python爬虫基础（requests、BeautifulSoup）
• request模块
1.发送请求
1 #get请求 2 requests.get(url='xxx', #地址 3 params={}, #传入URL的参数 4 headers={}, #请求头 5 cookies={} #cookie 6 ) #相当于requests.request(method='get',url='xxx') 7 #post请求 8 requests.post(url='xxx', 9 params={}, 10 headers={}, 11 data={}, #数据 12 json={}, #传json格式数据 13 cookies={} 14 ) #相当于requests.request(method='post',url='xxx')
1 response = requests.get('http://www.baidu.com') 2 print(response.status_code) # 打印状态码 3 print(response.url) # 打印请求url 4 print(response.headers) # 打印头信息 5 print(response.cookies) # 打印cookie信息 6 print(response.text) #以文本形式打印网页源码 7 print(response.content) #以字节流形式打印 8 response.encoding = response.apparent_encoding #apparent_encoding检测字符编码，encoding设置字符编码
2.其他参数
1 url 2 params 3 data #传入字典 4 json #传入字典 5 headers 6 cookies #传入字典 7 files #上传文件 8 auth #基本认证 9 timeout #超时时间 10 allow_redirects #是否允许重定向，默认为true 11 proxies #使用代理IP 12 verify 13 stream 14 cert
文档：http://docs.python-requests.org/zh_CN/latest/user/quickstart.html
• BeautifulSoup
1. name，标签名称 # tag = soup.find('a') # name = tag.name # 获取 # tag.name = 'span' # 设置 2. attr，标签属性 # tag = soup.find('a') # attrs = tag.attrs # 获取 # tag.attrs = {'ik':123} # 设置 # tag.attrs['id'] = 'iiiii' # 设置 3. children,所有子标签 # body = soup.find('body') # v = body.children 4. children,所有子子孙孙标签 # body = soup.find('body') # v = body.descendants 5. clear,将标签的所有子标签全部清空（保留标签名） # tag = soup.find('body') # tag.clear() 6. decompose,递归的删除所有的标签 # body = soup.find('body') # body.decompose() 7. extract,递归的删除所有的标签，并获取删除的标签 # body = soup.find('body') # v = body.extract() 8. decode,转换为字符串（含当前标签）；decode_contents（不含当前标签） # body = soup.find('body') # v = body.decode() # v = body.decode_contents() 9. encode,转换为字节（含当前标签）；encode_contents（不含当前标签） # body = soup.find('body') # v = body.encode() # v = body.encode_contents() 10. find,获取匹配的第一个标签 # tag = soup.find('a') # tag = soup.find(name='a', attrs={'class': 'sister'}, recursive=True, text='Lacie') # tag = soup.find(name='a', class_='sister', recursive=True, text='Lacie') 11. find_all,获取匹配的所有标签 # tags = soup.find_all('a') # tags = soup.find_all('a',limit=1) # tags = soup.find_all(name='a', attrs={'class': 'sister'}, recursive=True, text='Lacie') # v = soup.find_all(name=['a','div']) # v = soup.find_all(class_=['sister0', 'sister']) # v = soup.find_all(text=['Tillie']) # v = soup.find_all(id=['link1','link2']) # v = soup.find_all(href=['link1','link2']) # ####### 正则 ####### import re # rep = re.compile('^p') # v = soup.find_all(name=rep) # rep = re.compile('sister.*') # v = soup.find_all(class_=rep) # rep = re.compile('http://www.oldboy.com/static/.*') # v = soup.find_all(href=rep) # ####### 方法筛选 ####### # def func(tag): # return tag.has_attr('class') and tag.has_attr('id') # v = soup.find_all(name=func) # ## get,获取标签属性 # tag = soup.find('a') # v = tag.get('id') 12. has_attr,检查标签是否具有该属性 # tag = soup.find('a') # v = tag.has_attr('id') 13. get_text,获取标签内部文本内容 # tag = soup.find('a') # v = tag.get_text('id') 14. index,检查标签在某标签中的索引位置 # tag = soup.find('body') # v = tag.index(tag.find('div')) # 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' # tag = soup.find('br') # v = tag.is_empty_element # print(v) 16. 当前的关联标签 # 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") 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"]') 19. 标签的内容 # tag = soup.find('span') # print(tag.string) # 获取 # tag.string = 'new content' # 设置 # tag = soup.find('body') # v = tag.stripped_strings # 递归内部获取所有标签的文本 20.append在当前标签内部追加一个标签 # 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)
• 抽屉网实现批量点赞
1 from bs4 import BeautifulSoup 2 import requests 3 4 5 headers={ 6 'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2785.104 Safari/537.36 Core/1.53.4882.400 QQBrowser/9.7.13059.400', 7 } 8 9 10 resoponse_1 = requests.get(url='https://dig.chouti.com/', 11 headers=headers 12 ) 13 cookie_dict = resoponse_1.cookies.get_dict() 14 15 resoponse_2 = requests.post( 16 url='https://dig.chouti.com/login', 17 data={ 18 'phone':'8615733239039', 19 'password':'xxxxxx', 20 'oneMonth':'1', 21 }, 22 headers=headers, 23 cookies=cookie_dict 24 ) 25 for page in range(1,3): 26 html = requests.get(url='https://dig.chouti.com/all/hot/recent/{}'.format(page),headers=headers) 27 soup = BeautifulSoup(html.text,'html.parser') 28 divs = soup.find(name='div',id='content-list') 29 items = divs.find_all(attrs={'class':'item'}) 30 for i in items: 31 click_id = i.find('img').get('lang') 32 if click_id: 33 print(click_id) 34 click_hand = requests.post(url='https://dig.chouti.com/link/vote?linksId={}'.format(click_id), 35 headers=headers, 36 cookies=cookie_dict, 37 )
参考链接：http://www.cnblogs.com/wupeiqi/articles/6283017.html
