使用python获取nature系列期刊封面高清图片

nature作为科学界最顶级的期刊之一，其期刊封面审美也一直很在线，兼具科学和艺术的美感

为了方便快速获取nature系列封面，这里用python requests模块进行自动化请求并使用BeautifulSoup模块进行html解析

import requests
from bs4 import BeautifulSoup
import os

path = 'C:\Users\User\Desktop\nature 封面\nature 正刊'
# path = os.getcwd()
if not os.path.exists(path):
    os.makedirs(path)
    print("新建文件夹 nature正刊")

# 在这里改变要下载哪期的封面
# 注意下载是从后往前下载的，所以start_volume应大于等于end_volume
start_volume = 501
end_volume = 500
# nature_url = 'https://www.nature.com/ng/volumes/' # nature genetics
nature_url='https://www.nature.com/nature/volumes/'  # nature 正刊
kv = {
    'User-Agent':
    'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.132 Safari/537.36'
}
while start_volume >= end_volume:
    try:
        volume_url = nature_url + str(start_volume)
        volume_response = requests.get(url=volume_url, headers=kv, timeout=120)
    except Exception:
        print(str(start_volume) + "请求异常")
        with open(path + "\异常.txt", 'at') as txt:
            txt.write(str(start_volume) + "请求异常\n")
        continue
    volume_response.encoding = 'utf-8'
    volume_soup = BeautifulSoup(volume_response.text, 'html.parser')
    ul_tag = volume_soup.find_all(
        'ul',
        class_=
        'ma0 clean-list grid-auto-fill grid-auto-fill-w220 very-small-column medium-row-gap'
    )
    img_list = ul_tag[0].find_all("img")
    issue_number = 0
    for img_tag in img_list:
        issue_number += 1
        filename = path + '\' + str(start_volume) + '_' + str(
            issue_number) + '.png'
        if os.path.exists(filename):
            print(filename + "已经存在")
            continue
        print("Loading...........................")
        img_url = 'https:' + img_tag.get("src").replace("w200", "w1000")
        try:
            img_response = requests.get(img_url, timeout=240, headers=kv)
        except Exception:
            print(start_volume, issue_number, '???????????异常????????')
            with open(path + "\异常.txt", 'at') as txt:
                txt.write(
                    str(start_volume) + '_' + str(issue_number) + "请求异常\n")
            continue
        with open(filename, 'wb') as imgfile:
            imgfile.write(img_response.content)
        print("成功下载图片：" + str(start_volume) + '_' + str(issue_number))
    start_volume -= 1

运行结果：

以上部分代码可以自动下载nature和nature genetics的封面，这两个期刊的网站结构跟其他子刊略有不同，其他子刊可以用以下代码来进行爬虫：

import requests
from bs4 import BeautifulSoup
import os


other_journals = {
    'nature biomedical engineering': 'natbiomedeng',
    'nature methods': 'nmeth',
    'nature astronomy': 'natastron',
    'nature medicine': 'nm',
    'nature protocols': 'nprot',
    'nature microbiology': 'nmicrobiol',
    'nature cell biology': 'ncb',
    'nature nanotechnology': 'nnano',
    'nature immunology': 'ni',
    'nature energy': 'nenergy',
    'nature materials': 'nmat',
    'nature cancer': 'natcancer',
    'nature neuroscience': 'neuro',
    'nature machine intelligence': 'natmachintell',
    'nature metabolism': 'natmetab',
    'nature food': 'natfood',
    'nature ecology & evolution': "natecolevol",
    "nature stuctural & molecular biology":"nsmb",
    "nature physics":"nphys",
    "nature human behavior":"nathumbehav",
    "nature chemical biology":"nchembio"
}


nature_journal = {
    # 要下载的期刊放这里
    'nature plants': 'nplants',
    'nature biotechnology': 'nbt'
}
folder_Name = "nature 封面"
kv = {
    'User-Agent':
    'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.132 Safari/537.36'
}


def makefile(path):
    folder = os.path.exists(path)
    if not folder:
        os.makedirs(path)
        print("Make file -- " + path + " -- successfully!")
    else:
        raise AssertionError



################################################################
def getCover(url, journal, year, filepath, startyear=2022, endyear=2022):
    # 注意endyear是比startyear小的,因为是从endyear开始由后往前来下载的
    if not (endyear <= year <= startyear):
        return
    try:
        issue_response = requests.get("https://www.nature.com" + url,
                                      timeout=120,
                                      headers=kv)
    except Exception:
        print(journal + "  " + str(year) + "  Error")
        return
    issue_response.encoding = 'gbk'
    if 'Page not found' in issue_response.text:
        print(journal + "  Page not found")
        return
    issue_soup = BeautifulSoup(issue_response.text, 'html.parser')
    cover_image = issue_soup.find_all("img", class_='image-constraint pt10')
    for image in cover_image:
        image_url = image.get("src")
        print("Start loading img.............................")
        image_url = image_url.replace("w200", "w1000")
        if (image_url[-2] == '/'):
            month = "0" + image_url[-1]
        else:
            month = image_url[-2:]
        image_name = nature_journal[journal] + "_" + str(
            year) + "_" + month + ".png"
        if os.path.exists(filepath + journal + "\" + image_name):
            print(image_url + " 已经存在")
            continue
        print(image_url)
        try:
            image_response = requests.get("http:" + image_url,
                                          timeout=240,
                                          headers=kv)
        except Exception:
            print("获取图片异常:" + image_name)
            continue
        with open(filepath + journal + "\" + image_name,
                  'wb') as downloaded_img:
            downloaded_img.write(image_response.content)


def main():
    try:
        path = os.getcwd() + '\'
        makefile(path + folder_Name)
    except Exception:
        print("文件夹 --nature 封面-- 已经存在")
    path = path + folder_Name + "\"
    for journal in nature_journal:
        try:
            makefile(path + journal)
        except AssertionError:
            print("File -- " + path + " -- has already exist!")
        try:
            volume_response = requests.get("https://www.nature.com/" +
                                           nature_journal[journal] +
                                           "/volumes",
                                           timeout=120,
                                           headers=kv)
        except Exception:
            print(journal + " 异常")
            continue
        volume_response.encoding = 'gbk'
        volume_soup = BeautifulSoup(volume_response.text, 'html.parser')
        volume_list = volume_soup.find_all(
            'ul',
            class_=
            'clean-list ma0 clean-list grid-auto-fill medium-row-gap background-white'
        )
        
        number_of_volume = 0
        for volume_child in volume_list[0].children:
            if volume_child == '\n':
                continue
            issue_url = volume_child.find_all("a")[0].get("href")
            print(issue_url)
            print(2020 - number_of_volume)
            getCover(issue_url,
                     journal,
                     year=(2020 - number_of_volume),
                     filepath=path,
                     startyear=2022, 
                     endyear=2022)
            number_of_volume += 1


if __name__ == "__main__":
    main()
    print("Finish Everything!")

运行结果：