Twitter Python爬虫的爬取机制问题

Question

下面是我的 twitter 爬虫机制的一小段代码：

from BeautifulSoup import BeautifulSoup
import re
import urllib2

url = 'http://mobile.twitter.com/NYTimesKrugman'

def gettweets(soup):
    tags = soup.findAll('div', {'class' : "list-tweet"})#to obtain tweet of a follower
    for tag in tags: 
        print tag.renderContents()
        print ('\n\n')

def are_more_tweets(soup):#to check whether there is more than one page on mobile   twitter 
    links = soup.findAll('a', {'href': True}, {id: 'more_link'})
    for link in links:
        b = link.renderContents()
        test_b = str(b)
        if test_b.find('more'):
            return True
        else:
            return False

def getnewlink(soup): #to get the link to go to the next page of tweets on twitter 
    links = soup.findAll('a', {'href': True}, {id : 'more_link'})
    for link in links:
        b = link.renderContents()
        if str(b) == 'more':
            c = link['href']
            d = 'http://mobile.twitter.com' +c
            return d

def checkforstamp(soup): # the parser scans a webpage to check if any of the tweets are older than 3 months
    times = soup.findAll('a', {'href': True}, {'class': 'status_link'})
    for time in times:
        stamp = time.renderContents()
        test_stamp = str(stamp)
        if test_stamp == '3 months ago':  
            print test_stamp
            return True
        else:
            return False


response = urllib2.urlopen(url)
html = response.read()
soup = BeautifulSoup(html)
gettweets(soup)
stamp = checkforstamp(soup)
tweets = are_more_tweets(soup)
print 'stamp' + str(stamp)
print 'tweets' +str (tweets)
while (stamp is False) and (tweets is True): 
    b = getnewlink(soup)
    print b
    red = urllib2.urlopen(b)
    html = red.read()
    soup = BeautifulSoup(html)
    gettweets(soup)
    stamp = checkforstamp(soup)
    tweets = are_more_tweets(soup)
print 'done' 

问题是，在我的推特爬虫点击大约 3 个月的推文后，我希望它停止转到用户的下一页。但是，它似乎没有这样做。它似乎在不断地搜索下一页的推文。我相信这是由于 checkstamp 不断评估为 False 的事实。有没有人对我如何修改代码有任何建议，以便爬虫只要有更多推文（由 are_more_tweets 机制验证）并且还没有达到 3 个月的推文，就可以继续寻找下一页的推文？ ??谢谢！

编辑 - 请参见下文：

from BeautifulSoup import BeautifulSoup
import re
import urllib

url = 'http://mobile.twitter.com/cleversallie'
output = open(r'C:\Python28\testrecursion.txt', 'a') 

def gettweets(soup):
    tags = soup.findAll('div', {'class' : "list-tweet"})#to obtain tweet of a follower
    for tag in tags: 
        a = tag.renderContents()
        b = str (a)
        print(b)
        print('\n\n')

def are_more_tweets(soup):#to check whether there is more than one page on mobile twitter 
    links = soup.findAll('a', {'href': True}, {id: 'more_link'})
    for link in links:
        b = link.renderContents()
        test_b = str(b)
        if test_b.find('more'):
            return True
        else:
            return False

def getnewlink(soup): #to get the link to go to the next page of tweets on twitter 
    links = soup.findAll('a', {'href': True}, {id : 'more_link'})
    for link in links:
        b = link.renderContents()
        if str(b) == 'more':
            c = link['href']
            d = 'http://mobile.twitter.com' +c
            return d

 def checkforstamp(soup): # the parser scans a webpage to check if any of the tweets are older than 3 months
    times = soup.findAll('a', {'href': True}, {'class': 'status_link'})
    for time in times:
        stamp = time.renderContents()
        test_stamp = str(stamp)
        if not (test_stamp[0]) in '0123456789':
            continue
        if test_stamp == '3 months ago':
            print test_stamp
            return True
        else:
            return False


response = urllib.urlopen(url)
html = response.read()
soup = BeautifulSoup(html)
gettweets(soup)
stamp = checkforstamp(soup)
tweets = are_more_tweets(soup)
while (not stamp) and (tweets): 
    b = getnewlink(soup)
    print b
    red = urllib.urlopen(b)
    html = red.read()
    soup = BeautifulSoup(html)
    gettweets(soup)
    stamp = checkforstamp(soup)
    tweets = are_more_tweets(soup)
 print 'done' 

Answer 1

您的soup.findall() 正在获取与您的模式匹配的链接中的图像标签（具有href 属性和class status-link）。

不要总是在第一个链接上returning，试试：

for time in times:
    stamp = time.renderContents()
    test_stamp = str(stamp)
    print test_stamp
    if not test_stamp[0] in '0123456789':
        continue
    if test_stamp == '3 months ago':  
        return True
    else:
        return False

如果链接不以数字开头，它将跳过链接，因此您实际上可能会找到正确的链接。将print 声明保留在其中，这样您就可以查看是否点击了以数字开头的其他类型的链接，您还需要过滤掉该链接。

编辑：您所做的是总是返回在times中的第一个项。我对其进行了更改，使其忽略任何不以数字开头的链接。

但是，如果它没有找到带有数字的任何链接，这将导致它返回None。这可以正常工作，除非您将 while not stamp and tweets 更改为 while stamp is False and tweets is True。将其改回while not stamp and tweets，它将正确地将None和False视为相同，并且应该可以工作。