''' Created on 2017年4月5日 @author: Admin ''' import requests from bs4 import BeautifulSoup as bsp # 网站链接 site = 'http://www.runoob.com' lineNo = 1 class Movie: def __init__(self, name, url): self.name = name self.url = url def __str__(self): return '%s,\t%s分,\t%s' % (self.name, self.url) __repr__ = __str__ def getSoup(url): r = requests.get(url) # r.encoding = 'gb18030' return bsp(r.text, "html.parser") # 解析指定url,获取其中指定内容 def filterMovie(url): resultList = []
# url处理,注意页面的编码集 soup = getSoup(url)
# 查找所有target=_top的a标签 atags = soup.find_all('a', target='_top') for atag in atags:
# 取到指定a标签的title属性 titleA = atag['title'] if atag is not None: try:
# 根据取到的href属性,拼接上页面域名 获得完整的跳转url url = site + atag['href'] print('url:', url) print('title:', titleA)
# 根据主方法里面 _init_ 中定义的内容,将获取到的字段进行组合,然后放到集合中 movie = Movie(titleA, url) resultList.append(movie) except: print('error !!') return resultList # 根据传入的结果结合 按照指定格式保存到 文本文件中 def saveInfo(atagList): # 注意指定编码,否则输入到txt文件的时候会乱码 fileObj = open('vueJS.txt', 'a',encoding='utf8') for atag in atagList: atagName = str(atag.name) print('url info:', atagName) global lineNo fileObj.write('(' + str(lineNo) + ') ' + atagName ) fileObj.write('\t') fileObj.write(atag.url) fileObj.write( '————————————————————————————————————————————————————————————————————————————————————————————————') fileObj.write('\n') lineNo += 1 fileObj.close() # 获取到根据url整理出的一个结果集合,然后将结果集合保存的物理文件中 def getPageResource(url):
resultList = filterMovie(url) if len(resultList) > 0: saveInfo(resultList)
# 方法入口,定义一个页面url,然后去解析 if __name__ == '__main__': url = 'http://www.runoob.com/vue2/vue-tutorial.html' getPageResource(url)