抓取oschina上面的代码分享python块区下的 标题和对应URL

时间:2021-08-09 13:55:20
# -*- coding=utf-8 -*-
import requests,re
from lxml import etree
import sys
reload(sys)
sys.setdefaultencoding( "utf-8" ) """
目标:抓取oschina上面的代码分享python块区下的 标题和对应URL
"""
class spiders_oschina:
def __init__(self):
print u'开始运行' def get_html_obj(self,url = 'http://www.oschina.net/code/list?lang=python&catalog=&show=time&sort=&p=1'): #传入地址,返回一个xpath对象
tou = {'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.110 Safari/537.36'}
obj = etree.HTML(requests.get(url,headers = tou).content) # 实例化可以被lxml操作的对像
return obj def get_page(self):
tmp = '//*[@id="OSC_Content"]/div[1]/ul/li[11]/a/text()'
obj = self.get_html_obj()
page = int(obj.xpath(tmp)[0]) #从第一页可取得一共有多少页
urllist = []
for i in range(1,page+1):
urllist.append('http://www.oschina.net/code/list?lang=python&catalog=&show=time&sort=&p=' + str(i))
return urllist def get_result(self,obj): #需要传入一个xpath对像
tmp = '//*[@id="OSC_Content"]/div[1]/div[3]/ul/li/h3/a/text()' #a标签中的文本
tmp2 = '//*[@id="OSC_Content"]/div[1]/div[3]/ul/li/h3/a/@href' #a标签的href属性
t = obj.xpath(tmp) #[0].decode('utf-8') #测试xpath方法
t2 = obj.xpath(tmp2)
f = open('res.txt','a')
str = ''
for i in t:
n = 0
str += i + ' ——>对应的URL是:' + t2[n] + '\n \n --------------------------\n'
n += 1
f.write(str) #把结果最终写入txt文本
f.close() if __name__ == "__main__":
oca = spiders_oschina()
n = 1
for i in oca.get_page():
obj = oca.get_html_obj(i)
oca.get_result(obj)
print u'第%d页爬取完成' %n
n += 1

貌似生成的url有问题,待优化。。。