Python_Demo_maoyanBoard4

练习对象 :猫眼榜单Top100

import requests 
import re
import json
import time

# from requests.exceptions import RequestException 

def get_one_page(url):
    headers={
        'User-agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.25 Safari/537.36 Core/1.70.3722.400 QQBrowser/10.'
    }
    response = requests.get(url, headers=headers) 
    if response.status_code == 200:
         return response.text
    return None 

def parse_one_page(html):
    p=[]
    p.append('<dd>')
    p.append('.*?board-index.*?>(.*?)</i>')    # 排名信息
    p.append('.*?data-src="(.*?)"')            # 图片地址
    p.append('.*?name.*?a.*?>(.*?)</a>')       #电影名称
    p.append('.*?star.*?>\s*(.*?)\s*</p>')     # 主演
    p.append('.*?releasetime.*?>(.*?)</p>')     #发行时间
    p.append('.*?integer.*?>(.*?)</i>.*?fraction.*?>(.*?)</i>')  #打分
    p.append('.*?</dd>')
    pattern=re.compile(''.join(p),re.S) #re.S使得匹配包括换行符在内的所有字符
   
    items = re.findall(pattern, html)
    for item in items:
        yield {
            'index': item[0],
            'image':re.search('.*/(.*?.jpg)',item[1]).group(1) if len(item[1])>1 else '',
            'title': item[2],
            'actor': item[3].strip()[3:],# strip 默认删除空白符(包括'\n', '\r', '\t', ' ')
            'time': item[4].strip()[5:],
            'score': item[5] + item[6]
        }#yield执行后并没有退出,每次遇到关键字后返回相应结果

def write_to_file(content):
    #通过 JSON 库的 dumps() 方法实现字典的序列化,并指定 ensure ascii 参数为 False,
    # 这样可以保证输出结果是中文形式而不 是 Unicode 编码
    with open('result.txt', 'a', encoding='utf-8') as f:
        f.write(json.dumps(content, ensure_ascii=False) + '\n')#inorder to output the chinese
 

def main(offset):
    url = 'http://maoyan.com/board/4?offset=' + str(offset)
    html=get_one_page(url)

    for item in parse_one_page(html):
        print(item)
        write_to_file(item)

if __name__ == "__main__":
   for i in range(10):
        main(offset=i * 10)
        time.sleep(1)

  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
文件: import scrapy from demo1.items import Demo1Item import urllib from scrapy import log # BOSS直聘网站爬虫职位 class DemoSpider(scrapy.Spider): # 爬虫名, 启动爬虫时需要的参数*必填 name = 'demo' # 爬取域范围,允许爬虫在这个域名下进行爬取(可选) allowed_domains = ['zhipin.com'] # 爬虫需要的url start_urls = ['https://www.zhipin.com/c101280600/h_101280600/?query=测试'] def parse(self, response): node_list = response.xpath("//div[@class='job-primary']") # 用来存储所有的item字段 # items = [] for node in node_list: item = Demo1Item() # extract() 将xpath对象转换为Unicode字符串 href = node.xpath("./div[@class='info-primary']//a/@href").extract() job_title = node.xpath("./div[@class='info-primary']//a/div[@class='job-title']/text()").extract() salary = node.xpath("./div[@class='info-primary']//a/span/text()").extract() working_place = node.xpath("./div[@class='info-primary']/p/text()").extract() company_name = node.xpath("./div[@class='info-company']//a/text()").extract() item['href'] = href[0] item['job_title'] = job_title[0] item['sa 报错: C:\Users\xieqianyun\AppData\Local\Programs\Python\Python36\python.exe "C:\Users\xieqianyun\PyCharm Community Edition 2019.2.5\helpers\pydev\pydevconsole.py" --mode=client --port=55825 import sys; print('Python %s on %s' % (sys.version, sys.platform)) sys.path.extend(['C:\\Users\\xieqianyun\\demo1', 'C:/Users/xieqianyun/demo1']) Python 3.6.5 (v3.6.5:f59c0932b4, Mar 28 2018, 17:00:18) [MSC v.1900 64 bit (AMD64)] Type 'copyright', 'credits' or 'license' for more information IPython 7.10.0 -- An enhanced Interactive Python. Type '?' for help. PyDev console: using IPython 7.10.0 Python 3.6.5 (v3.6.5:f59c0932b4, Mar 28 2018, 17:00:18) [MSC v.1900 64 bit (AMD64)] on win32 runfile('C:/Users/xieqianyun/demo1/demo1/begin.py', wdir='C:/Users/xieqianyun/demo1/demo1') Traceback (most recent call last): File "C:\Users\xieqianyun\AppData\Local\Programs\Python\Python36\lib\site-packages\IPython\core\interactiveshell.py", line 3319, in run_code exec(code_obj, self.user_global_ns, self.user_ns) File "<ipython-input-2-fc5979762143>", line 1, in <module> runfile('C:/Users/xieqianyun/demo1/demo1/begin.py', wdir='C:/Users/xieqianyun/demo1/demo1') File "C:\Users\xieqianyun\PyCharm Community Edition 2019.2.5\helpers\pydev\_pydev_bundle\pydev_umd.py", line 197, in runfile pydev_imports.execfile(filename, global_vars, local_vars) # execute the script File "C:\Users\xieqianyun\PyCharm Community Edition 2019.2.5\helpers\pydev\_pydev_imps\_pydev_execfile.py", line 18, in execfile exec(compile(contents+"\n", file, 'exec'), glob, loc) File "C:/Users/xieqianyun/demo1/demo1/begin.py", line 3, in <module> cmdline.execute('scrapy crawl demo'.split()) File "C:\Users\xieqianyun\AppData\Local\Programs\Python\Python36\lib\site-packages\scrapy\cmdline.py", line 145, in execute cmd.crawler_process = CrawlerProcess(settings) File "C:\Users\xieqianyun\AppData\Local\Programs\Python\Python36\lib\site-packages\scrapy\crawler.py", line 267, in __init__ super(CrawlerProcess, self).__init__(settings) File "C:\Users\xieqianyun\AppData\Local\Programs\Python\Python36\lib\site-packages\scrapy\crawler.py", line 145, in __init__ self.spider_loader = _get_spider_loader(settings) File "C:\Users\xieqianyun\AppData\Local\Programs\Python\Python36\lib\site-packages\scrapy\crawler.py", line 347, in _get_spider_loader return loader_cls.from_settings(settings.frozencopy()) File "C:\Users\xieqianyun\AppData\Local\Programs\Python\Python36\lib\site-packages\scrapy\spiderloader.py", line 61, in from_settings return cls(settings) File "C:\Users\xieqianyun\AppData\Local\Programs\Python\Python36\lib\site-packages\scrapy\spiderloader.py", line 25, in __init__ self._load_all_spiders() File "C:\Users\xieqianyun\AppData\Local\Programs\Python\Python36\lib\site-packages\scrapy\spiderloader.py", line 47, in _load_all_spiders for module in walk_modules(name): File "C:\Users\xieqianyun\AppData\Local\Programs\Python\Python36\lib\site-packages\scrapy\utils\misc.py", line 73, in walk_modules submod = import_module(fullpath) File "C:\Users\xieqianyun\AppData\Local\Programs\Python\Python36\lib\importlib\__init__.py", line 126, in import_module return _bootstrap._gcd_import(name[level:], package, level) File "<frozen importlib._bootstrap>", line 994, in _gcd_import File "<frozen importlib._bootstrap>", line 971, in _find_and_load File "<frozen importlib._bootstrap>", line 955, in _find_and_load_unlocked File "<frozen importlib._bootstrap>", line 665, in _load_unlocked File "<frozen importlib._bootstrap_external>", line 678, in exec_module File "<frozen importlib._bootstrap>", line 219, in _call_with_frames_removed File "C:\Users\xieqianyun\demo1\demo1\spiders\demo.py", line 4, in <module> from scrapy import log ImportError: cannot import name 'log'
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值