Python网络爬虫与信息提取

pip install requests

>>> import requests
>>> r = requests.get("http://www.baidu.com")
>>> r.status_code
200
>>> r.encoding = 'utf-8' #修改默认编码
>>> r.text      #打印网页内容

requests.request(method,url,**kwargs)
#method:请求方式，对应get/put/post等7种
#url：拟获取页面的url链接
#**kwargs：控制访问的参数，共13个

r  = requests.get(url)
完整方法：
requests.get(url,params=None,**kwargs)
    url:拟获取页面的url链接
    params:url中的额外参数，字典或字节流格式，可选
    **kwargs:12个控制访问的参数，可选

r = requests.head('http://httpbin.org/get')
r.headers

payload = {'key1':'value1','key2':'value2'} #新建一个字典
#向URL POST一个字典，自动编码为form（表单）
r = requests.post('http://httpbin.org/post',data = payload)
#向URL POST一个字符串，自动编码为data
r = requests.post('http://httpbin.org/post',data = 'ABC') 
print(r.text)     

import requests

def getHTMLText(url):
    try:
        r = requests.get(url,timeout=30)
        r.raise_for_status() #如果不是200，引发HTTPError异常
        r.recoding = r.apparent_encoding
        return r.text
    except:
        return "产生异常"
if __name__ == "__main__":
    url = "http://www.baidu.com"
    print(getHTMLText(url))

import requests

# 向搜索引擎进行关键词提交
url = "http://www.baidu.com"
try:
    kv = {'wd':'python'}
    r = requests.get(url,params =kv)
    print(r.request.url)
    r.raise_for_status()
    print(len(r.text))
except:
    print("产生异常")

import requests
import os
url = "http://image.ngchina.com.cn/2019/0423/20190423024928618.jpg"
root = "D://2345//Temp//"
path = root + url.split('/')[-1]
try:
    if not os.path.exists(root):
        os.mkdir(root)
    if not os.path.exists(path):
        r = requests.get(url)
        with open(path,'wb') as f:
            f.write(r.content)  #r.content返回二进制内容
            f.close()
            print("文件保存成功")
    else:
        print("文件已存在")
except:
    print("爬取失败")

pip install beautifulsoup4

import requests
r = requests.get("http://python123.io/ws/demo.html")
demo = r.text
form bs4 import BeautifulSoup #从bs4中引入BeautifulSoup类
soup = BeautifulSoup(demo, "html.parser")

from bs4 import BeautifulSoup
soup = BeautifulSoup(demo,"html.parser")

#遍历儿子节点
for child in soup.body.children
    print(child)
#遍历子孙节点
for child in soup.body.descendants
    print(child)

soup = BeautifulSoup(demo,"html.parser")
for parent in soup.a.parents:
    if parent is None:
        print(parent)
    else:
        print(parent.name)
#输出结果
#p
#body
#html
#[document]

#遍历后续节点
for sibling in soup.a.next_siblings
    print(sibling)
#遍历前续节点
for sibling in soup.a.previous_siblings
    print(sibling)

soup = BeautifulSoup(demo,"html.parser")
print(soup.a.prettify())

soup = BeautifulSoup("<p>中文</p>","html.parser")
soup.p.string
#'中文'
print(soup.p.prettify())
#<p>
#  中文
#</p>

<name>...</name>
<name/>
<!--  -->

#有类型的键值对表示信息的标记形式
"key":"value"
"key":["value1","value2"]
"key":{"subkey":"subvalue"}

#无类型的键值对表示信息的标记形式
key : "value"
key : #comment
-value1
-value2
key :
    subkey : subvalue

form bs4 import BeautifulSoup
soup = BeautifulSoup(demo,"html.parser")
for link in soup.find_all('a'):
    print(link.get('href'))

#name:对标签名称的检索字符串
soup.find_all('a')
soup.find_all(['a', 'b'])
soup.find_all(True) #返回soup的所有标签信息
for tag in soup.find_all(True):
    print(tag.name) #html head title body p b p a a
#输出所有b开头的标签，包括b和body    
#引入正则表达式库
import re
for tag in soup.find_all(re.compile('b')):
    print(tag.name) #body b

#attrs:对标签属性值的检索字符串，可标注属性检索
soup.find_all('p', 'course')
soup.find_all(id='link1')
import re 
soup.find_all(id=re.compile('link'))

#recursive:是否对子孙全部检索，默认为True
soup.find_all('p', recursive = False)

#string:<>...</>字符串区域的检索字符串
soup.find_all(string = "Basic Python")
import re
soup.find_all(string = re.compile('Python'))
#简写形式：soup(..) = soup.find_all(..)

import requests
from bs4 import BeautifulSoup
import bs4

def getHTMLText(url):
    try:
        r = requests.get(url, timeout= 30)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text
    except:
        return ""

def fillUnivList(ulist, html):
    soup = BeautifulSoup(html, "html.parser")
    for tr in soup.find('tbody').children:
        if isinstance(tr, bs4.element.Tag):
            tds = tr('td')
            ulist.append([tds[0].string, tds[1].string, tds[3].string])

def printUnivList(ulist, num):
    print("{:^10}\t{:^6}\t{:^10}".format("排名", "学校名称", "分数"))
    for i in range(num):
        u = ulist[i]
        print("{:^10}\t{:^6}\t{:^10}".format(u[0], u[1], u[2]))

def main():
    uinfo = []
    url = 'http://www.zuihaodaxue.cn/zuihaodaxuepaiming2016.html'
    html = getHTMLText(url)
    fillUnivList(uinfo,html)
    printUnivList(uinfo,20) #20 univs
main()

import requests
from bs4 import BeautifulSoup
import bs4

def getHTMLText(url):
    try:
        r = requests.get(url, timeout= 30)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text
    except:
        return ""

def fillUnivList(ulist, html):
    soup = BeautifulSoup(html, "html.parser")
    for tr in soup.find('tbody').children:
        if isinstance(tr, bs4.element.Tag):
            tds = tr('td')
            ulist.append([tds[0].string, tds[1].string, tds[3].string])

def printUnivList(ulist, num):
    tplt = "{0:^10}\t{1:{3}^10}\t{2:^10}"
    print(tplt.format("排名", "学校名称", "分数",chr(12288)))
    for i in range(num):
        u = ulist[i]
        print(tplt.format(u[0], u[1], u[2],chr(12288)))

def main():
    uinfo = []
    url = 'http://www.zuihaodaxue.cn/zuihaodaxuepaiming2016.html'
    html = getHTMLText(url)
    fillUnivList(uinfo,html)
    printUnivList(uinfo,20) #20 univs
main()

import re
match = re.search(r'[1-9]\d{5}','BIT 100081')
if match:
    print(match.group(0))  #'100081'

import re
match = re.match(r'[1-9]\d{5}','BIT 100081')
if match:
    print(match.group(0))  #NULL
match = re.match(r'[1-9]\d{5}','100081 BIT')
if match:
    print(match.group(0))  #'100081'

import re
ls = re.findall(r'[1-9]\d{5}', 'BIT100081 TSU100084')
print(ls) #['100081', '100084']

import re
ls = re.split(r'[1-9]\d{5}', 'BIT100081 TSU100084')
print(ls) #['BIT', ' TSU', '']
ls2 = re.split(r'[1-9]\d{5}', 'BIT100081 TSU100084', maxsplit=1)
print(ls2) #['BIT', ' TSU10084']

import re
for m in re.finditer(r'[1-9]\d{5}', 'BIT100081 TSU100084'):
    if m:
        print(m.group(0)) #100081 100084

import re
rst = re.sub(r'[1-9]\d{5}', ':zipcode', 'BIT 100081,TSU 100084')
print(rst) # 'BIT :zipcode TSU :zipcode'

#函数式用法：一次性操作
rst = re.search(r'[1-9]\d{5}', 'BIT 100081')

#面向对象用法：编译后的多次操作
pat = re.compile(r'[1-9]\d{5}')
rst = pat.search('BIT 100081')

regex = re.compile(r'[1-9]\d{5}')

import re
match = re.search(r'[1-9]\d{5}','BIT 100081')
if match:
    print(match.group(0))  # '100081'
print(type(match)) # <class 're.Match'>

import re
m = re.search(r'[1-9]\d{5}', 'BIT100081 TSU100084')
print(m.string) # BIT100081 TSU100084
print(m.re) # re.compile('[1-9]\\d{5}')
print(m.pos) # 0
print(m.endpos) # 19
print(m.group(0)) # '100081' 返回的是第一次匹配的结果,获取所有使用re.finditer()方法
print(m.start()) # 3
print(m.end()) # 9
print(m.span()) # (3, 9)

import re
match = re.search(r'PY.*N', 'PYANBNCNDN')
print(match.group(0)) # PYANBNCNDN

import re
match = re.search(r'PY.*?N', 'PYANBNCNDN')
print(match.group(0)) # PYAN

import requests
import re

def getHTMLText(url):
    #浏览器请求头中的User-Agent，代表当前请求的用户代理信息（下方有获取方式）
    headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.131 Safari/537.36'}
    try:
        #浏览器请求头中的cookie，包含自己账号的登录信息（下方有获取方式）
        coo = ''
        cookies = {}
        for line in coo.split(';'): #浏览器伪装
            name, value = line.strip().split('=', 1)
            cookies[name] = value
        r = requests.get(url, cookies = cookies, headers=headers, timeout = 30)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text
    except:
        return ""

#解析请求到的页面，提取出相关商品的价格和名称
def parsePage(ilt, html):
    try:
        plt = re.findall(r'\"view_price\"\:\"[\d\.]*\"', html)
        tlt = re.findall(r'\"raw_title\"\:\".*?\"', html)
        for i in range(len(plt)):
            price = eval(plt[i].split(':')[1])
            title = eval(tlt[i].split(':')[1])
            ilt.append([price, title])
    except:
        print("")

def printGoodsList(ilt):
    tplt = "{:4}\t{:8}\t{:16}"
    print(tplt.format("序号", "价格", "商品名称"))
    count = 0
    for g in ilt:
        count = count + 1
        print(tplt.format(count, g[0], g[1]))


def main():
    goods = '书包'
    depth = 2 #爬取深度，2表示爬取两页数据
    start_url = 'https://s.taobao.com/search?q=' + goods
    infoList = []
    for i in range(depth):
        try:
            url = start_url + '&s=' + str(44*i)
            html = getHTMLText(url)
            parsePage(infoList, html)
        except:
            continue
    printGoodsList(infoList)

main()

import requests
from bs4 import BeautifulSoup
import traceback
import re
 
def getHTMLText(url):
    try:
        r = requests.get(url)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text
    except:
        return ""
 
def getStockList(lst, stockURL):
    html = getHTMLText(stockURL)
    soup = BeautifulSoup(html, 'html.parser') 
    a = soup.find_all('a')
    for i in a:
        try:
            href = i.attrs['href']
            lst.append(re.findall(r"[s][hz]\d{6}", href)[0])
        except:
            continue
 
def getStockInfo(lst, stockURL, fpath):
    for stock in lst:
        url = stockURL + stock + ".html"
        html = getHTMLText(url)
        try:
            if html=="":
                continue
            infoDict = {}
            soup = BeautifulSoup(html, 'html.parser')
            stockInfo = soup.find('div',attrs={'class':'stock-bets'})
 
            name = stockInfo.find_all(attrs={'class':'bets-name'})[0]
            infoDict.update({'股票名称': name.text.split()[0]})
             
            keyList = stockInfo.find_all('dt')
            valueList = stockInfo.find_all('dd')
            for i in range(len(keyList)):
                key = keyList[i].text
                val = valueList[i].text
                infoDict[key] = val
             
            with open(fpath, 'a', encoding='utf-8') as f:
                f.write( str(infoDict) + '\n' )
        except:
            traceback.print_exc()
            continue
 
def main():
    stock_list_url = 'https://quote.eastmoney.com/stocklist.html'
    stock_info_url = 'https://gupiao.baidu.com/stock/'
    output_file = 'D:/BaiduStockInfo.txt'
    slist=[]
    getStockList(slist, stock_list_url)
    getStockInfo(slist, stock_info_url, output_file)
 
main()

import requests
from bs4 import BeautifulSoup
import traceback
import re
 
def getHTMLText(url, code="utf-8"):
    try:
        r = requests.get(url)
        r.raise_for_status()
        r.encoding = code
        return r.text
    except:
        return ""
 
def getStockList(lst, stockURL):
    html = getHTMLText(stockURL, "GB2312")
    soup = BeautifulSoup(html, 'html.parser') 
    a = soup.find_all('a')
    for i in a:
        try:
            href = i.attrs['href']
            lst.append(re.findall(r"[s][hz]\d{6}", href)[0])
        except:
            continue
 
def getStockInfo(lst, stockURL, fpath):
    count = 0
    for stock in lst:
        url = stockURL + stock + ".html"
        html = getHTMLText(url)
        try:
            if html=="":
                continue
            infoDict = {}
            soup = BeautifulSoup(html, 'html.parser')
            stockInfo = soup.find('div',attrs={'class':'stock-bets'})
 
            name = stockInfo.find_all(attrs={'class':'bets-name'})[0]
            infoDict.update({'股票名称': name.text.split()[0]})
             
            keyList = stockInfo.find_all('dt')
            valueList = stockInfo.find_all('dd')
            for i in range(len(keyList)):
                key = keyList[i].text
                val = valueList[i].text
                infoDict[key] = val
             
            with open(fpath, 'a', encoding='utf-8') as f:
                f.write( str(infoDict) + '\n' )
                count = count + 1
                print("\r当前进度: {:.2f}%".format(count*100/len(lst)),end="")
        except:
            count = count + 1
            print("\r当前进度: {:.2f}%".format(count*100/len(lst)),end="")
            continue
 
def main():
    stock_list_url = 'https://quote.eastmoney.com/stocklist.html'
    stock_info_url = 'https://gupiao.baidu.com/stock/'
    output_file = 'D:/BaiduStockInfo.txt'
    slist=[]
    getStockList(slist, stock_list_url)
    getStockInfo(slist, stock_info_url, output_file)
 
main()

import requests
import re
import traceback
from bs4 import BeautifulSoup
import bs4


def getHTMLText(url):
    try:
        r = requests.get(url, timeout=30)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text
    except:
        return""


def getStockList(lst, stockListURL):
    html = getHTMLText(stockListURL)
    soup = BeautifulSoup(html, 'html.parser')
    a = soup.find_all('a')
    lst = []
    for i in a:
        try:
            href = i.attrs['href']
            lst.append(re.findall(r"[S][HZ]\d{6}", href)[0])
        except:
            continue
    lst = [item.lower() for item in lst]  # 将爬取信息转换小写
    return lst


def getStockInfo(lst, stockInfoURL, fpath):
    count = 0
    for stock in lst:
        url = stockInfoURL + stock + ".html"
        html = getHTMLText(url)
        try:
            if html == "":
                continue
            infoDict = {}
            soup = BeautifulSoup(html, 'html.parser')
            stockInfo = soup.find('div', attrs={'class': 'stock-bets'})

            if isinstance(stockInfo, bs4.element.Tag):  # 判断类型
                name = stockInfo.find_all(attrs={'class': 'bets-name'})[0]
                infoDict.update({'股票名称': name.text.split('\n')[1].replace(' ','')})
                keylist = stockInfo.find_all('dt')
                valuelist = stockInfo.find_all('dd')
                for i in range(len(keylist)):
                    key = keylist[i].text
                    val = valuelist[i].text
                    infoDict[key] = val

            with open(fpath, 'a', encoding='utf-8') as f:
                f.write(str(infoDict) + '\n')
                count = count + 1
                print("\r当前速度：{:.2f}%".format(count*100/len(lst)), end="")
        except:
            count = count + 1
            print("\r当前速度：{:.2f}%".format(count*100/len(lst)), end="")
            traceback.print_exc()
            continue


def main():
    fpath = 'D://gupiao.txt'
    stock_list_url = 'https://hq.gucheng.com/gpdmylb.html'
    stock_info_url = 'https://gupiao.baidu.com/stock/'
    slist = []
    list = getStockList(slist, stock_list_url)
    getStockInfo(list, stock_info_url, fpath)


main()

pip install scrapy
#验证
scrapy -h

 building 'twisted.test.raiser' extension
    error: Microsoft Visual C++ 14.0 is required. Get it with "Microsoft Visual C++ Build Tools": https://visualstudio.microsoft.com/downloads/

#打开命令提示符-win+r 输入cmd
#进入存放工程的目录
D:\>cd demo
D:\demo>
#建立一个工程，工程名python123demo
D:\demo>scrapy startproject python123demo
New Scrapy project 'python123demo', using template directory 'd:\program files\python\lib\site-packages\scrapy\templates\project', created in:
    D:\demo\python123demo

You can start your first spider with:
    cd python123demo
    scrapy genspider example example.com
D:\demo>

#切换到工程目录
D:\demo>cd python123demo
#产生一个scrapy爬虫
D:\demo\python123demo>scrapy genspider demo python123.io
Created spider 'demo' using template 'basic' in module:
  python123demo.spiders.demo

D:\demo\python123demo>

# -*- coding: utf-8 -*-
import scrapy


class DemoSpider(scrapy.Spider):
    name = 'demo'
#    allowed_domains = ['python123.io']
    start_urls = ['http://python123.io/ws/demo.html']

    def parse(self, response):
        fname = response.url.split('/')[-1]
        with open(fname, 'wb') as f:
            f.write(response.body)
        self.log('Save file %s.' % name)

import scrapy

class DemoSpider(scrapy.Spider):
    name = "demo"
    
    def start_requests(self):
        urls = [
                'http://python123.io/ws/demo.html'
        ]
        for url in urls:
            yield scrapy.Requests(url=url, callback=self.parse)
            
    def parse(self, response):
        fname = response.url.split('/')[-1]
        with open(fname, 'wb') as f:
            f.write(response.body)
        self.log('Saved file %s.' % fname)

#输入运行命令 scrapy crawl
D:\demo\python123demo>scrapy crawl demo

ModuleNotFoundError: No module named 'win32api'

def gen(n):
    for i in range(n):
        yield i**2
#产生小于n的所有2的平方值
for i in gen(5):
    print(i, " ", end="")
#0 1 4 9 16

#普通写法
def square(n):
    ls = [i**2 for i in range(n)]
    return ls
for i in square(5):
    print(i, " ", end="")
#0 1 4 9 16

scrapy startproject BaiduStocks
cd BaiduStocks
scrapy genspider stocks baidu.com
#进一步修改spiders/stocks.py文件

    # -*- coding: utf-8 -*-
import scrapy
import re
    
    
class StocksSpider(scrapy.Spider):
    name = "stocks"
    start_urls = ['https://quote.eastmoney.com/stocklist.html']
    
    def parse(self, response):
        for href in response.css('a::attr(href)').extract():
            try:
                stock = re.findall(r"[s][hz]\d{6}", href)[0]
                url = 'https://gupiao.baidu.com/stock/' + stock + '.html'
                yield scrapy.Request(url, callback=self.parse_stock)
            except:
                continue
    
    def parse_stock(self, response):
        infoDict = {}
        stockInfo = response.css('.stock-bets')
        name = stockInfo.css('.bets-name').extract()[0]
        keyList = stockInfo.css('dt').extract()
        valueList = stockInfo.css('dd').extract()
        for i in range(len(keyList)):
            key = re.findall(r'>.*</dt>', keyList[i])[0][1:-5]
            try:
                val = re.findall(r'\d+\.?.*</dd>', valueList[i])[0][0:-5]
            except:
                val = '--'
            infoDict[key]=val
    
        infoDict.update(
            {'股票名称': re.findall('\s.*\(',name)[0].split()[0] + \
                re.findall('\>.*\<', name)[0][1:-1]})
        yield infoDict

# -*- coding: utf-8 -*-
    
# Define your item pipelines here
#
# Don't forget to add your pipeline to the ITEM_PIPELINES setting
# See: https://doc.scrapy.org/en/latest/topics/item-pipeline.html
    
    
class BaidustocksPipeline(object):
    def process_item(self, item, spider):
        return item
    
class BaidustocksInfoPipeline(object):
    def open_spider(self, spider):
        self.f = open('BaiduStockInfo.txt', 'w')
    
    def close_spider(self, spider):
        self.f.close()
    
    def process_item(self, item, spider):
        try:
            line = str(dict(item)) + '\n'
            self.f.write(line)
        except:
            pass
        return item

# Configure item pipelines
# See https://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
    'BaiduStocks.pipelines.BaidustocksInfoPipeline': 300,
}