功能
1.自动登录csdn
2.查找未评论的资源并自动评论
用到的库
1.python自带的requests，获取以及发送网页数据
2.python自带的time，用作休眠，csdn资源一段时间内只允许评论一个资源，每评论一个资源要休息一段时间
3.BeautifulSoup，解析html文本，搜索文本中指定的标签和属性
过程
1.用chrome的开发者工具抓取登录以及评论的数据包，获取数据包格式
2.requests获取指定页面html文本
3.BeautifulSoup分析页面属性，提取评论以及登录必须的页面信息
4.对BeautifulSoup的结果进行筛选，去掉一些干扰的标签信息，并判断资源是否评论过
5.组装评论消息并post。
脚本
import requests
from BeautifulSoup import BeautifulSoup
import time
def commitfunc(source_id, refer):
commiturl='http://download.csdn.net/index.php/comment/post_comment?jsonpcallback=jsonp1419934439524&sourceid='+source_id+'&content=%E6%88%90%E5%8A%9F%E9%85%8D%E5%AF%B9%EF%BC%8C%E5%8F%AF%E4%BB%A5%E4%BD%BF%E7%94%A8%E3%80%82&rating=5&t=1419935091974'
commitdata = {
"Accept" : "text/javascript, application/javascript, */*",
"Accept-Encoding" : "gzip, deflate, sdch",
"Accept-Language" : "zh-CN,zh;q=0.8",
"Connection" : "keep-alive",
"Content-Type" :"application/x-www-form-urlencoded",
"cookie" : "",
"Host" : "download.csdn.net",
"Refer" : refer,
"User-Agent" : "Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36",
"X-Requested-With" : "XMLHttpRequest",
"jsonpcallback" : "jsonp1419934439524",
"sourceid" : source_id,
"content" : "a good resource, it's worth to download it",
"rating" : "5",
"t" : "1419935091974",
}
sess_source.post(commiturl, commitdata)
def GetPageCount():
url_source_page = url_source + "1"
html_source = sess_source.get(url_source_page).text
soup_source = BeautifulSoup(html_source)
#resource_once = soup_source.findAll('h3')
page_count = soup_source.find('div', attrs={'class': "page_nav"}).text
page_list = page_count.split()
page_ac = page_list[2].split('&')
return page_ac[0][1:len(page_ac[0])-1]
def CommitWholePage(page_nu):
url_source_page = url_source + page_nu
html_source = sess_source.get(url_source_page).text
soup_source = BeautifulSoup(html_source)
resource_once = soup_source.findAll('h3')
for element in resource_once:
if(len(element) > 1):
#print type(element.contents[0].attrs[0][1])
#print element.contents[0].attrs[0][1]
attr = element.contents[0].attrs[0][1].split('/')
reftext = '/detail/' + attr[2] + '/' + attr[3] + '#comment'
result = soup_source.findAll('a', attrs={'href' : reftext, 'class' : 'btn-comment'})
if len(result) != 0:
#sess_source.get(url_source_page)
commitfunc(attr[3], attr[2])
print attr[2]
print attr[3]
print "sleep"
time.sleep(70)
def logincsdn():
html_login = sess_source.get(url_login).text
soup_login = BeautifulSoup(html_login)
lt_value = soup_login.findAll('input', attrs={'name': "lt"})[0]['value']
execution_value = soup_login.findAll('input', attrs={'name': "execution"})[0]['value']
data_login = {
"lt" : lt_value,
"execution" : execution_value,
"_eventId" : "submit",
"username" : "xxxxx",
"password" : "xxxxx"
}
sess_source.post(url_login, data_login)
#main begin
url_login = "https://passport.csdn.net/account/login"
url_source = "http://download.csdn.net/my/downloads/"
sess_source = requests.session()
logincsdn()
total_page = GetPageCount()
for num in range(1,int(total_page)):
CommitWholePage(str(num))
from BeautifulSoup import BeautifulSoup
import time
def commitfunc(source_id, refer):
commiturl='http://download.csdn.net/index.php/comment/post_comment?jsonpcallback=jsonp1419934439524&sourceid='+source_id+'&content=%E6%88%90%E5%8A%9F%E9%85%8D%E5%AF%B9%EF%BC%8C%E5%8F%AF%E4%BB%A5%E4%BD%BF%E7%94%A8%E3%80%82&rating=5&t=1419935091974'
commitdata = {
"Accept" : "text/javascript, application/javascript, */*",
"Accept-Encoding" : "gzip, deflate, sdch",
"Accept-Language" : "zh-CN,zh;q=0.8",
"Connection" : "keep-alive",
"Content-Type" :"application/x-www-form-urlencoded",
"cookie" : "",
"Host" : "download.csdn.net",
"Refer" : refer,
"User-Agent" : "Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36",
"X-Requested-With" : "XMLHttpRequest",
"jsonpcallback" : "jsonp1419934439524",
"sourceid" : source_id,
"content" : "a good resource, it's worth to download it",
"rating" : "5",
"t" : "1419935091974",
}
sess_source.post(commiturl, commitdata)
def GetPageCount():
url_source_page = url_source + "1"
html_source = sess_source.get(url_source_page).text
soup_source = BeautifulSoup(html_source)
#resource_once = soup_source.findAll('h3')
page_count = soup_source.find('div', attrs={'class': "page_nav"}).text
page_list = page_count.split()
page_ac = page_list[2].split('&')
return page_ac[0][1:len(page_ac[0])-1]
def CommitWholePage(page_nu):
url_source_page = url_source + page_nu
html_source = sess_source.get(url_source_page).text
soup_source = BeautifulSoup(html_source)
resource_once = soup_source.findAll('h3')
for element in resource_once:
if(len(element) > 1):
#print type(element.contents[0].attrs[0][1])
#print element.contents[0].attrs[0][1]
attr = element.contents[0].attrs[0][1].split('/')
reftext = '/detail/' + attr[2] + '/' + attr[3] + '#comment'
result = soup_source.findAll('a', attrs={'href' : reftext, 'class' : 'btn-comment'})
if len(result) != 0:
#sess_source.get(url_source_page)
commitfunc(attr[3], attr[2])
print attr[2]
print attr[3]
print "sleep"
time.sleep(70)
def logincsdn():
html_login = sess_source.get(url_login).text
soup_login = BeautifulSoup(html_login)
lt_value = soup_login.findAll('input', attrs={'name': "lt"})[0]['value']
execution_value = soup_login.findAll('input', attrs={'name': "execution"})[0]['value']
data_login = {
"lt" : lt_value,
"execution" : execution_value,
"_eventId" : "submit",
"username" : "xxxxx",
"password" : "xxxxx"
}
sess_source.post(url_login, data_login)
#main begin
url_login = "https://passport.csdn.net/account/login"
url_source = "http://download.csdn.net/my/downloads/"
sess_source = requests.session()
logincsdn()
total_page = GetPageCount()
for num in range(1,int(total_page)):
CommitWholePage(str(num))
欢迎咨询和指正，python菜鸟一枚。
BeautifulSoup中文资料站：http://www.crummy.com/software/BeautifulSoup/bs3/documentation.zh.html#Iterating%20over%20a%20Tag