爬虫实战

from bs4 import BeautifulSoup


with open('new_index.html') as wb_date:
	Soup = BeautifulSoup(wb_date,'lxml')
	lis = Soup.select('body > div.main-content > ul > li')
	for li in lis:
		image=li.select('li > img')[0].get('src')
		title= li.select('li > div.article-info > h3 > a')[0].get_text()
		descs = li.select('li > div.article-info > p.description')[0].get_text()
		rates = li.select('li > div.rate > span')[0].get_text()
		cates =list(li.select('li > div.article-info > p.meta-info ')[0].stripped_strings)


		if float(rates)>3:
			print(title,descs,rates,image)
	
	

	


'''
from bs4 import BeautifulSoup
info =[]
with open('new_index.html') as wb_date:
	Soup = BeautifulSoup(wb_date,'lxml')
	
	images=Soup.select('body > div.main-content > ul > li > img')
	titles = Soup.select('body > div.main-content > ul > li > div.article-info > h3 > a')
	descs = Soup.select('body > div.main-content > ul > li > div.article-info > p.description')
	rates = Soup.select('body > div.main-content > ul > li > div.rate > span')
	cates =Soup.select('body > div.main-content > ul > li > div.article-info > p.meta-info ')
	
	
	#print(images,title,descs,rates,cates,sep ='\n------------------\n')
	
for title,desc,rate,cate,image in zip(titles,descs,rates,cates,images):
	data = {
		'title': title.get_text(),
		'desc': desc.get_text(),
		'rate': rate.get_text(),
		'cate': list(cate.stripped_strings),
		'image': image.get('src')
	}
	#print(date)
	info.append(data)

for i in info:
	if float(i['rate'])>3:
		print(i['title'],i['cate'])
'''