Twitter Python爬网程序的爬网机制问题

Question

Below is a small snippet of code I have for my twitter crawler mechanism:

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' 

The problem is, after my twitter crawler hits about 3 months of tweets, I would like it to stop going to the next page of a user. However, it does not appear to be doing that. It seems to continually going searching for the next page of tweets. I believe this is due to the fact that checkstamp keeps evaluating to False. Does anyone have any suggestions as to how I can modify the code so that the crawler keeps looking for the next page of tweets as long as there are more tweets (verified by are_more_tweets mechanism) and it hasn't hit 3 months of tweets yet??? Thanks!

EDIT - Please see below:

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

Your soup.findall() is picking up an image tag in a link that matches your pattern (has an href attribute and class status-link ).

Instead of always return ing on the very first link, try:

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

Which will skip the link if it doesn't start with a number, so you might actually get to the right link. Keep that print statement in there so you can see if you hit some other kind of link that starts with a number that you also need to filter out.

Edit: What you were doing was always returning on the very first item in times . I changed it so it ignored any links that didn't start with a number.

However, this would cause it to return None if it didn't find any links with a number. This would work fine, except you changed while not stamp and tweets to while stamp is False and tweets is True . Change it back to while not stamp and tweets and it will correctly treat None and False as the same, and it should work.