#Python爬虫#--使用Python-Goose提取文章标题内容图片

git clone https://github.com/grangier/python-goose.git
cd python-goose
python setup.py install

#!/usr/bin/python
# _*_ coding:utf-8 _*_
# author: Robinn

from goose import Goose
from bs4 import BeautifulSoup

class SourceTitle:
    def __init__(self,url,pagenum):
        self.url = url
        self.pagenum = pagenum


    def spider(self):
        titleList = []
        for i in self.pagenum:
            g = Goose()
            article = g.extract(url=self.url+str(i))
            soup = BeautifulSoup(article.raw_html,"html.parser")
            post_list = soup.find_all(class_="title2")
            for line in post_list:
                titleList.append(line.a.text)
        return titleList


if __name__ == "__main__":
    pageList = range(1,11)
    url = "http://jandan.net/tag/%E8%B5%B0%E8%BF%9B%E7%A7%91%E5%AD%A6/page/"
    gs = SourceTitle(url,pageList)
    plist = gs.spider()
    for title in plist:
        print(title)

#!/usr/bin/python
# _*_ coding:utf-8 _*_
# author: Robinn

from goose import Goose
from goose.text import StopWordsChinese

if __name__ == "__main__":
    url = "http://jandan.net/ooxx/page-1#comments"
    g = Goose({"stopwords_class":StopWordsChinese})
    article = g.extract(url=url)
    print(article.cleaned_text[:150])