html_content = self.html_downloader.download(downloading_url)
# 第一个参数：需要解析的html代码
# 第二个参数：用于url拼接的url
self.school_infos = self.html_parser.province_parser(html_content)
# print(self.school_infos)
#exit()
if (len(self.school_infos) != 20):
print(downloading_url + "解析成功")
print("当前页面数据：" + str(len(self.school_infos)))
#print(self.province_url_list)
with open(self.path + "school.txt", "a") as f:
# print("writting")
for mc, xd, qy, xz, dh, dz in self.school_infos:
f.write(mc + "\t" + xd + "\t" + qy + "\t" + xz + "\t" +
dh + "\t" + dz)
f.close()
return len(self.school_infos)
except Exception as e:
print('[ERROR] Craw Field!Url:', downloading_url, 'Info:', e)
# 利用traceback定位异常
traceback.print_exc()
class CodeSpider(object):
def __init__(self):
# 实例化其他模块类
self.mysql_handler = MysqlHandler()
self.html_downloader = HtmlDownloader()
self.html_parser = HtmlParser()
# 爬取起点url
# self.root_url = 'http://infomap.cdedu.gov.cn/Home/Index?all=1&pages=1'
# # 用于后续url的拼接
# self.split_url = 'http://infomap.cdedu.gov.cn/Home/Index?all=1&pages='
# # school info
# self.school_infos = []
#日志文件路径需要自行修改
# self.last_log_path = "d:\\log.txt"
# self.last_log_path = "/Users/spike/spider_log.txt"
def craw(self,downloading_url):
try:
# 记录正在下载、解析的url，便于分析错误
# downloading_url = self.root_url
html_content = self.html_downloader.download(downloading_url)
# 第一个参数：需要解析的html代码
self.school_infos = self.html_parser.province_parser(html_content)
# print(self.school_infos)
if (len(self.school_infos)!=20):
print(downloading_url+"解析成功")
print("当前页面数据："+str(len(self.school_infos)))
for mc,xd,qy,xz,dh,dz in self.school_infos:
# print(mc+xd+qy+xz+dh+dz)
province_id = self.mysql_handler.insert(mc,xd,qy,xz,dh,dz)
# print(province_id)
# exit()
# 记录正在下载、解析的url，便于分析错误
# self.mysql_handler.close()
return len(self.school_infos)
except Exception as e:
print('[ERROR] Craw Field!Url:', downloading_url, 'Info:', e)
# 利用traceback定位异常
traceback.print_exc()
time.sleep(60)
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)
class SpiderMain(object):
"""docstring for SpiderMain"""
def __init__(self):
self.urlManage = UrlManage()
self.downloader = HtmlDownloader()
self.parser = HtmlParser()
self.outputer = HtmlOutputer()
def craw(self,url):
self.urlManage.add_new_url(url)
count = 1
while self.urlManage.has_new_url():
url = self.urlManage.get_new_url()
print '%dth page,address:%s' % (count,url)
html_content = self.downloader.downloadPage(url)
new_urls,new_data = self.parser.parse(html_content,url)
self.urlManage.add_new_urls(new_urls)
self.outputer.collect_data(new_data)
if count == 10:
break
count = count + 1
self.outputer.output_html()
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 UrlManager(object):
def __init__(self):
args = ArgumentParser()
index_start = 1
try:
with open(args.index_end_path, 'r', encoding='utf-8') as f:
index_end = int(f.readline().strip('\n'))
except Exception as e:
print(e)
sys.exit(-1)
self.new_urls = set()
print("Adding all urls ...")
for index in range(index_start, index_end):
url = "https://baike.baidu.com/view/" + str(index)
self.new_urls.add(url)
print("Done.")
self.old_urls = set()
self.fail_urls = set()
self.fail_url_mark = True
self.downloader = HtmlDownloader()
# self.update_new_url(index_end, args)
def update_new_url(self, index_end, args):
err_cnt = 0
start = index_end
end = start
while True:
if err_cnt > 10:
break
url = "https://baike.baidu.com/view/" + str(start)
response, response_url = self.downloader.download_update(url)
if not response_url or response_url == 'https://baike.baidu.com/error.html':
err_cnt += 1
else:
err_cnt = 0
self.new_urls.add(url)
end = start
start += 1
with open(args.index_end_path, 'w', encoding='utf-8') as f:
f.write(str(end))
def add_new_url(self, url):
if url is None:
return
if url not in self.new_urls and url not in self.old_urls:
self.new_urls.add(url)
def add_old_url(self, url):
if url is None:
return
if url not in self.new_urls:
self.old_urls.add(url)
def add_fail_url(self, url):
if url is None:
return
if url not in self.new_urls and url not in self.old_urls:
self.fail_urls.add(url)
def add_new_urls(self, urls):
if urls is None or len(urls) == 0:
return
for url in urls:
if url not in self.old_urls:
self.new_urls.add(url)
def has_new_url(self):
if len(self.new_urls) != 0:
return True
elif self.fail_url_mark:
self.new_urls = self.fail_urls.copy()
self.fail_urls.clear()
self.fail_url_mark = False
return True
else:
return False
def get_new_url(self):
new_url = self.new_urls.pop()
return new_url
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)
def __init__(self):
self.urls = UrlManager()
self.downloader = HtmlDownloader()
self.parser = HtmlParser()
self.outputer = HtmlOutputer()
def __init__(self):
# 实例化其他模块类
self.mysql_handler = MysqlHandler()
self.html_downloader = HtmlDownloader()
self.html_parser = HtmlParser()
class LinkExtractor(object):
def __init__(self):
self.counter = 0
self.k_count = 0
self.downloader = HtmlDownloader()
def get_menu_page_info(self, menu_page_url):
if menu_page_url is None:
return None
html_text = self.downloader.download(menu_page_url)
if html_text == None:
return None
self.counter = (self.counter + 1)%100
if self.counter == 0:
self.k_count += 1
print('Get Manu Pages: %d00'%(self.k_count))
return self.parse_menu_page_info(html_text)
def parse_menu_page_info(self, html_text):
if html_text is None:
return None
soup = BeautifulSoup(html_text, 'lxml')
menu_page_data = []
for entry in soup.select('.r-ent'):
data = {
'title': entry.select('.title')[0].text.strip(),
'post_url': PTT_HOST_URL + entry.select('.title > a')[0].get('href') if entry.select('.title > a') else None,
'date': entry.select('.date')[0].text.strip(),
'author': entry.select('.author')[0].text.strip(),
'visited': 0
}
menu_page_data.append(data)
return menu_page_data
# 抓 post_links 到 post_url_infos table
def fetch_menu_page_links(self, menu_page_url):
menu_page_data = self.get_menu_page_info(menu_page_url)
if menu_page_data != None:
url_manager.add_new_url_infos(menu_page_data)
def next_page(self, html_text):
soup = BeautifulSoup(html_text, 'lxml')
if soup.find_all('a', class_='btn wide', text='下頁 ›'):
return PTT_HOST_URL + soup.find_all('a', class_='btn wide', text='下頁 ›')[0].get('href')
return None
def run(self, root_menu_page, min_menu_page_index=1, max_menu_page_index=6000, threadNum=5):
print('===================== start run extractor() ========================')
try:
pool = threadpool.ThreadPool(threadNum)
menu_page_urls = [root_menu_page.format(i) for i in range(min_menu_page_index, max_menu_page_index)]
requests = threadpool.makeRequests(self.fetch_menu_page_links, menu_page_urls)
[pool.putRequest(req) for req in requests]
pool.wait()
print('link extractor done.')
except:
print('link_extractor excepttion')
raise
def __init__(self):
self.counter = 0
self.k_count = 0
self.downloader = HtmlDownloader()
def __init__(self):
self.urlManage = UrlManage()
self.downloader = HtmlDownloader()
self.parser = HtmlParser()
self.outputer = HtmlOutputer()
def __init__(self):
self.url_manager = UrlManager()
self.html_downloader = HtmlDownloader()
self.html_parser = HtmlParser()
self.data_storage = DataStorage()
def __init__(self):
# 实例化其他模块类
#self.mysql_handler = MysqlHandler()
self.html_downloader = HtmlDownloader()
self.html_parser = HtmlParser()
self.path = "/Users/spike/python_项目/get_cd_school/"
class CodeSpider(object):
def __init__(self):
# 实例化其他模块类
self.mysql_handler = MysqlHandler()
self.html_downloader = HtmlDownloader()
self.html_parser = HtmlParser()
# 爬取起点url
self.root_url = 'http://www.stats.gov.cn/tjsj/tjbz/tjyqhdmhcxhfdm/2017/index.html'
# 用于后续url的拼接
self.split_url = 'http://www.stats.gov.cn/tjsj/tjbz/tjyqhdmhcxhfdm/2017/'
# 省页面列表
self.province_url_list = []
# 市页面列表
self.city_url_list = []
# 区页面列表
self.county_url_list = []
# 乡镇、街道页面列表
self.town_url_list = []
self.last_log_path = "d:\\log.txt"
def craw(self):
try:
# 记录正在下载、解析的url，便于分析错误
downloading_url = self.root_url
html_content = self.html_downloader.download(downloading_url)
# 第一个参数：需要解析的html代码
# 第二个参数：用于url拼接的url
self.province_url_list = self.html_parser.province_parser(
html_content, self.split_url)
#print(self.province_url_list)
pro = self.province_url_list
#print(self.province_url_list[0][0])
with open(self.last_log_path, "r") as r:
last_log = r.read()
#print(last_log)
if last_log != "":
last_log_index = pro.index(tuple(last_log.split(';')))
#print("inde:"+str(last_log_index))
for i in range(last_log_index):
del self.province_url_list[0]
print("删除已下载元素后还剩余：" + str(len(self.province_url_list)) +
"共计：31")
#print(self.province_url_list)
#exit()
#else:
# print("下载开始，共计:"+str(len(pro))
#print(last_log_index)
#exit()
for province_name, province_url, province_code in self.province_url_list:
#print(province_code)
#记录最后一个下载
last_record = (province_name, province_url, province_code)
#print(last_record)
with open(self.last_log_path, "w") as l:
#last_name = province_name.encode('utf8')
l.write(last_record[0] + ";" + last_record[1] + ";" +
last_record[2])
#exit()
province_id = self.mysql_handler.insert(
province_code + '0000000000', province_name)
#print(province_id)
# 记录正在下载、解析的url，便于分析错误
downloading_url = province_url
html_content = self.html_downloader.download(downloading_url)
self.city_url_list = self.html_parser.city_parser(
html_content, self.split_url)
for city_name, city_url, city_code in self.city_url_list:
city_id = self.mysql_handler.insert(city_code, city_name)
# 例如直辖市没有下级页面
if city_url is None:
continue
# 记录正在下载、解析的url，便于分析错误
downloading_url = city_url
html_content = self.html_downloader.download(
downloading_url)
self.county_url_list = self.html_parser.county_parser(
html_content, self.split_url + province_code + "/")
for county_name, county_url, county_code in self.county_url_list:
county_id = self.mysql_handler.insert(
county_code, county_name)
if county_url is None:
continue
# 记录正在下载、解析的url，便于分析错误
downloading_url = county_url
html_content = self.html_downloader.download(
downloading_url)
self.town_url_list = self.html_parser.town_parser(
html_content, self.split_url)
for town_name, town_url, town_code in self.town_url_list:
# 输出抓取到的乡镇街道的名称、链接（实际不需要）、编号代码
print(town_name, town_url, town_code)
self.mysql_handler.insert(town_code, town_name)
self.mysql_handler.close()
except Exception as e:
print('[ERROR] Craw Field!Url:', downloading_url, 'Info:', e)
# 利用traceback定位异常
traceback.print_exc()
time.sleep(60)
return self.craw()
from html_downloader import HtmlDownloader
from html_paraser import HtmlParser
import pymysql
from date_provider import getAllDayPerYear
import time
conn = pymysql.connect(host='192.168.64.135',
port=3306,
user='******',
passwd='123456',
db='comp')
cursor = conn.cursor()
if __name__ == '__main__':
hd = HtmlDownloader()
hp = HtmlParser()
province = 'zhejiang'
for year in range(2019, 1949, -1):
print(year)
year_date_list = getAllDayPerYear(year)
# print(year_date_list)
for comregdate in year_date_list:
print(comregdate)
errcnt = 0
pagecnt_tmp = 0
for pagecnt in range(0, 1000):
url = r'https://gongshang.mingluji.com/' + province + r'/riqi/' + comregdate + r'?page=' + str(
pagecnt)
class CodeSpider(object):
def __init__(self):
# 实例化其他模块类
#self.mysql_handler = MysqlHandler()
self.html_downloader = HtmlDownloader()
self.html_parser = HtmlParser()
self.path = "D:\\python_work\\get_diqu_dm\\"
# 爬取起点url
self.root_url = 'http://www.stats.gov.cn/tjsj/tjbz/tjyqhdmhcxhfdm/2017/index.html'
# 用于后续url的拼接
self.split_url = 'http://www.stats.gov.cn/tjsj/tjbz/tjyqhdmhcxhfdm/2017/'
# 省页面列表
self.province_url_list = []
# 市页面列表
self.city_url_list = []
# 区页面列表
self.county_url_list = []
# 乡镇、街道页面列表
self.town_url_list = []
def craw(self):
try:
# 记录正在下载、解析的url，便于分析错误
downloading_url = self.root_url
html_content = self.html_downloader.download(downloading_url)
# 第一个参数：需要解析的html代码
# 第二个参数：用于url拼接的url
self.province_url_list = self.html_parser.province_parser(html_content, self.split_url)
#print(self.province_url_list)
with open(self.path+"shen_daima.txt", "a") as f:
for province_name, province_url, province_code in self.province_url_list:
province_code = province_code+'0000000000'
f.write(province_code+"\t"+province_name+"\n")
# 第一个参数：1-插入一个省数据；2-市数据；3-区数据；4-乡镇街道数据
# 第二个参数：省市区街道名称
# 第三个参数：上级的id，注意省没有上级id
# 第四个参数：市区街道的行政区划编码
#province_id = self.mysql_handler.insert(1, province_name, None, None)
# 记录正在下载、解析的url，便于分析错误
downloading_url = province_url
html_content = self.html_downloader.download(downloading_url)
self.city_url_list = self.html_parser.city_parser(html_content, self.split_url)
with open(self.path+"other_daima.txt","a") as o:
for city_name, city_url, city_code in self.city_url_list:
o.write(city_code+"\t"+city_name+"\n")
#city_id = self.mysql_handler.insert(2, city_name, province_id, city_code)
# 例如直辖市没有下级页面
if city_url is None:
continue
# 记录正在下载、解析的url，便于分析错误
downloading_url = city_url
html_content = self.html_downloader.download(downloading_url)
self.county_url_list = self.html_parser.county_parser(html_content, self.split_url + province_code + "/")
for county_name, county_url, county_code in self.county_url_list:
o.write(county_code+"\t"+county_name+"\n")
#county_id = self.mysql_handler.insert(3, county_name, city_id, county_code)
if county_url is None:
continue
# 记录正在下载、解析的url，便于分析错误
print('To deal with county')
downloading_url = county_url
html_content = self.html_downloader.download(downloading_url)
self.town_url_list = self.html_parser.town_parser(html_content, self.split_url)
for town_name, town_url, town_code in self.town_url_list:
# 输出抓取到的乡镇街道的名称、链接（实际不需要）、编号代码
o.write(town_code+"\t"+town_name+"\n")
print(town_name, town_url, town_code)
#self.mysql_handler.insert(4, town_name, county_id, town_code)
#self.mysql_handler.close()
f.close()
o.close()
except Exception as e:
print('[ERROR] Craw Field!Url:', downloading_url, 'Info:', e)
# 利用traceback定位异常
traceback.print_exc()
def __init__(self):
self.downloader = HtmlDownloader()
self.parser = HtmlParser()
self.output = DataOutput()
