class SpiderMan(object): def _init_(self): self.manager = UrlManager() self.downloader = HtmlDownloader() self.parser = HtmlParser() self.output = DataOutput() def crawl(self,root_url): #添加入口URL self.manager.add_new_url(root_url) #判断url管理器中是否有新的url，同时判断抓取了多少个url while(self.manager.has_new_url() and self.manager.old_url_size()<100): try: #从URL管理器获取新的url new_url = self.manager.get_new_url() #HTML下载器下载网页 html = self.downloader.download(new_url) #HTML解析器抽取网页数据 new_urls,data = self.parser.parser(new_url,html) #将抽取的url添加到URL管理器中 self.output.store_data(data) print "已经抓取%s个链接"%self.manager.old_url_size() except Exception,e: print "crawl failed" #数据存储器将文件输出成指定格式 self.output.output_html()
class SpiderMan(object):
def __init__(self):
self.manager = UrlManager()
self.downloader = HtmlDownloader()
self.parser = HtmlParser()
self.output = DataOutput()
def crawl(self):
# 添加URL入口
self.manager.add_new_url(
"https://www.amazon.cn/gp/bestsellers/books/ref=zg_bs_pg_1?ie=UTF8&pg=1"
)
self.manager.add_new_url(
"https://www.amazon.cn/gp/bestsellers/books/ref=zg_bs_pg_2?ie=UTF8&pg=2"
)
while (self.manager.has_new_url()
and self.manager.old_url_size() < 100):
try:
# 从URL管理器获取新的URL
new_url = self.manager.get_new_url()
# HTML下载器下载网页
html = self.downloader.download(new_url)
# HTML解析器抽取网页数据
book_details = self.parser.parser(new_url, html)
# 数据存储器存储文件
print(book_details)
for book_detail in book_details:
self.output.store_book(book_detail)
except Exception as e:
print("crawl failed")
self.output.output_html()
def crawl(self, root_url):
self.manager.add_new_url(root_url)
while (self.manager.has_new_url() and self.manager.get_old_url_size() < 100):
try:
new_url = self.manager.get_new_url()
html = HtmlDownloader.download(new_url)
data = self.parser.parser(new_url, html)
# self.manager.add_new_url(new_urls)
self.output.store_data(data)
# print '已经抓取%s个链接' % self.manager.get_old_url_size()
except Exception, e:
print 'craml execption %s' % e
class SpiderMan(object):
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_url_size() < 300):
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_url_size())
except Exception as e:
print("crawl failed")
self.output.output_html()
class SpiderMan(object):
def __init__(self):
self.manager = UrlManager()
self.downloader = HtmlDownloader()
self.parser = HtmlParser()
self.output = DataOutput()
def crawlHTML(self, root_url):
# 添加入口URL
self.manager.add_new_url(root_url)
# 判断url管理中时候是否有新的url， 同时判断抓取了多少个url
while (self.manager.has_new_url()):
try:
# 从URL管理器获取新的url
new_url = self.manager.get_new_url()
# HTML下载器下载网页
html = self.downloader.download(new_url)
# HTML解析器抽取网页数据
self.parser.parser(new_url, html)
except Exception, e:
print e
print "crawl failed"
def __init__(self):
self.manager = UrlManager()
self.downloader = HtmlDownloader()
self.parser = HtmlParser()
self.output = DataOutput()
def __init__(self):
self.htmlDownloader = HtmlDownloader()
self.dataOutput = DataOutput()
class HtmlParser(object):
def __init__(self):
self.htmlDownloader = HtmlDownloader()
self.dataOutput = DataOutput()
def parser(self, page_url, html_cont):
'''
用于解析网页内容， 抽取URL和数据
:param page_url: 下载页面的URL
:param html_cont: 下载的网页内容
:return: 返回URL和数据
'''
if page_url is None or html_cont is None:
return
soup = BeautifulSoup(html_cont, 'html.parser', from_encoding='utf-8')
new_urls = self._get_new_urls(page_url, soup)
return new_urls
def _get_new_urls(self, page_url, soup):
'''
抽取新的URL集合
:param page_url: 下载页面的URl
:param soup: soup
:return: 返回新的URL集合
'''
new_urls = set()
#抽取符合要求的a标记
wrapper = soup.select(
'div.exp-gridwall-standard > div.exp-product-wall > div')
# print len(wrapper)
i = 0
headers = ['title', 'category', 'imgName', 'price']
for child in wrapper:
link = child.div.div.div.div.a['href'].encode('utf8')
imgLink = self.htmlDownloader.imgDownloader(link).encode('utf8')
imgFileName = self.getFileName(imgLink)
name = child.div.select('.product-display-name')[0].string.encode(
'utf8')
category = child.div.select('.product-subtitle')[0].string.encode(
'utf8')
price = child.div.select(
'.local.nsg-font-family--base')[0].string.encode('utf8')
if name == None:
name = ''
if category == None:
category = ''
if imgFileName == None:
imgFileName = ''
if price == None:
price = '0'
data = {
'title': name,
'category': category,
'imgName': imgFileName,
'price': price
}
print('目前下载进度： ' + str(i))
i = i + 1
self.dataOutput.datas.append(data)
print data
self.dataOutput.output_csv(headers)
return new_urls
def _get_new_data(self, page_url, soup):
'''
抽取有效数据
:param page_url:下载页面的URL
:param soup:
:return: 返回有效数据
'''
data = {}
data['url'] = unquote(page_url)
title = soup.find('dd', class_='lemmaWgt-lemmaTitle-title').find('h1')
data['title'] = title.get_text()
summary = soup.find('div', class_='lemma-summary')
# 获取ta中包含的所有的文本内容， 包括子孙tag中的内容， 并将结合作为Unicode字符串返回
data['summary'] = summary.get_text()
return data
def parserJSON(self, jsonData):
if jsonData is None:
return
text = json.loads(jsonData)
itemsArr = text['sections'][0]['items']
# print text['sections'][0]['items']
i = 0
headers = ['title', 'category', 'imgName', 'price']
for item in itemsArr:
title = item['title'].encode('utf8')
category = item['subtitle'].encode('utf8')
price = item['localPrice'].encode('utf8')
link = item['pdpUrl'].encode('utf8')
imgLink = self.htmlDownloader.imgDownloader(link).encode('utf8')
imgFileName = self.getFileName(imgLink)
if title == None:
title = ''
if category == None:
category = ''
if imgFileName == None:
imgFileName = ''
if price == None:
price = '0'
data = {
'title': title,
'category': category,
'imgName': imgFileName,
'price': price
}
print('Current Download Status： ' + str(i))
print data
i = i + 1
self.dataOutput.datas.append(data)
self.dataOutput.output_csv(headers)
def getFileName(self, url, file_path='', file_suffix=''):
queryArr = url.split('/')
strLen = len(queryArr)
name = queryArr[strLen - 1]
try:
if type(int(name[0])) == int:
name = 'a' + name
except Exception:
name = name
file_name = re.sub(r'.tif\?(\D)*$', '.jpg', name)
return '{}{}{}'.format(file_path, file_name, file_suffix)