清华大佬耗费三个月吐血整理的几百G的资源，免费分享！....>>>
import requests
import lxml
from lxml import etree
def get_content(url):
try:
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.2; WOW64; rv:37.0) Gecko/20100101 Firefox/37.0'}
r = requests.get(url, headers = headers)
return '<html>' + r.content.decode('utf-8') + '</html>'
except Exception as exc:
#raise exc
return None
class User(object):
pass
def parse_content(content):
if content is None: return []
try:
xml = etree.fromstring(content)
divs= xml.findall('li/div')
page_info = []
for div in divs:
u = User()
tweets = div.findall('p')
if len(tweets) < 2:
continue
user_and_text = list(tweets[0].itertext())
u.name,u.txt = user_and_text if len(user_and_text) == 2 else [None]*2
data_comments = list(tweets[1].itertext())
u.data,u.commtents,u.client = data_comments if len(data_comments) ==3 else [None]*3
u.link = tweets[1].xpath('a')[0].get('href')
page_info.append(u)
return page_info
except Exception as exc:
raise exc
def test():
url = "http://www.oschina.net/fetch_tweets?p=40"
content = get_content(url)
infos = parse_content(content)
for u in infos:
print(u.name)
print(u.txt)
print(u.client.split('\n')[1].strip() if u.client else u.client)
#print(u.name, u.txt)
if __name__ == '__main__':
test()