Python爬虫（urllib.request和BeautifulSoup）

学习urllib.request和beautifulsoup，并从dribbble和behance上爬取了一些图片，记录一下

一、urllib.request

1. url的构造

构造请求的url遇到的主要问题是如何翻页的问题，dribbble网站是下拉到底自动加载下一页，地址栏的url没有变化，如下：

但是通过检查，我们可以发现request url里关于page的字段，如下：

因此，我们构造如下的url：

for i in range(25):  # 最多25页
    url = 'https://dribbble.com/shots?page=' + str(i + 1) + '&per_page=24'

2. header的构造

不同网页需要的header的内容不一样，参照检查里request header来构造。例如dribbble需要Referer，即从哪一个页面跳转到这个当前页面的，一般填写网站相关页面网址就可以。

headers = {"Accept": "text/html,application/xhtml+xml,application/xml;",
           "Referer": "https://dribbble.com/",
           "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3493.3 Safari/537.36"}

3. urllib.request获取页面内容

用url和header实例化一个urllib.request.Request(url, headers)，然后url.request.urlopen()访问网页获取数据，使用read()函数即可读取页面内容。

def open_url(url):
    # 将Request类实例化并传入url为初始值，然后赋值给req
    headers = {"Accept": "text/html,application/xhtml+xml,application/xml;",
               "Referer": "https://dribbble.com/",
               "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3493.3 Safari/537.36"}
    req = urllib.request.Request(url, headers=headers)
    # 访问url，并将页面的二进制数据赋值给page
    res = urllib.request.urlopen(req)
    # 将page中的内容转换为utf-8编码
    html = res.read().decode('utf-8')
    return html

这里需要注意的是，有的页面返回的数据是“text/html; charset=utf-8”格式，直接decode('utf-8')编码即可，而有的页面返回的是“application/json; charset=utf-8”格式数据，例如behance：

此时就需要json.loads()来获取数据，得到的是列表，用操作列表的方式拿到html数据：

 html = json.loads(res.read())
 return html['html']

二、BeautifulSoup

BeautifulSoup将复杂的html文档转换为树形结构，每一个节点都是一个对象。

1.创建对象

soup = BeautifulSoup(open_url(url), 'html.parser')

‘html.parser’是解析器，BeautifulSoup支持Python标准库中的HTML解析器,还支持一些第三方的解析器，如果我们不安装它，则 Python 会使用 Python默认的解析器，lxml 解析器更加强大，速度更快，推荐安装，常见解析器：

2. 标签选择器

标签选择筛选功能弱但是速度快，通过这种“soup.标签名” 我们就可以获得这个标签的内容，但通过这种方式获取标签，如果文档中有多个这样的标签，返回的结果是第一个标签的内容

# 获取p标签
soup.p

# 获取p标签的属性的两种方法
soup.p.attrs['name']
soup.p['name']

# 获取第一个p标签的内容
soup.p.string

# 获取p标签下所有子标签，返回一个列表
soup.p.contents

# 获取p标签下所有子标签，返回一个迭代器
for i,child in enumerate(soup.p.children):
    print(i,child)

# 获取父节点的信息
soup.a.parent

# 获取祖先节点
list(enumerate(soup.a.parents))

# 获取后面的兄弟节点
soup.a.next_siblings

# 获取前面的兄弟节点
soup.a.previous_siblings

# 获取下一个兄弟标签
soup.a.next_sibling

# 获取上一个兄弟标签
souo.a.previous_sinbling

3. 标准选择器

find_all(name,attrs,recursive,text,**kwargs)可以根据标签名，属性，内容查找文档，返回一个迭代器，例如：

# 获取所有class为js-project-module--picture的所有img标签，并选择每个标签的src构成一个列表
image.src = [item['src'] for item in soup.find_all('img', {"class": "js-project-module--picture"})]

# .string获取div的内容，strip()去除前后空格
desc = soup.find_all('div', {"class": "js-basic-info-description"})
if desc:
    image.desc = [item.string.strip() for item in desc]

find(name,attrs,recursive,text,**kwargs)，返回匹配的第一个元素

其他一些类似的用法：
find_parents()返回所有祖先节点，find_parent()返回直接父节点
find_next_siblings()返回后面所有兄弟节点，find_next_sibling()返回后面第一个兄弟节点
find_previous_siblings()返回前面所有兄弟节点，find_previous_sibling()返回前面第一个兄弟节点
find_all_next()返回节点后所有符合条件的节点, find_next()返回第一个符合条件的节点
find_all_previous()返回节点后所有符合条件的节点, find_previous()返回第一个符合条件的节点

三、从dribbble爬取图片完整代码

1.批量获取图片页面链接

# -*- coding: utf-8 -*-

import random
import urllib.request
from bs4 import BeautifulSoup
import os
import time


def open_url(url):
    headers = {"Accept": "text/html,application/xhtml+xml,application/xml;",
               "Referer": "https://dribbble.com/",
               "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3493.3 Safari/537.36"}
    req = urllib.request.Request(url, headers=headers)
    res = urllib.request.urlopen(req)
    html = res.read().decode('utf-8')
    return html


# 打开/创建“dribbble_list.txt”文件，O_CREAT：不存在即创建、O_WRONLY:只写、O_APPEND:追加
fd = os.open('dribbble_list.txt', os.O_CREAT | os.O_WRONLY | os.O_APPEND)
for i in range(25):
    url = 'https://dribbble.com/shots?page=' + str(i + 1) + '&per_page=24'
    soup = BeautifulSoup(open_url(url), 'html.parser')
    srcs = soup.find_all('a', {"class": "dribbble-link"})
    src_list = [src['href'] for src in srcs]
    for src in src_list:
        os.write(fd, bytes(src, 'UTF-8'))
        os.write(fd, bytes('\n', 'UTF-8'))
    time.sleep(random.random()*5)

2. 获取图片和信息

import os
import random
import urllib.request
import re
import time
from bs4 import BeautifulSoup


class Image:
    title = ''
    src = ''
    desc = []
    tags = []
    colors = []
    view = []
    like = []
    save = []


def open_url(url):
    headers = {"Accept": "text/html,application/xhtml+xml,application/xml;",
               "Referer": "https://dribbble.com/shots",
               "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3493.3 Safari/537.36"}
    try:
        req = urllib.request.Request(url, headers=headers)
        res = urllib.request.urlopen(req)
        html = res.read().decode('utf-8')
    except:
        return None
    return html


def get_number(x):
    return int(re.sub('\D', "", x))


def get_img_info(html):
    # 实例化一张图
    image = Image()
    soup = BeautifulSoup(html, 'html.parser')
    # 标题
    image.title = soup.find('div', {"class": "slat-header"}).find('h1').string.strip()
    # 地址
    image.src = soup.find('div', {"class": "detail-shot"}).find('img')['src']
    # 描述
    desc = soup.find('div', {"class": "shot-desc"})
    if desc:
        image.desc = [item.string.strip() for item in desc.find_all(text=True)]
    # 标签
    image.tags = [item.string for item in soup.find_all('a', {"rel": "tag"})]
    # 颜色
    image.colors = [item.string for item in soup.find_all('a', {"style": re.compile('background-color.*')})]
    # 浏览量
    view = soup.find('div', {"class": "shot-views"})
    if view:
        image.view = [str(get_number(item)) for item in view.stripped_strings]
    # 喜欢
    like = soup.find('div', {"class": "shot-likes"})
    if like:
        image.like = [str(get_number(item)) for item in like.stripped_strings]
    # 收藏
    save = soup.find('div', {"class": "shot-saves"})
    if save:
        image.save = [str(get_number(item)) for item in save.stripped_strings]
    return image


def save_text(root_path, img, num):
    text = {
        'src': img.src,
        'desc': ';'.join(img.desc),
        'tags': ';'.join(img.tags),
        'colors': ';'.join(img.colors),
        'score': ';'.join([img.title, ''.join(img.view), ''.join(img.like), ''.join(img.save)])
    }
    text_list = ['src', 'desc', 'tags', 'colors', 'score']
    for item in text_list:
        save_path = root_path + item + '.txt'
        fd = os.open(save_path, os.O_CREAT | os.O_WRONLY | os.O_APPEND)
        write_str = str(num).zfill(3) + ' ' + text[item] + '\n'
        os.write(fd, bytes(write_str, 'UTF-8'))
        os.close(fd)


def read_dribbble_data(data_folder):
    import pandas as pd
    import os
    columns = ['url']
    df = pd.read_csv(os.path.join(data_folder, 'dribbble_list.txt'), names=columns)
    return df


def to_url(img_url):
    return 'https://dribbble.com{img_url}'.format(img_url=img_url)


if __name__ == '__main__':
    data_folder = './'
    df = read_dribbble_data(data_folder)
    urls = map(to_url, df['url'].values)
    for i, url in enumerate(urls):
        print(url)
        # 获取并解析网页
        html = open_url(url)
        if html:
            image = get_img_info(open_url(url))
            # 获取并保存图片
            # save_path_img = 'img/' + image.title + '.jpg'
            save_path_img = 'img/' + str(i+556).zfill(3) + '.jpg'
            urllib.request.urlretrieve(image.src, save_path_img)
            # 保存“标题 地址 描述 标签 颜色 浏览量 喜欢 收藏”
            save_path_text_root = 'dribbble_text/'
            save_text(save_path_text_root, img=image, num=i+556)
            time.sleep(random.random()*5)

四、从behance爬取图片完整代码

1. 批量获取图片页面链接

# -*- coding: utf-8 -*-

import random
import urllib.request
from bs4 import BeautifulSoup
import os
import time
import json


def open_url(url):
    headers = {"Accept": "*/*",
               "Referer": "https://www.behance.net/search?field=48&content=projects&sort=appreciations&time=week",
               "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3493.3 Safari/537.36",
               "Host": "www.behance.net",
               "Connection": "keep-alive",
               "X-BCP": "523bc8eb-c6a4-4eeb-a73d-0bf9ec1c06d9",
               "X-NewRelic-ID": "VgUFVldbGwACXFJSBAUF",
               "X-Requested-With": "XMLHttpRequest"}
    req = urllib.request.Request(url, headers=headers)
    res = urllib.request.urlopen(req)
    html = json.loads(res.read())
    return html['html']


fd = os.open('behance_list.txt', os.O_CREAT | os.O_WRONLY | os.O_APPEND)
for i in range(200):
    url = 'https://www.behance.net/search?ordinal=' + str((i+100) * 48) + '&per_page=48&field=48&content=projects&sort=appreciations&time=week&location_id=&timestamp=0&mature=0'
    print(url)
    soup = BeautifulSoup(open_url(url), 'html.parser')
    srcs = soup.find_all('a', {"class": "js-project-cover-image-link"})
    src_list = [src['href'] for src in srcs]
    for src in src_list:
        os.write(fd, bytes(src, 'UTF-8'))
        os.write(fd, bytes('\n', 'UTF-8'))
    time.sleep(random.random()*5)
os.close(fd)

2. 获取图片和信息

# -*- coding: utf-8 -*-

import os
import random
import urllib.request
import re
import time
from bs4 import BeautifulSoup


class Image:
    title = ''
    src = []
    desc = []
    tags = []
    data = []


def open_url(url):
    headers = {"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
               "Referer": "https://www.behance.net/gallery/70675447/YELLOWSTONE",
               "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3493.3 Safari/537.36",
               "Host": "www.behance.net",
               "Connection": "keep-alive",
               "Upgrade-Insecure-Requests": 1,
               "Cookie": "巴啦啦小魔仙全身变"
               }
    try:
        req = urllib.request.Request(url, headers=headers)
        res = urllib.request.urlopen(req)
        html = res.read().decode('utf-8')
    except:
        return None
    return html


def get_number(x):
    return int(re.sub('\D', "", x))


def get_img_info(html):
    # 实例化一张图
    image = Image()
    soup = BeautifulSoup(html, 'html.parser')
    # 地址
    image.src = [item['src'] for item in soup.find_all('img', {"class": "js-project-module--picture"})]
    # 标题
    image.title = soup.find('div', {"class": "js-project-title"}).string.strip()
    # 描述
    desc = soup.find_all('div', {"class": "js-basic-info-description"})
    if desc:
        image.desc = [item.string.strip() for item in desc]
    # 标签
    tags = soup.find_all('a', {"class": "object-tag"})
    if tags:
        image.tags = [item.string.strip() for item in tags]
    # 浏览 点赞 评论
    data = soup.find_all('div', {"class": "project-stat"})
    if data:
        image.data = [item.string.strip() for item in data][:2]
    return image


def save_text(root_path, img, num):
    text = {
        'title': image.title.replace(' ', '_'),
        'score': ' '.join(img.data),
        'desc': ';' + (';'.join(img.desc)).replace('\n', ';'),
        'tags': ';' + ';'.join(img.tags),
        'src': ';' + ';'.join(img.src)
    }
    text_list = ['title', 'score', 'desc', 'tags', 'src']
    for item in text_list:
        save_path = root_path + item + '.txt'
        fd = os.open(save_path, os.O_CREAT | os.O_WRONLY | os.O_APPEND)
        write_str = str(num).zfill(5) + ' ' + text[item] + '\n'
        os.write(fd, bytes(write_str, 'UTF-8'))
        os.close(fd)


def read_dribbble_data(data_folder):
    import pandas as pd
    import os
    columns = ['url']
    df = pd.read_csv(os.path.join(data_folder, 'behance_list.txt'), names=columns)
    return df


if __name__ == '__main__':
    data_folder = './'
    urls = read_dribbble_data(data_folder)['url'].values
    for i, url in enumerate(urls):
        print(url)
        # 获取并解析网页
        html = open_url(url)
        if html:
            image = get_img_info(open_url(url))
            # 获取并保存图片
            for j, src in enumerate(image.src):
                save_path_img = './behance_img/' + str(i).zfill(5) + '_' + str(j).zfill(3) + src[-4:]
                urllib.request.urlretrieve(src, save_path_img)
                time.sleep(random.random()*3)
            # 保存“标题 浏览量 喜欢 收藏 描述 标签 ”
            save_path_text_root = './behance_text/'
            save_text(save_path_text_root, img=image, num=i)
            time.sleep(random.random()*5)