Python学习日记 xpath练习

import requests
from lxml import etree
import re
import random
import traceback
from time import sleep

# url = 'https://image.baidu.com/search/acjson?tn=resultjson_com&logid=8700291432374701138&ipn=rj&ct=201326592&is=&fp=result&fr=ala&word=%E8%A1%A8%E6%83%85%E5%8C%85&queryWord=%E8%A1%A8%E6%83%85%E5%8C%85&cl=2&lm=-1&ie=utf-8&oe=utf-8&adpicid=&st=&z=&ic=&hd=&latest=©right=&s=&se=&tab=&width=&height=&face=&istype=&qc=&nc=&expermode=&nojc=&isAsync=&pn=390&rn=30&gsm=186'
headers = {
    'Cookie':'winWH=%5E6_1920x963; BDIMGISLOGIN=0; BDqhfp=%E8%A1%A8%E6%83%85%E5%8C%85%26%26NaN-1undefined%26%268772%26%2614; BIDUPSID=47D1A97F74FE4D84D9C060A7E9D9623C; PSTM=1688450494; BAIDUID=64354928A148308F322D02D378FB19A4:FG=1; BAIDUID_BFESS=64354928A148308F322D02D378FB19A4:FG=1; ZFY=r0Ch4DZ4vzKkjKsCTr20yTyvBoJZR:BJjX3:AbIpxAvCs:C; BA_HECTOR=05812la52la52l80008505891ieo2c31p; PSINO=1; H_PS_PSSID=36548_39226_39223_39193_39199_39240_39233_26350_39238_39138_39224_39137_22157_39100; delPer=0; BDORZ=B490B5EBF6F3CD402E515D22BCDA1598; BDRCVFR[dG2JNJb_ajR]=mk3SLVN4HKm; BDRCVFR[-pGxjrCMryR]=mk3SLVN4HKm; BDRCVFR[tox4WRQ4-Km]=mk3SLVN4HKm; BDRCVFR[A24tJn4Wkd_]=mk3SLVN4HKm',
    'Host':'image.baidu.com',
    'Referer':'https://image.baidu.com/search/index?tn=baiduimage&ct=201326592&lm=-1&cl=2&ie=gb18030&word=%B1%ED%C7%E9%B0%FC&fr=ala&ala=1&alatpl=normal&pos=0&',
    'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/116.0.0.0 Safari/537.36'
}
for i in range(1350,1440,30):
    sleep(random.uniform(1,2))
    num =hex(i)
    num = num[2:]
    url =f'https://image.baidu.com/search/acjson?tn=resultjson_com&logid=8700291432374701138&ipn=rj&ct=201326592&is=&fp=result&fr=ala&word=%E8%A1%A8%E6%83%85%E5%8C%85&queryWord=%E8%A1%A8%E6%83%85%E5%8C%85&cl=2&lm=-1&ie=utf-8&oe=utf-8&adpicid=&st=&z=&ic=&hd=&latest=©right=&s=&se=&tab=&width=&height=&face=&istype=&qc=&nc=&expermode=&nojc=&isAsync=&pn={i}&rn=30&gsm={num}'
    data = {
        'tn': 'resultjson_com',
        'logid': '8700291432374701138',
        'ipn': 'rj',
        'ct': '201326592',
        'is': '',
        'fp': 'result',
        'fr': 'ala',
        'word': '表情包',
        'queryWord': '表情包',
        'cl': '2',
        'lm': '-1',
        'ie': 'utf-8',
        'oe': 'utf-8',
        'adpicid': '',
        'st': '',
        'z': '',
        'ic': '',
        'hd': '',
        'latest': '',
        'copyright': '',
        's': '',
        'se': '',
        'tab': '',
        'width': '',
        'height': '',
        'face': '',
        'istype': '',
        'qc': '',
        'nc': '',
        'expermode': '',
        'nojc': '',
        'isAsync': '',
        'pn': f'{i}',
        'rn': '30',
        'gsm': f'{num}',
        
    }
    resp = requests.get(url , headers=headers,data=data)

    resp_json = resp.json()
    resp_urls = resp_json['data']

    for resp_url in resp_urls:
        sleep(random.uniform(0,1))
        try:
            fromPageTitle = resp_url['fromPageTitle']
            fromPageTitle = re.sub(r'[/\*?<>|\n-_ ]','',fromPageTitle)
            fromPageTitle = fromPageTitle[0:15]
            middleURL = resp_url['middleURL']
            name = re.split(r'(\w+)',middleURL)
            info = requests.get(middleURL)
            # print(name[-10],fromPageTitle,middleURL)
            with open (str(i)+fromPageTitle+'.'+name[-10],'wb') as f:
                f.write(info.content)
            print(str(i) + fromPageTitle + '下载完成')
        except Exception as e:
            traceback.print_exc()
            continue

这个是昨天做的百度表情包下载的程序

import traceback
# # for i in range(30,600,30):
# #     num = hex(i)
# #     num = num[2:]
# #     print(num)
# # from time import sleep
# # import random
# # for i in range(0,10):
# #     # x = random.uniform(1,2)
# #     sleep(random.uniform(0,1))
# #     print(random.uniform(0,1))
# for i in range(0,5):
#     try:
#         n =1/ i
#         print(n)
#     except Exception as e:
#         traceback.print_exc()


import requests
import csv
from lxml import etree
data = []
for i in range(0,250,25):
    url = f'https://movie.douban.com/top250?start={i}&filter='
    headers = {
        'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/116.0.0.0 Safari/537.36'
    }
    resp = requests.get(url , headers=headers)
    html = etree.HTML(resp.text)
    html_info = html.xpath('//ol[@class="grid_view"]/li')
    # print(html_info)

    for info in html_info:
        # print(info)
        dic = {}
        dic['href'] = info.xpath('.//div[@class="hd"]/a/@href')[0]
        dic['title'] = info.xpath('.//div[@class="pic"]/a/img/@alt')[0]
        dic['pingjiashu'] = info.xpath('.//div[@class="star"]/span[4]/text()')[0]
        dic['content'] = info.xpath('.//div[@class="star"]/span[2]/text()')[0]
        data.append(dic)
    print(f'正在下载第{i}页')

with open('dbmovie.csv','a',encoding='utf-8',newline='')as f:
    w = csv.DictWriter(f,fieldnames=['title','href','pingjiashu','content'])
    w.writeheader()
    w.writerows(data)

xpath练习