爬虫笔记二
一、BeautifulSoup模块
BeautifulSoup模块，该模块用于接收一个HTML或XML字符串，然后将其进行格式化，之后便可以使用它提供的方法进行快速查找指定元素，从而使得在HTML或XML中查找指定元素变得简单。
安装：
pip3 install beautifulsoup4 pip3 install lxml
使用示例：
from bs4 import BeautifulSoup html_doc = """ <html><head><title>The Dormouse's story</title></head> <body> asdf <div class="title"> <b>The Dormouse's story总共</b> <h1>f</h1> </div> <div class="story">Once upon a time there were three little sisters; and their names were <a class="sister0" id="link1">Els<span>f</span>ie</a>, <a href="http://example.com/lacie" class="sister" id="link2">Lacie</a> and <a href="http://example.com/tillie" class="sister" id="link3">Tillie</a>; and they lived at the bottom of a well.</div> ad<br/>sf <p class="story">...</p> </body> </html> """ # soup = BeautifulSoup(html_doc,'html.parser') # 内置的parser soup = BeautifulSoup(html_doc, features="lxml") # 找到第一个a标签 tag1 = soup.find(name='a') # 找到所有的a标签 tag2 = soup.find_all(name='a') # 找到id＝link2的标签 类似css选择器 tag3 = soup.select('#link2')
1. name 标签名称
soup = BeautifulSoup(html_doc, features="lxml")
tag = soup.find('a')
name = tag.name # 获取标签名称
print(name)
tag.name = 'span' # 把soup中的a标签改成span标签
print(soup)
2. attr，标签属性
soup = BeautifulSoup(html_doc, features="lxml")
tag = soup.find('a')
attrs = tag.attrs # 获取第一个a标签中含有的属性
print(attrs)
tag.attrs = {'ik':123} # 给找到的第一个a标签设置属性
tag.attrs['id'] = 'iiiii' # 给找到的第一个a标签设置属性
print(soup)
3.children,所有子标签
soup = BeautifulSoup(html_doc, features="lxml")
body = soup.find('body')
v = body.children
4. children 所有的子子孙孙标签
soup = BeautifulSoup(html_doc, features="lxml")
body = soup.find('body') # 先找到body标签
v = body.descendants # 找到body标签里所有的子孙标签
# v是一个生成器，需要循环遍历出来
for i in v:
print(i,end=' ')
5. clear,将标签的所有子标签全部清空（保留外层标签名）
soup = BeautifulSoup(html_doc, features="lxml")
tag = soup.find('body')
tag.clear()
print(soup)
6. decompose,递归的删除所有的标签（包括外层标签）
soup = BeautifulSoup(html_doc, features="lxml")
body = soup.find('body')
body.decompose()
print(soup)
7. extract,递归的删除所有的标签，并获取删除的标签
soup = BeautifulSoup(html_doc, features="lxml")
body = soup.find('body')
v = body.extract()
print(soup)
8. decode,转换为字符串（含当前标签）；decode_contents（不含当前标签）
soup = BeautifulSoup(html_doc, features="lxml")
body = soup.find('body')
# v = body.decode()
v = body.decode_contents()
print(v,type(v))
9. encode,转换为字节（含当前标签）；encode_contents（不含当前标签）
soup = BeautifulSoup(html_doc, features="lxml")
body = soup.find('body')
# v = body.encode()
v = body.encode_contents()
print(v,type(v))
10. find,获取匹配的第一个标签
soup = BeautifulSoup(html_doc, features="lxml")
# 找到第一个a标签
tag = soup.find('a')
print(tag)
# 找到属性中有class="sister" 文本内容为Lacie 符合要求的第一个a标签
tag = soup.find(name='a', attrs={'class': 'sister'}, recursive=True, text='Lacie')
# tag = soup.find(name='a', class_='sister', recursive=True, text='Lacie')
print(tag)
11. find_all,获取匹配的所有标签
soup = BeautifulSoup(html_doc, features="lxml")
# 找到所有a标签
tags = soup.find_all('a')
print(tags)
# 找到所有的a标签后取第一个
tags = soup.find_all('a',limit=1)
print(tags)
# 找到所有属性class="sister" 文本内容为Lacie 的a标签
tags = soup.find_all(name='a', attrs={'class': 'sister'}, recursive=True, text='Lacie')
# tags = soup.find(name='a', class_='sister', recursive=True, text='Lacie')
print(tags)
# ####### 列表 #######
v = soup.find_all(name=['a','div'])
print(v)
v = soup.find_all(class_=['sister0', 'sister'])
print(v)
v = soup.find_all(text=['Tillie'])
print(v, type(v[0]))
v = soup.find_all(id=['link1','link2'])
print(v)
v = soup.find_all(href=['link1','link2'])
print(v)
# ####### 正则 #######
import re
# rep = re.compile('p')
rep = re.compile('^p')
v = soup.find_all(name=rep)
print(v)
rep = re.compile('sister.*')
v = soup.find_all(class_=rep)
print(v)
rep = re.compile('http://www.oldboy.com/static/.*')
v = soup.find_all(href=rep)
print(v)
# ####### 方法筛选 #######
def func(tag):
return tag.has_attr('class') and tag.has_attr('id')
v = soup.find_all(name=func)
print(v)
## get,获取标签属性
tag = soup.find('a')
v = tag.get('id')
print(v)
12. has_attr,检查标签是否具有该属性
soup = BeautifulSoup(html_doc, features="lxml")
tag = soup.find('a')
v = tag.has_attr('id')
print(v)
13. get_text,获取标签内部文本内容
soup = BeautifulSoup(html_doc, features="lxml")
tag = soup.find('a')
v = tag.get_text()
print(v)
14. index,检查标签在某标签中的索引位置
soup = BeautifulSoup(html_doc, features="lxml")
tag = soup.find('body')
v = tag.index(tag.find('div'))
print(v)
tag = soup.find('body')
for i,v in enumerate(tag):
print(i,v)
15. is_empty_element,是否是空标签(是否可以是空)或者自闭合标签，判断是否是如下标签：'br' , 'hr', 'input', 'img', 'meta','spacer', 'link', 'frame', 'base'
soup = BeautifulSoup(html_doc, features="lxml")
tag = soup.find('br')
v = tag.is_empty_element
print(v)
16. 当前的关联标签
soup = BeautifulSoup(html_doc, features="lxml") # soup.next # soup.next_element # soup.next_elements # soup.next_sibling # soup.next_siblings # # tag.previous # tag.previous_element # tag.previous_elements # tag.previous_sibling # tag.previous_siblings # # tag.parent # tag.parents
17. 查找某标签的关联标签
# tag.find_next(...) # tag.find_all_next(...) # tag.find_next_sibling(...) # tag.find_next_siblings(...) # tag.find_previous(...) # tag.find_all_previous(...) # tag.find_previous_sibling(...) # tag.find_previous_siblings(...) # tag.find_parent(...) # tag.find_parents(...) # 参数同find_all
18. select,select_one, CSS选择器
soup.select("title")
soup.select("p nth-of-type(3)")
soup.select("body a")
soup.select("html head title")
tag = soup.select("span,a")
soup.select("head > title")
soup.select("p > a")
soup.select("p > a:nth-of-type(2)")
soup.select("p > #link1")
soup.select("body > a")
soup.select("#link1 ~ .sister")
soup.select("#link1 + .sister")
soup.select(".sister")
soup.select("[class~=sister]")
soup.select("#link1")
soup.select("a#link2")
soup.select('a[href]')
soup.select('a[href="http://example.com/elsie"]')
soup.select('a[href^="http://example.com/"]')
soup.select('a[href$="tillie"]')
soup.select('a[href*=".com/el"]')
from bs4.element import Tag
def default_candidate_generator(tag):
for child in tag.descendants:
if not isinstance(child, Tag):
continue
if not child.has_attr('href'):
continue
yield child
tags = soup.find('body').select("a", _candidate_generator=default_candidate_generator)
print(type(tags), tags)
from bs4.element import Tag
def default_candidate_generator(tag):
for child in tag.descendants:
if not isinstance(child, Tag):
continue
if not child.has_attr('href'):
continue
yield child
tags = soup.find('body').select("a", _candidate_generator=default_candidate_generator, limit=1)
print(type(tags), tags)
19. 标签的内容
# tag = soup.find('span')
# print(tag.string) # 获取
# tag.string = 'new content' # 设置
# print(soup)
# tag = soup.find('body')
# print(tag.string)
# tag.string = 'xxx'
# print(soup)
# tag = soup.find('body')
# v = tag.stripped_strings # 递归内部获取所有标签的文本
# print(v)
20.append在当前标签内部追加一个标签
soup = BeautifulSoup(html_doc, features="lxml")
tag = soup.find('body')
tag.append(soup.find('a'))
print(soup)
from bs4.element import Tag
obj = Tag(name='i',attrs={'id': 'it'})
obj.string = '我是一个新来的'
tag = soup.find('body')
tag.append(obj)
print(soup)
21.insert在当前标签内部指定位置插入一个标签
# from bs4.element import Tag
# obj = Tag(name='i', attrs={'id': 'it'})
# obj.string = '我是一个新来的'
# tag = soup.find('body')
# tag.insert(2, obj)
# print(soup)
22. insert_after,insert_before 在当前标签后面或前面插入
# from bs4.element import Tag
# obj = Tag(name='i', attrs={'id': 'it'})
# obj.string = '我是一个新来的'
# tag = soup.find('body')
# # tag.insert_before(obj)
# tag.insert_after(obj)
# print(soup)
23. replace_with 在当前标签替换为指定标签
# from bs4.element import Tag
# obj = Tag(name='i', attrs={'id': 'it'})
# obj.string = '我是一个新来的'
# tag = soup.find('div')
# tag.replace_with(obj)
# print(soup)
24. 创建标签之间的关系
# tag = soup.find('div')
# a = soup.find('a')
# tag.setup(previous_sibling=a)
# print(tag.previous_sibling)
25. wrap，将指定标签把当前标签包裹起来
# from bs4.element import Tag
# obj1 = Tag(name='div', attrs={'id': 'it'})
# obj1.string = '我是一个新来的'
#
# tag = soup.find('a')
# v = tag.wrap(obj1)
# print(soup)
# tag = soup.find('a')
# v = tag.wrap(soup.find('p'))
# print(soup)
26. unwrap，去掉当前标签，将保留其包裹的标签
# tag = soup.find('a')
# v = tag.unwrap()
# print(soup)
转载：武沛齐
二、爬虫性能相关
详细：性能相关
import socket import select class Request(object): def __init__(self, sock, info): self.sock = sock self.info = info # 调用sock内部的fileno方法 def fileno(self): return self.sock.fileno() class AsyncRequest(object): def __init__(self): self.sock_list = [] self.conns = [] def add_request(self, req_info): """ 创建请求 req_info: {'host': 'www.baidu.com', 'port': 80, 'path': '/'}, :return: """ sock = socket.socket() sock.setblocking(False) try: sock.connect((req_info['host'], req_info['port'])) except BlockingIOError as e: pass obj = Request(sock, req_info) self.sock_list.append(obj) self.conns.append(obj) def run(self): """ 开始事件循环,检测：连接成功？数据是否返回？ :return: """ while True: # select.select([socket对象,]) # 可是任何对象，对象一定要fileno方法 # 对象.fileno() # select.select([request对象,]) rlist, wlist, elist = select.select(self.sock_list, self.conns, [], 0.05) # wlist,是否连接成功 for obj in wlist: # 检查obj:request对象 # socket, {'host': 'www.baidu.com', 'port': 80, 'path': '/'}, data = "GET %s http/1.1\r\nhost:%s\r\n\r\n" % (obj.info['path'], obj.info['host']) obj.sock.send(data.encode('utf-8')) self.conns.remove(obj) # rlist 数据返回，接收到数据 for obj in rlist: response = obj.sock.recv(8096) obj.info['callback'](response) self.sock_list.remove(obj) # self.sock_list为空时，表明所有请求已经返回 if not self.sock_list: break # 相应网址定制的回调函数 def done1(response): print(response) # 相应网址定制的回调函数 def done2(response): print(response) url_list = [ {'host': 'www.baidu.com', 'port': 80, 'path': '/', 'callback': done1}, {'host': 'www.cnblogs.com', 'port': 80, 'path': '/index.html', 'callback': done2}, {'host': 'www.bing.com', 'port': 80, 'path': '/', 'callback': done2}, ] asyncRequest = AsyncRequest() for item in url_list: asyncRequest.add_request(item) asyncRequest.run()
import socket import select ############### HTTP请求本质 阻塞 """ sk = socket.socket() # 连接 sk.connect(('www.baidu.com',80)) # IO阻塞 print('连接成功') # 发送消息 sk.send(b'GET / HTTP/1.0\r\nHost:www.baidu.com\r\n\r\n') # 等待服务端响应 data = sk.recv(8096) # IO阻塞 print(data) #关闭连接 sk.close() """ ############### HTTP请求本质 非阻塞 # sk = socket.socket() # sk.setblocking(False) # # try: # # 连接 # sk.connect(('www.baidu.com',80)) # IO阻塞 # print('连接成功') # except BlockingIOError as e: # print(e) # # # 发送消息 # sk.send(b'GET / HTTP/1.0\r\nHost:www.baidu.com\r\n\r\n') # # # 等待服务端响应 # data = sk.recv(8096) # IO阻塞 # print(data) # # #关闭连接 # sk.close() #########################
url_list = [ 'http://www.cnblogs.com/wupeiqi/articles/6229292.html', 'http://www.baidu.com', 'http://www.xiaohuar.com', ] import requests # 1. 穿行(6s，1个) # for url in url_list: # response = requests.get(url) # print(response.content) # 2. 线程，进程(3s，三个) # from concurrent.futures import ThreadPoolExecutor,ProcessPoolExecutor # # def tast(url): # response = requests.get(url) # print(response.content) # # pool = ThreadPoolExecutor(10) # # pool = ProcessPoolExecutor(10) # for url in url_list: # # requests.get(url) # pool.submit(tast,url) # 线程池中获取一个线程，执行task函数 # pool.shutdown(wait=True) # 3. 异步非阻塞 # 【异步】，回调(请求发出去后就不管了，然后去干别的事情，等执行完后回调函数告诉我一下，) # 【非阻塞】，不等，socket， # 阻塞： client = socket();client.connet(ip,端口) # 非阻塞：client = socket(); client.setblocking(False); client.connet(ip,端口) # 【协程】和异步非阻塞没有关系，协程是人为的先控制这执行一会儿然后再那儿执行一会儿 #连接；发送数据；接受数据 from twisted.web.client import getPage, defer from twisted.internet import reactor def all_done(arg): reactor.stop() def callback(contents): print(contents) deferred_list = [] url_list = ['http://www.bing.com', 'http://www.baidu.com', ] for url in url_list: deferred = getPage(bytes(url, encoding='utf8')) # requests deferred.addCallback(callback) deferred_list.append(deferred) dlist = defer.DeferredList(deferred_list) dlist.addCallback(all_done) reactor.run()
