python简单爬虫

# 1、简单爬虫,不做任何处理
import requests　　# 导入用来爬虫的包
URL="https://www.baidu.com"　　# 请求地址
req = requests.get(URL)　　# 开始请求
print(req.text)　　# 把请求的数据打印

 2、简单处理，抓取自己想要的东西
import requests
from bs4 import BeautifulSoup

URL = "https://www.biqiuge.com/paihangbang/"
req = requests.get(url=URL)
req_txt = req.text
bs = BeautifulSoup(req_txt, "html.parser")
for i in bs.find_all("div", class_="block bd"):
    print(i.text)

# 3、携带请求头
# 部分网站直接访问不通，需要加上请求头，如：知乎:
import requests

# 请求头字典
headers = {
    ‘user-agent‘: ‘Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.146 Safari/537.36‘
}
# 在get请求内，添加user-agent
response = requests.get(url=‘https://www.zhihu.com/explore‘, headers=headers)
print(response.status_code)  # 200
print(response.text)
with open(‘zhihu.html‘, ‘w‘, encoding=‘utf-8‘) as f:  #创建一个zhihu.html文件
    f.write(response.text)

# 简单的爬取图片，只爬取一张
import requests

# 这是一个图片的url
url = ‘https://timgsa.baidu.com/timg?image&quality=80&size=b9999_10000&sec=1596560238680&di=0b9fd395e131fc1df9d992b1c33f3c70&imgtype=0&src=http%3A%2F%2Ft7.baidu.com%2Fit%2Fu%3D3616242789%2C1098670747%26fm%3D79%26app%3D86%26f%3DJPEG%3Fw%3D900%26h%3D1350‘
response = requests.get(url)
# 获取的文本实际上是图片的二进制文本
img = response.content
# 将他拷贝到本地文件 w 写  b 二进制  wb代表写入二进制文本
with open(‘./a.jpg‘, ‘wb‘) as f:
    f.write(img)

import re
import requests


def download(html):
    # 通过正则匹配
    pic_url = re.findall(‘"objURL":"(.*?)",‘, html, re.S)
    i = 1
    for key in pic_url:
        print("开始下载图片：" + key + "\r\n")
        try:
            pic = requests.get(key, timeout=10)
        except requests.exceptions.ConnectionError:
            print(‘图片无法下载‘)
            continue
        # 保存图片路径
        dir = ‘保存路径‘ + str(i) + ‘.jpg‘
        fp = open(dir, ‘wb‘)
        fp.write(pic.content)
        fp.close()
        i += 1


def main():
    url = "https://image.baidu.com/search/index?tn=baiduimage&ipn=r&ct=201326592&cl=2&lm=-1&st=-1&fm=result&fr=&sf=1&fmq=1596723403215_R&pv=&ic=0&nc=1&z=&hd=&latest=&copyright=&se=1&showtab=0&fb=0&width=&height=&face=0&istype=2&ie=utf-8&sid=&word=%E5%88%98%E4%BA%A6%E8%8F%B2"
    result = requests.get(url)
    download(result.text)


if __name__ == ‘__main__‘:
    main()

import json
import os
import requests
from bs4 import BeautifulSoup

# 请求头
headers = {
    ‘User-Agent‘: ‘Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/77.0.3865.120 Safari/537.36‘
}
# 请求URL
url = "https://movie.douban.com/ithil_j/activity/widget/987"
req = requests.get(url=url, headers=headers)

# 进行Unicode解码
req_txt = req.text.encode(‘utf8‘).decode(‘unicode_escape‘)

# 把接口返回的结果转换为dict
dict_req = json.loads(req_txt)

# 取出subjes
sub_list = dict_req[‘res‘][‘subjects‘]

# 把subjes转换为dict
dd = {i: v for i, v in enumerate(sub_list)}

for j in dd.keys():
    title = dd[j][‘title‘]
    cover = dd[j][‘cover‘]
    rating = dd[j][‘rating‘]
    url_sub = dd[j][‘url‘]
    req_cover = requests.get(url=cover)
    req_rating = requests.get(url=url_sub, headers=headers)

    # 获取的文本实际上是图片的二进制文本
    img = req_cover.content

    # 创建文件夹
    b = os.getcwd()  # 返回当前进程的工作目录
    path = b + "/movie/" + str(rating) + title
    ispath = os.path.exists(path)  # 判断一个目录是否存在
    if ispath == False:
        os.makedirs(path)  # 创建目录
        os.makedirs(path + "/" + title + "演员")
        img_path = os.path.exists(path + "/" + title + ‘.jpg‘)
        # 将他拷贝到本地文件 w 写  b 二进制  wb代表写入二进制文本
        if img_path == False:
            with open(path + "/" + title + ‘.jpg‘, ‘wb‘) as f:
                f.write(img)

    # 找到简介的页面标签
    bf = BeautifulSoup(req_rating.text, "html.parser")
    text2 = bf.find(‘span‘, property=‘v:summary‘)

    # 把简介写入TXT文档
    file_handle = open(path + "/" + title + ‘-简介.txt‘, mode=‘w‘, encoding=‘utf-8‘)
    file_handle.write(text2.text)

    movie_title = bf.findAll(‘li‘, class_=‘celebrity‘)
    for m in movie_title:
        # movie_img = bf.findAll(‘div‘, class_=‘avatar‘)
        div_txt = m.findChild(‘div‘)
        url_movie = div_txt[‘style‘]
        url_mov = url_movie[22:-1]

        mov_img = requests.get(url_mov).content
        a_txt = m.findChild(‘a‘)
        name = a_txt[‘title‘]
        with open(path + "/" + title + "演员/" + name + ‘.jpg‘, ‘wb‘) as f:
            f.write(mov_img)