python爬虫科研数据提取_python爬虫数据提取四之pyquery

1 pyquery

简介：同样是一个强大的网页解析工具 它提供了和jQuery类似的语法来解析HTML文档，支持CSS选择器，使用非常方便

2 pyquery基本用法

2.1 安装

pip install pyquery

2.2 初始化

字符串初始化

html = '''

• first item
• second item
• third item
• fourth item
• fifth item

'''

from pyquery import PyQuery as pq

doc = pq(html)

print(doc('li'))

first item second item third item fourth item fifth item

URL初始化

from pyquery import PyQuery as pq

doc = pq(url='http://www.baidu')

print(doc('head'))

ç�¾åº¦ä¸�ä¸�ï¼�ä½ å°±ç�¥é��

文件初始化

from pyquery import PyQuery as pq

doc = pq(filename='test.html')

print(doc('li'))

11111111112222222222333333333344444444445555555555

2.3 基本CSS选择器

html = '''

• first item
• second item
• third item
• fourth item
• fifth item

'''

from pyquery import PyQuery as pq

doc = pq(html)

print(doc('#container .list li'))

first item second item third item fourth item fifth item

2.4 查找元素

2.4.1 子元素

html = '''

• first item
• second item
• third item
• fourth item
• fifth item

'''

from pyquery import PyQuery as pq

doc = pq(html)

items = doc('.list')

print(type(items))

print(items)

lis = items.find('li')

print(type(lis))

print(lis)

• first item
• second item
• third item
• fourth item
• fifth item

first item second item third item fourth item fifth item

lis = items.children()

print(type(lis))

print(lis)

first item second item third item fourth item fifth item

lis = items.children('.active')

print(lis)

third item fourth item

注意：这里的item-0和active是两个类，在html中可以给同一元素设置两个类，中间用空格隔开

2.4.2 父元素

html = '''

• first item
• second item
• third item
• fourth item
• fifth item

'''

from pyquery import PyQuery as pq

doc = pq(html)

items = doc('.list')

container = items.parent()

print(type(container))

print(container)

• first item
• second item
• third item
• fourth item
• fifth item

html = '''

• first item
• second item
• third item
• fourth item
• fifth item

'''

from pyquery import PyQuery as pq

doc = pq(html)

items = doc('.list')

parents = items.parents()

print(type(parents))

print(parents)

• first item
• second item
• third item
• fourth item
• fifth item

• first item
• second item
• third item
• fourth item
• fifth item

parent = items.parents('.wrap')

print(parent)

• first item
• second item
• third item
• fourth item
• fifth item

2.4.3 兄弟元素

html = '''

• first item
• second item
• third item
• fourth item
• fifth item

'''

from pyquery import PyQuery as pq

doc = pq(html)

li = doc('.list .item-0.active')

print(li.siblings())

second itemfirst item fourth item fifth item

可以看到，结果的顺序并不是完全和输入的顺序一致

html = '''

• first item
• second item
• third item
• fourth item
• fifth item

'''

from pyquery import PyQuery as pq

doc = pq(html)

li = doc('.list .item-0.active') # 表示class为list的元素下的元素，这个元素的class为item-0和active

print(li.siblings('.active'))

fourth item

2.5 遍历

单个元素

html = '''

• first item
• second item
• third item
• fourth item
• fifth item

'''

from pyquery import PyQuery as pq

doc = pq(html)

li = doc('.item-0.active')

print(li)

third item

多个元素

html = '''

• first item
• second item
• third item
• fourth item
• fifth item

'''

from pyquery import PyQuery as pq

doc = pq(html)

lis = doc('li').items()

print(type(lis))

for li in lis:

print(li)

first item second item third item fourth item fifth item

2.6 获取信息

获取属性

html = '''

• first item
• second item
• third item
• fourth item
• fifth item

'''

from pyquery import PyQuery as pq

doc = pq(html)

a = doc('.item-0.active a')

print(a)

print(a.attr('href'))

print(a.attr.href)

third item

link3.html

link3.html

获取文本

html = '''

• first item
• second item
• third item
• fourth item
• fifth item

'''

from pyquery import PyQuery as pq

doc = pq(html)

a = doc('.item-0.active a')

print(a)

print(a.text())

third item

third item

获取HTML

html = '''

• first item
• second item
• third item
• fourth item
• fifth item

'''

from pyquery import PyQuery as pq

doc = pq(html)

li = doc('.item-0.active')

print(li)

print(li.html())

third item

third item

2.7 DOM操作

addClass、removeClass

html = '''

• first item
• second item
• third item
• fourth item
• fifth item

'''

from pyquery import PyQuery as pq

doc = pq(html)

li = doc('.item-0.active')

print(li)

li.removeClass('active')

print(li)

li.addClass('active')

print(li)

third item third item third item

attr、css

html = '''

• first item
• second item
• third item
• fourth item
• fifth item

'''

from pyquery import PyQuery as pq

doc = pq(html)

li = doc('.item-0.active')

print(li)

li.attr('name', 'link')

print(li)

li.css('font-size', '14px')

print(li)

third item third item third item

remove

html = '''

Hello, World

This is a paragraph.

'''

from pyquery import PyQuery as pq

doc = pq(html)

wrap = doc('.wrap')

print(wrap.text())

wrap.find('p').remove()

print(wrap.text())

Hello, World

This is a paragraph.

Hello, World

2.8 伪类选择器

html = '''

• first item
• second item
• third item
• fourth item
• fifth item

'''

from pyquery import PyQuery as pq

doc = pq(html)

li = doc('li:first-child')

print(li)

li = doc('li:last-child')

print(li)

li = doc('li:nth-child(2)')

print(li)

li = doc('li:gt(2)')# index > 2 的所有子元素，从0开始

print(li)

li = doc('li:nth-child(2n)')

print(li)

li = doc('li:contains(second)') # 根据文本选择

print(li)

first item fifth item second item fourth item fifth item second item fourth item second item

3 实战---爬取百度校花吧(pyquery版)

import requests

from lxml import etree

import os

from pyquery import PyQuery as pq

class Baidu(object):

def __init__(self, name):

self.url = 'http://tieba.baidu/f?ie=utf-8&kw={}'.format(name)

# 使用较老版本的请求头，该浏览器不支持js

self.headers = {

'User-Agent': 'Mozilla/4.0 (compatible; MSIE 5.01; Windows NT 5.0) '

}

# 发送请求，获取响应

def get_data(self, url):

response = requests.get(url,headers=self.headers)

return response.content

# 解析列表页数据，获取列表页面帖子的标题和链接

def parse_list_page(self, data):

with open('baidu1.html','wb') as f:

f.write(data)

# 实例化etree对象

# html = etree.HTML(data).

doc = pq(data)

node_list= doc.find('.j_thread_list .threadlist_title a')

# 使用xpath语法，提取网页数据

# node_list = html.xpath("//*[@id='thread_list']/li[@class=' j_thread_list clearfix']/div/div[2]/div[1]/div[1]/a")

# 判断获取结果

# print(len(node_list))

data_list = []

# 遍历node_list

for node in node_list.items():

temp = {}

temp['url'] = 'http://tieba.baidu' + node.attr('href')

temp['title'] = node.text()

data_list.append(temp)

# 提取下一页的节点

next_node = doc.find('#frs_list_pager .next').attr('href')

# next_node = html.xpath('//*[@id="frs_list_pager"]/a[last()-1]/@href')[0]

# print(next_node)

# 拼接下一页的完整url

next_url = 'http:' + next_node

# print(next_url)

return data_list,next_url

def parse_detail_page(self, data_list):

html = etree.HTML(data_list)

doc = pq(data_list)

# 提取详情页面的图片链接

imagelst = doc.find('.BDE_Image').items()

image_list = [img.attr('src') for img in imagelst]

# image_list = html.xpath("//cc/div[contains(@class,'d_post')]/img[@class='BDE_Image']/@src")

# 返回图片节点列表

print(image_list)

return image_list

# 下载图片，保存图片文件

# 创建文件夹

def download(self, image_list):

if not os.path.exists('images1'):

os.makedirs('images1')

for image in image_list:

# os.sep在mac系统中是/,如果是windows系统，\\,跨平台

file_name = 'images1'+ os.sep + image.split('/')[-1]

image_data = self.get_data(image)

with open(file_name,'wb') as f:

f.write(image_data)

def run(self):

# 构造url和请求头

# 发送请求，获取响应

next_url = self.url

# 开启循环，

while next_url:

data = self.get_data(next_url)

# 解析列表页数据，返回的列表数据、下一页的的数据

data_list,next_url = self.parse_list_page(data)

# 解析详情页的数据，获取详情页的图片的链接地址

for data in data_list:

url = data['url']

result_list = self.get_data(url)

image_list = self.parse_detail_page(result_list)

# 保存数据，下载图片

self.download(image_list)

if __name__ == '__main__':

# 爬取百度校花吧所有图片并存在文件夹中

baidu = Baidu('校花吧')

baidu.run()