Last active
December 10, 2015 06:58
-
-
Save seckcoder/4397413 to your computer and use it in GitHub Desktop.
Crawl weibo(repost timeline) asynchronously in python. It needs gevent and sina python weibo client(https://github.com/michaelliao/sinaweibopy) installed.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import math | |
import gevent | |
import gevent.greenlet | |
from gevent import monkey | |
from functools import partial | |
monkey.patch_all() | |
from weibo import APIClient | |
import time | |
class ActionCounter: | |
def __init__(self, count=0, finished=0): | |
self.count = count | |
self.finished = finished | |
def main(mid, access_token): | |
client = APIClient(None, None) | |
client.set_access_token(access_token, time.time() + 3600 * 60) | |
weibo_id = client.get.statuses__queryid( | |
access_token=access_token, mid=mid, type=1, isBase62=1)['id'] | |
root_tweet = client.get.statuses__show(access_token=access_token, id=weibo_id) | |
nreposts_per_page = 200 | |
def get_reposts(page, callback=None): | |
try: | |
reply = client.get.statuses__repost_timeline( | |
id=weibo_id, count=nreposts_per_page, page=page) | |
if callback: | |
callback(reply) | |
except Exception, e: | |
print "Exception %s happended" % e | |
tweets = {} | |
def crawl_callback(depth, reply): | |
if reply and reply.has_key("reposts"): | |
for repost in reply["reposts"]: | |
if add_tweet(repost): | |
crawl_reposts(repost, depth + 1) | |
def crawl_reposts(tweet, depth): | |
if depth >= 5: | |
return | |
if not (tweet and tweet.has_key("reposts_count")): | |
return | |
total_reposts_count = tweet.reposts_count | |
page_num = int(math.ceil(float(total_reposts_count) / nreposts_per_page)) | |
#print tweet.user.screen_name, page_num | |
if page_num > 0 and total_reposts_count >= 2: | |
# Instead of using link of Greenlet, I use callback directly since spawning greenlet in the link seems not work | |
gs = [gevent.spawn(get_reposts, page, partial(crawl_callback, depth)) for page in xrange(1, page_num+1)] | |
gevent.joinall(gs) | |
def add_tweet(tweet): | |
if not tweets.has_key(tweet.id) and tweet.has_key("reposts_count"): | |
tweets[tweet.id] = { | |
"id": tweet.id, | |
"text": tweet.text, | |
"reposts_count": tweet.reposts_count | |
} | |
return True | |
return False | |
crawl_reposts(root_tweet, 1) | |
return tweets | |
if __name__ == "__main__": | |
try: | |
now = time.time() | |
mid = "zbQaYdw5V" | |
access_token = "xxx" | |
print "This will take some time..." | |
tweets = main(mid, access_token) | |
print "Total number of tweets:", len(tweets) | |
print "Take %s seconds" % (time.time() - now) | |
except Exception, e: | |
print e |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment