python爬虫小案例

1、豆瓣网美剧电影评分爬取

from parse import  parse_url
import json
class DoubanSpider:
    def __init__(self):
        self.temp_url = "https://movie.douban.com/j/search_subjects?type=movie&tag=欧美&sort=recommend&page_limit=20&page_start={}"

    def get_content_list(self,html_str):
        dict_data = json.loads(html_str)
        content_list = dict_data["subjects"]
        print(type(content_list))     #content_lsit是一个列表形式的，里面存的是一序列字典类型的值
        return  content_list

    def save_content_list(self,content_list):
        with open("douban.json","a",encoding="utf-8") as f:
            for content in content_list:
                f.write(json.dumps(content,ensure_ascii=False))   #将python字典类型的数据转换成json类型，便于进行文件存储
                f.write("\n")
        print("保存成功")

    def run(self):   #实现主要逻辑
        num = 0
        total = 200
        while num<total+20       :
            #1.start_url
            url = self.temp_url.format(num)
            #2.发送请求，获取响应、
            html_str = parse_url(url)
            #3.提取数据
            content_list = self.get_content_list(html_str)
            #4.保存
            self.save_content_list(content_list)
            #5.构造下一页的url地址，循环2-5步
            num +=20

if __name__ == '__main__':
    douban = DoubanSpider()
    douban.run()

2、糗事百科段子爬取

from lxml import etree
import requests
import json

class QiubaiSpidera():
    def __init__(self):
        self.url_temp = "https://www.qiushibaike.com/text/page/{}/"
        self.header = {"User-Agent":"Mozilla/5.0(Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko)Chrome/70.0.3538.110 Safari/537.36"}

    def get_url_list(self):
        url_list = [self.url_temp.format(i) for i in range(1,14)]
        return url_list

    def parse_url(self,url):
        response = requests.get(url,headers=self.header)
        return  response.content.decode()

    def get_content_list(self,html_str):
        html = etree.HTML(html_str)
        #1、分组
        div_list = html.xpath("//div[@class='col1 old-style-col1']/div")
        content_list = []
        for div in div_list:
            item= {}
            item["auther_name"] = div.xpath(".//h2//text()")[0].strip() if len(div.xpath(".//h2//text()"))>0 else None
            item["content"] = div.xpath(".//span//text()")[0].strip()
            item["stats_vote"] = div.xpath(".//span[@class='stats-vote']/i/text()")
            item["stats_vote"] =  item["stats_vote"][0] if len(item["stats_vote"] )>0 else None
            content_list.append(item)
        return content_list

    def save_content_list(self,content_list):   #数据保存
        with open("qiubai.txt","a",encoding="utf-8") as f:
            for content in content_list:
                f.write(json.dumps(content,ensure_ascii=False))
                f.write("\n")
        print("保存成功")

    def run(self):   #实现主要逻辑
        #1、根据url规律构造url
        url_list = self.get_url_list()
        #2、发送请求，获取数据
        for url in url_list:
            html_str = self.parse_url(url)
            #3、提取数据
            content_list = self.get_content_list(html_str)
            #4、保存
            self.save_content_list(content_list)

if __name__ == '__main__':
    qiubai = QiubaiSpidera()
    qiubai.run()