python之爬虫篇

1，POST请求

# -*- coding: UTF-8 -*-import requestsformdata = { 'type': 'AUTO', 'i': 'i love python', 'doctype': 'json', 'xmlVersion': '1.8', 'keyfrom': 'fanyi.web', 'ue': 'UTF-8', 'action': 'FY_BY_ENTER', 'typoResult': 'true'}url = 'http://fanyi.youdao.com/translate?smartresult=dict&smartresult=rule&smartresult=ugc&sessionFrom=null'headers = { 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.103 Safari/537.36'}response = requests.post(url, data=formdata, headers=headers)print response.text

2，下载图片

# -*- coding: UTF-8 -*-import requestsimport reimport randomimport stringdef write_file(file, content):    with open(file, 'wb') as f:        f.write(content)        print 'done'def down_picture(file, url, headers):    response = requests.get(url, headers)    if response.status_code == 200:        write_file(file, response.content)def for_get_picture(url):    headers = {}    response = requests.get(url, headers = headers)    print 'code: %d ' % (response.status_code)    patterm = re.compile('src=(.*.jpg)')    if response.status_code == 200:        content = response.content        list = patterm.findall(content)        str1 = str(list)        image_list = str1.split('\'')        for i in image_list:            if i.endswith('jpg'):                jpg_url = 'https://pic.netbian.com' + i                print jpg_url                radom = ''.join(random.sample(string.ascii_letters + string.digits, 8))                #print salt                file = 'D:\\python\\download\\' + radom + '.jpg'                print file                down_picture(file, jpg_url, '')                #write_file('D:\\python\\download\\1.jpg', response.content)url = 'https://pic.netbian.com/4kmeinv/index_3.html'for i in range(4,175,1):    url1 = 'https://pic.netbian.com/4kmeinv/index_%s.html' % (i)    #print url1    for_get_picture(url1)

3，下载视频

# -*- coding: UTF-8 -*-import requests#url = 'https://www.fa67e7417bdc.com/shipin/play-143013.html'url1 = 'https://s1.cdn-c55291f64e9b0e3a.com/common/duanshipin/2021-05-11/dsp_7814d78ed1b2cafda14e85dd81488872_wm/dsp_7814d78ed1b2cafda14e85dd81488872_wm.mp4'#res = requests.get(url1)#print res.contenthd = {'Origin': 'https://www.fa67e7417bdc.com','Referer': 'https://www.fa67e7417bdc.com/shipin/play-143014.html','User-Agent': 'Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.110 Mobile Safari/537.36'}print('开始下载')url = 'https://myjkgl.net/common/duanshipin/2021-05-11/dsp_ad0acdb7273fef972bcc14b3d81edac2_wm/enc_dsp_ad0acdb7273fef972bcc14b3d81edac2_wm4.ts'r = requests.get(url, headers=hd, stream=True)with open('test.mp4', 'wb') as mp4: for chunk in r.iter_content(chunk_size=1024 * 1024): if chunk: mp4.write(chunk)

4，request请求

# -*- coding: UTF-8 -*-import requestsfrom requests.packages.urllib3.exceptions import InsecureRequestWarningrequests.packages.urllib3.disable_warnings(InsecureRequestWarning)url = 'https://www.cnblogs.com/ljfight/p/9577783.html'header = {    'test': '123',    'test1': '124'}parameters = {    'test': '124'}#response = requests.get(url, params = parameters, headers = header)response = requests.get(url, verify = False)print response.contentprint response.status_code