r'chuanzhiboke\t\.\tpython'

from urllib.request import urlopen
import redef spider_quotes():url = "http://quotes.toscrape.com"response = urlopen(url)html = response.read().decode("utf-8")#  获取 10  个  名言quotes = re.findall('<span class="text" itemprop="text">(.*)</span>',html)list_quotes = []for quote in quotes:#  strip 从两边开始搜寻，只要发现某个字符在当前这个方法的范围内，统统去掉list_quotes.append(quote.strip("“”"))# 获取 10 个名言的作者list_authors = []authors = re.findall('<small class="author" itemprop="author">(.*)</small>',html)for author in authors:list_authors.append(author)# 获取这10个名言的  标签tags = re.findall('<div class="tags">(.*?)</div>',html,re.RegexFlag.DOTALL)list_tags = []for tag in tags:temp_tags = re.findall('<a class="tag" href=".*">(.*)</a>',tag)tags_t1 = []for tag in temp_tags:tags_t1.append(tag)list_tags.append(",".join(tags_t1))# 结果汇总results = []for i in range(len(list_quotes)):results.append("\t".join([list_quotes[i],list_authors[i],list_tags[i]]))for result in results:print(result)#调取方法
spider_quotes()

from urllib.request import urlopen
from bs4 import BeautifulSoupurl = "http://quotes.toscrape.com"
response = urlopen(url)# 初始化一个 bs 实例
#  对应的response对象的解析器， 最常用的解析方式，就是默认的  html.parser
bs = BeautifulSoup(response, "html.parser")#  获取 10  个  名言
spans = bs.select("span.text")
list_quotes = []
for span in spans:span_text = span.textlist_quotes.append(span_text.strip("“”"))# 获取 10 个名言的作者
authors = bs.select("small")
list_authors = []
for author in authors:author_text = author.textlist_authors.append(author_text)# 获取这10个名言的  标签
divs = bs.select("div.tags")
list_tags = []
for div in divs:tag_text = div.select("a.tag")tag_list = [ tag_a.text for tag_a in tag_text]list_tags.append(",".join(tag_list))#结果汇总
results = []
for i in range(len(list_quotes)):results.append("\t".join([list_quotes[i],list_authors[i],list_tags[i]]))for result in results:print(result)