Python爬虫实列

Python爬虫实列(格式为参考)

 

复制代码
import requests
url = "https://item.jd.com/2967929.html"
try:
    r = requests.get(url)
    r.raise_for_status()
    r.encoding = r.apparent_encoding
    print(r.text[:1000])
except:
    print("爬取失败")
实例1：京东商品页面的爬取
复制代码
复制代码
import requests
url = "https://www.amazon.cn/gp/product/B01M8L5Z3Y"
try:
    kv = {'user-agent':'Mozilla/5.0'}
    r = requests.get(url,headers=kv)
    r.raise_for_status()
    r.encoding = r.apparent_encoding
    print(r.text[1000:2000])
except:
    print("爬取失败")
实例2：亚马逊商品页面的爬取
复制代码
复制代码
import requests
keyword = "Python"
try:
    kv = {'wd':keyword}
    r = requests.get("http://www.baidu.com/s",params = kv)
    print(r.request.url)
    r.raise_for_status()
    print(len(r.text))
except:
    print("爬取失败")
实例3：百度搜索关键词提交
复制代码
复制代码
import requests
import os
url = "http://image.nationalgeographic.com.cn/2017/0211/20170211061910157.jpg"
root = "D://pics//"
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)
            f.close()
            print("文件保存成功")
    else:
        print("文件已存在")
except:
    print("爬取失败")
实例4：网络图片的爬取和存储
复制代码

 

复制代码
import requests
url = "http://m.ip138.com/ip.asp?ip="
try:
    r = requests.get(url+'202.204.80.112')
    r.raise_for_status()
    r.encoding = r.apparent_encoding
    print(r.text[-500:])
except:
    print("爬取失败")
实例5：IP地址归属地的自动查询
复制代码
复制代码
#CrawUnivRankingA.py
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","总分"))
    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 = 'https://www.zuihaodaxue.cn/zuihaodaxuepaiming2016.html'
    html = getHTMLText(url)
    fillUnivList(uinfo, html)
    printUnivList(uinfo, 20) # 20 univs
main()
bs4实例6：“中国大学排名定向爬虫”实例代码A
复制代码
复制代码
#CrawUnivRankingB.py
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","总分",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 = 'https://www.zuihaodaxue.cn/zuihaodaxuepaiming2016.html'
    html = getHTMLText(url)
    fillUnivList(uinfo, html)
    printUnivList(uinfo, 20) # 20 univs
main()
bs4库实例6：“中国大学排名定向爬虫”实例代码B(优化)
复制代码
复制代码
#CrowTaobaoPrice.py
import requests
import re

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 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 = 3
    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()
Re实例7："淘宝商品信息定向爬虫"实例代码
复制代码
复制代码
#CrawBaiduStocksA.py
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()
Re实例8：“股票数据定向爬虫”实例代码A
复制代码
Re实例8：“股票数据定向爬虫”实例代码B(优化)
复制代码
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
“Scrapy爬虫”1：stocks.py文件源代码
复制代码
复制代码
# -*- 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
“Scrapy爬虫”2：pipelines.py文件源代码
复制代码
复制代码
# Configure item pipelines
# See https://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
    'BaiduStocks.pipelines.BaidustocksInfoPipeline': 300,
}
“Scrapy爬虫”3：settings.py文件中被修改的区域
复制代码

 

 

 

posted @   魔九念  阅读(63)  评论(0)  编辑  收藏  举报
相关博文：
· Scrapy爬虫框架
· BeautifulSoup库(1)
· Python 爬虫初探
· python 爬虫
· python爬虫
阅读排行：
· 无需6万激活码！GitHub神秘组织3小时极速复刻Manus，手把手教你使用OpenManus搭建本
· Manus爆火，是硬核还是营销？
· 终于写完轮子一部分：tcp代理 了，记录一下
· 别再用vector＜bool＞了！Google高级工程师：这可能是STL最大的设计失误
· 单元测试从入门到精通
点击右上角即可分享
微信分享提示