python+mongodb数据抓取详细介绍

def step():
  try:
    headers = {
      。。。。。
      }
    r = requests.get(url,headers,timeout=30)
    html = r.content
    soup = BeautifulSoup(html,"lxml")
    url = soup.find_all(正则表达式)
    for i in url:
      url2 = i.find_all('a')
      for j in url2:
         step1url =url + j['href']
         print step1url
         step2(step1url)
  except Exception,e:
    print e

def step2(step1url):
  try:
    headers = {
      。。。。
      }
    r = requests.get(step1url,headers,timeout=30)
    html = r.content
    soup = BeautifulSoup(html,"lxml")
    a = soup.find('div',id='divTbl')
    if a:
      url = soup.find_all('td',class_='S-ITabs')
      for i in url:
        classifyurl = i.find_all('a')
        for j in classifyurl:
           step2url = url + j['href']
           #print step2url
           step3(step2url)
    else:
      postdata(step1url)

def producturl(url):
  try:
    p1url = doc.xpath(正则表达式)
    for i in xrange(1,len(p1url) + 1):
      p2url = doc.xpath(正则表达式)
      if len(p2url) > 0:
        producturl = url + p2url[0].get('href')
        count = db[table].find({'url':producturl}).count()
        if count <= 0:
            sn = getNewsn()
            db[table].insert({"sn":sn,"url":producturl})
            print str(sn) + 'inserted successfully'
        else:
            'url exist'

  except Exception,e:
    print e

def parser(sn,url):
  try:
    headers = {
      。。。。。。
      }
    r = requests.get(url, headers=headers,timeout=30)
    html = r.content
    soup = BeautifulSoup(html,"lxml")
    dt = {}
    #partno
    a = soup.find("meta",itemprop="mpn")
    if a:
      dt['partno'] = a['content']
    #manufacturer
    b = soup.find("meta",itemprop="manufacturer")
    if b:
      dt['manufacturer'] = b['content']
    #description
    c = soup.find("span",itemprop="description")
    if c:
      dt['description'] = c.get_text().strip()
    #price
    price = soup.find("table",class_="table table-condensed occalc_pa_table")
    if price:
      cost = {}
      for i in price.find_all('tr'):
        if len(i) > 1:
          td = i.find_all('td')
          key=td[0].get_text().strip().replace(',','')
          val=td[1].get_text().replace(u'\u20ac','').strip()
          if key and val:
            cost[key] = val
      if cost:
        dt['cost'] = cost
        dt['currency'] = 'EUR'
    #quantity
    d = soup.find("input",id="ItemQuantity")
    if d:
      dt['quantity'] = d['value']
    #specs
    e = soup.find("div",class_="row parameter-container")
    if e:
      key1 = []
      val1= []
      for k in e.find_all('dt'):
        key = k.get_text().strip().strip('.')
        if key:
          key1.append(key)
      for i in e.find_all('dd'):
        val = i.get_text().strip()
        if val:
          val1.append(val)
      specs = dict(zip(key1,val1))
    if specs:
      dt['specs'] = specs
      print dt
      
    if dt:
      db[table].update({'sn':sn},{'$set':dt})
      print str(sn) + ' insert successfully'
      time.sleep(3)
    else:
      error(str(sn) + '\t' + url)
  except Exception,e:
    error(str(sn) + '\t' + url)
    print "Don't data!"