def get_fzrb():
paper_name = '法制日报'
today_str = datetime.strftime(datetime.now(), '%Y%m%d')
paper_dir = os.path.dirname(__file__) + os.sep + \
'papers' + os.sep + today_str+'/'+paper_name+'/'
os.makedirs(paper_dir, exist_ok=True)
url = 'http://epaper.legaldaily.com.cn/fzrb/content/PaperIndex.htm'
soup = getSoup(url)
real_url = re.findall('URL=(.*?)"', str(soup.select('meta')[3]))[0]
url = urljoin(url, real_url)
soup = getSoup(url)
url_page1 = urljoin(
url,
re.findall('URL=(.*?)"', str(soup.select('meta')[3]))[0])
soup = getSoup(url_page1)
# 各版面pdf地址列表
layout_pdf_trs = soup.select(
'body>table>tr:nth-of-type(2)>td:nth-of-type(1)>table>tr:nth-of-type(1)>td:nth-of-type(2)>table:nth-of-type(3) tr'
)
for tr in layout_pdf_trs:
print('-' * 50)
a = tr.select('tr td:nth-of-type(3) a')[0].attrs['href']
pdf_url = urljoin(url, a)
print(paper_name + ' - ' + pdf_url)
downwithbar(pdf_url, paper_dir)
print('-' * 50)
def get_kjrb():
paper_name = '科技日报'
today_str = datetime.strftime(datetime.now(), '%Y%m%d')
paper_dir = os.path.dirname(__file__) + os.sep + \
'papers' + os.sep + today_str+'/'+paper_name+'/'
os.makedirs(paper_dir, exist_ok=True)
url = 'http://digitalpaper.stdaily.com/'
soup = getSoup(url)
url_1 = urljoin(url,
re.findall('URL=(.*?)"', str(soup.select('meta')[3]))[0])
soup = getSoup(url_1)
url_2 = urljoin(url_1,
re.findall('URL=(.*?)"', str(soup.select('meta')[3]))[0])
soup = getSoup(url_2)
layouts = soup.select('div.bmname a')
for layout in layouts:
layout_url = urljoin(url_2, layout.attrs['href'])
layout_soup = getSoup(layout_url)
a = layout_soup.select('.pdf a')[0].attrs['href']
pdf_url = urljoin(layout_url, a)
print(paper_name + ' - ' + pdf_url)
downwithbar(pdf_url, paper_dir)
print('-' * 50)
def get_xxsb():
paper_name = '学习时报'
today_str = datetime.strftime(datetime.now(), '%Y%m%d')
paper_dir = os.path.dirname(__file__) + os.sep + \
'papers' + os.sep + today_str+'/'+paper_name+'/'
os.makedirs(paper_dir, exist_ok=True)
url = 'http://paper.cntheory.com'
soup = getSoup(url)
url_1 = urljoin(url,
re.findall('URL=(.*?)"', str(soup.select('meta')[3]))[0])
soup = getSoup(url_1)
layouts = soup.select('.right_title-pdf a')
for i in range(len(layouts)):
layout_url = urljoin(url_1, layouts[i].attrs['href'])
pdf_url = layout_url
print(paper_name + ' - ' + pdf_url)
i = i + 1
downwithbar(pdf_url, paper_dir, str(i) if i > 9 else '0' + str(i))
print('-' * 50)
def get_grrb():
paper_name = '工人日报'
today_str = datetime.strftime(datetime.now(), '%Y%m%d')
paper_dir = os.path.dirname(__file__) + os.sep + \
'papers' + os.sep + today_str+'/'+paper_name+'/'
os.makedirs(paper_dir, exist_ok=True)
paper_api_home = 'http://i.workercn.cn/paper'
paper_date = json.loads(
requests.get(paper_api_home + '/grrb/index.json?t=' +
str(random.random())).text)['index']
dates = str.split(paper_date, '-')
paperUrl = paper_api_home + "/" + "grrb" + "/" + \
dates[0] + "/" + dates[1] + "/" + dates[2] + ".json"
paper_data = json.loads(requests.get(paperUrl).text)
for i in range(1, len(paper_data['pages']) + 1):
pdf_url = paper_data['paperHomeUrl'] + "/" + \
str(i) + "/grrb" + dates[0] + dates[1] + dates[2] + str(i) + ".pdf"
print(paper_name + ' - ' + pdf_url)
downwithbar(pdf_url, paper_dir)
print('-' * 50)
def get_zggfb():
paper_name = '中国国防报'
today_str = datetime.strftime(datetime.now(), '%Y%m%d')
paper_dir = os.path.dirname(__file__) + os.sep + \
'papers' + os.sep + today_str+'/'+paper_name+'/'
os.makedirs(paper_dir, exist_ok=True)
url = 'http://www.81.cn:80/gfbmap/paperindex.htm'
soup = getSoup(url)
real_url = re.findall('URL=(.*?)"', str(soup.select('meta')[3]))[0]
url = urljoin(url, real_url)
soup = getSoup(url)
layouts = soup.select('#APP-SectionNav li a')
for layout in layouts:
layout_url = urljoin(url, layout.attrs['href'])
layout_soup = getSoup(layout_url)
pdf_url_temp = layout_soup.select('#APP-Pdf')[0].attrs['href']
pdf_url = urljoin(layout_url, pdf_url_temp)
print(paper_name + ' - ' + pdf_url)
downwithbar(pdf_url, paper_dir)
print('-' * 50)
def get_xhmrdx():
paper_name = '新华每日电讯'
today_str = datetime.strftime(datetime.now(), '%Y%m%d')
paper_dir = os.path.dirname(__file__) + os.sep + \
'papers' + os.sep + today_str+'/'+paper_name+'/'
os.makedirs(paper_dir, exist_ok=True)
url = 'http://mrdx.cn/content/PaperIndex.htm'
soup = getSoup(url)
real_url = re.findall('URL=(.*?)"', str(soup.select('meta')[3]))[0]
url = urljoin(url, real_url)
soup = getSoup(url)
real_url_2 = re.findall('URL=(.*?)"', str(soup.select('meta')[3]))[0]
url = urljoin(url, real_url_2)
soup = getSoup(url)
layouts = soup.select('.pdf')
for layout in layouts:
pdf_url = urljoin(url, layout.attrs['href'])
print(paper_name + ' - ' + pdf_url)
downwithbar(pdf_url, paper_dir)
print('-' * 50)
def get_rmrb():
paper_name = '人民日报'
today_str = datetime.strftime(datetime.now(), '%Y%m%d')
paper_dir = os.path.dirname(__file__) + os.sep + \
'papers' + os.sep + today_str+'/'+paper_name+'/'
os.makedirs(paper_dir, exist_ok=True)
url = 'http://paper.people.com.cn/rmrb/paperindex.htm'
soup = getSoup(url)
real_url = re.findall('URL=(.*?)"', str(soup.select('meta')[3]))[0]
url = urljoin(url, real_url)
soup = getSoup(url)
layouts = soup.select('#pageLink')
for layout in layouts:
time.sleep(1)
layout_url = urljoin(url, layout.attrs['href'])
layout_soup = getSoup(layout_url)
pdf_url_temp = layout_soup.select('.paper-bot .btn a')[0].attrs['href']
pdf_url = urljoin(layout_url, pdf_url_temp)
print(paper_name + ' - ' + pdf_url)
downwithbar(pdf_url, paper_dir)
print('-' * 50)