File size: 22,778 Bytes
39fe3d1 eaaafcb 39fe3d1 eaaafcb 39fe3d1 eaaafcb 39fe3d1 eaaafcb bd95ddb eaaafcb d05c91c eaaafcb 39fe3d1 eaaafcb 7b6960f eaaafcb d05c91c eaaafcb efcd6b8 eaaafcb 36b7b27 eaaafcb 7b6960f 36b7b27 eaaafcb d05c91c eaaafcb 39fe3d1 eaaafcb 8925fd4 d4c6492 eaaafcb d05c91c eaaafcb d05c91c eaaafcb d05c91c eaaafcb d05c91c eaaafcb d05c91c eaaafcb d05c91c eaaafcb 39fe3d1 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 |
"""
This script is responsible for collecting data from various websites related to financial and policy information in China.
It fetches data from different sources, extracts relevant information, translates it, and updates the content accordingly.
The collected data includes policy interpretations, financial news, macroeconomic research, and more.
"""
import json
import os
import time
import urllib.request
import uuid
from datetime import datetime, timedelta
from urllib.parse import urlparse
from lxml import etree
from utils import (crawl, datemodifier, encode, encode_content,
extract_from_pdf, extract_reference, fetch_url,
sentiment_computation, translate, update_content)
with open('xpath.json', 'r', encoding='UTF-8') as f:
xpath_dict = json.load(f)
DELTA = int(os.environ.get('DELTA') or '1')
print(f"DELTA = {DELTA}")
print("cbirc.gov.cn")
i = 1
while i > -1:
CATEGORY_URL = f"https://www.cbirc.gov.cn/cn/static/data/DocInfo/SelectDocByItemIdAndChild/data_itemId=917,pageIndex={i},pageSize=18.json"
i = i + 1
content = fetch_url(CATEGORY_URL)
reportinfo = json.loads(content)
for article in reportinfo['data']['rows']:
try:
article['publishDate'] = time.strftime("%Y-%m-%d", time.strptime(article['publishDate'],"%Y-%m-%d %H:%M:%S"))
parsed_datetime = datetime.strptime(article['publishDate'], "%Y-%m-%d")
if parsed_datetime < (datetime.today() - timedelta(days=DELTA)):
i = -1
else:
contentCN, summary = extract_from_pdf("https://www.cbirc.gov.cn" + article['pdfFileUrl'])
article['contentCN'] = repr(contentCN)[1:-1].strip()
if len(contentCN) < 10:
continue
CONTENT_ENG = ''
for element in article['contentCN'].split("\n"):
CONTENT_ENG += translate(element) + '\n'
article['content'] = repr(CONTENT_ENG)[1:-1].strip()
article['site'] = "National Financial Regulatory Administration of China"
article['originSite'] = "国家金融监督管理总局"
article['titleCN'] = article['docSubtitle']
article['title'] = translate(article['docSubtitle'])
article['link'] = "https://www.cbirc.gov.cn" + str(article['pdfFileUrl'])
article['category']= "Policy Interpretation"
article['id'] = uuid.uuid5(uuid.NAMESPACE_OID, article['titleCN']+article['publishDate'])
article['sentimentScore'], article['sentimentLabel'] = sentiment_computation(article['content'])
article['attachment'] = ''
article['author'] = ''
article['subtitle'] = translate(summary)
update_content(article)
except Exception as error:
print(error)
print("csrc.gov.cn")
i = 1
while i > -1:
try:
if i == 1:
CATEGORY_URL = "http://www.csrc.gov.cn/csrc/c100039/common_list.shtml"
else:
CATEGORY_URL = f"http://www.csrc.gov.cn/csrc/c100039/common_list_{i}.shtml"
i = i + 1
req = urllib.request.urlopen(CATEGORY_URL)
text = req.read()
html_text = text.decode("utf-8")
page = etree.HTML(html_text)
articlelist = page.xpath("//div[contains(@class, 'main-right fr common-list')]/ul/li")
for article in articlelist:
if isinstance(article, etree._Element):
subelement = etree.tostring(article).decode()
subpage = etree.HTML(subelement)
date = encode(subpage.xpath("//span[@class='date']"))
parsed_datetime = datetime.strptime(time.strftime("%Y-%m-%d", time.strptime(date,"%Y-%m-%d")), "%Y-%m-%d")
if parsed_datetime < (datetime.today() - timedelta(days=DELTA)):
i = -1
else:
urls = subpage.xpath("//a/@href")
for url in urls:
try:
article = {}
url = "http://www.csrc.gov.cn" + url
article['category']= "Policy Interpretation"
crawl(url, article)
except Exception as error:
print(error)
except Exception as error:
i = -1
print(error)
i = 1
while i > -1:
CATEGORY_URL = f"http://www.csrc.gov.cn/searchList/a1a078ee0bc54721ab6b148884c784a8?_isAgg=true&_isJson=true&_pageSize=18&_template=index&_rangeTimeGte=&_channelName=&page={i}"
i = i + 1
try:
content = fetch_url(CATEGORY_URL)
reportinfo = json.loads(content)
for article in reportinfo['data']['results']:
parsed_datetime = datetime.strptime(time.strftime("%Y-%m-%d", time.strptime(article['publishedTimeStr'],"%Y-%m-%d %H:%M:%S")), "%Y-%m-%d")
if parsed_datetime < (datetime.today() - timedelta(days=DELTA)):
i = -1
else:
article['category']= "Financial News"
article['site'] = "Securities Regulatory Commission of China"
article['originSite'] = "证监会"
article['titleCN'] = article['title']
article['title'] = translate(article['titleCN'])
article['author'] = ''
article['contentCN'] = repr(article['content'])[1:-1].strip()
if len(article['contentCN']) < 10:
continue
CONTENT_ENG = ''
for element in article['contentCN'].split("。"):
CONTENT_ENG += translate(element) + ' '
article['content'] = repr(CONTENT_ENG)[1:-1].strip()
article['subtitle'] = article['memo']
article['publishDate'] = time.strftime("%Y-%m-%d", time.strptime(article['publishedTimeStr'],"%Y-%m-%d %H:%M:%S"))
article['link'] = article['url']
article['attachment'] = ""
article['sentimentScore'], article['sentimentLabel'] = sentiment_computation(article['content'])
article['id'] = uuid.uuid5(uuid.NAMESPACE_OID, article['titleCN']+article['publishDate'])
update_content(article)
except Exception as error:
print(error)
print("data.eastmoney.com")
def crawl_eastmoney(url, article):
"""
Crawls the given URL and extracts information from the webpage.
Args:
url (str): The URL of the webpage to crawl.
article (dict): A dictionary to store the extracted information.
Returns:
None: If the length of the extracted content is less than 10 characters.
Raises:
None.
"""
domain = urlparse(url).netloc
req = urllib.request.urlopen(url)
text = req.read()
html_text = text.decode("utf-8")
page = etree.HTML(html_text)
contentCN, summary = encode_content(page.xpath(xpath_dict[domain]['content']))
article['attachment'] = encode(page.xpath(xpath_dict[domain]['attachment']))
article['link'] = url
if article['orgSName'] == "''":
article['site'] = translate(article['orgSName'])
else:
article['site'] = translate(article['orgName'])
article['titleCN'] = article['title']
article['title'] = translate(article['title'])
article['author'] = translate(article['researcher'])
article['originAuthor'] = article['researcher']
article['contentCN'] = repr(contentCN)[1:-1].strip()
article['subtitle'] = translate(summary)
article['category'] = "Macroeconomic Research"
if len(article['contentCN']) < 10:
return None
CONTENT_ENG = ''
for element in contentCN.split("\n"):
CONTENT_ENG += translate(element) + '\n'
article['content'] = repr(CONTENT_ENG)[1:-1].strip()
article['authorid'] = uuid.uuid5(uuid.NAMESPACE_OID, article['author'])
article['publishDate'] = datemodifier(article['publishDate'], xpath_dict[domain]['datetime_format'])
article['id'] = uuid.uuid5(uuid.NAMESPACE_OID, article['titleCN']+article['publishDate'])
article['sentimentScore'], article['sentimentLabel'] = sentiment_computation(contentCN.replace("\n",""))
extract_reference(article)
update_content(article)
today = datetime.today().strftime('%Y-%m-%d')
beginDate = (datetime.today() - timedelta(days=DELTA)).strftime('%Y-%m-%d')
i = 0
while i > -1:
URL = "https://reportapi.eastmoney.com/report/jg"
params = {
"cb": "datatable8544623",
"pageSize": "100",
"beginTime": beginDate,
"endTime": today,
"pageNo": i,
"qType": "3",
}
URL = URL + "?" + "&".join(f"{key}={value}" for key, value in params.items())
content = fetch_url(URL)
if content:
start_index = content.find("(")
if start_index != -1:
result = content[start_index + 1: -1]
else:
result = content
reportinfo = json.loads(result)
if reportinfo["size"] > 0:
i = i + 1
for article in reportinfo['data']:
try:
url = f"https://data.eastmoney.com/report/zw_macresearch.jshtml?encodeUrl={article['encodeUrl']}"
crawl_eastmoney(url,article)
except Exception as error:
print(error)
else:
i = -1
else:
print("Failed to fetch URL:", url)
print("gov.cn")
i = 0
while i > -1:
if i == 0:
CATEGORY_URL = "https://www.gov.cn/zhengce/jiedu/home.htm"
else:
CATEGORY_URL = f"https://www.gov.cn/zhengce/jiedu/home_{i}.htm"
i = i + 1
req = urllib.request.urlopen(CATEGORY_URL)
text = req.read()
html_text = text.decode("utf-8")
page = etree.HTML(html_text)
articlelist = page.xpath("//div[contains(@class, 'news_box')]//h4")
for article in articlelist:
if isinstance(article, etree._Element):
subelement = etree.tostring(article).decode()
subpage = etree.HTML(subelement)
date = subpage.xpath("//span/text()")[0]
parsed_datetime = datetime.strptime(time.strftime("%Y-%m-%d", time.strptime(date,"%Y-%m-%d")), "%Y-%m-%d")
if parsed_datetime < (datetime.today() - timedelta(days=DELTA)):
i = -1
else:
urls = subpage.xpath("//a[contains(@target, '_blank')]/@href")
for url in urls:
try:
article = {}
url = url.replace('../', 'https://www.gov.cn/zhengce/')
if "https://www.gov.cn" in url:
article['category']= "Policy Interpretation"
crawl(url, article)
except Exception as error:
print(error)
i = 0
while i > -1:
if i == 0:
CATEGORY_URL = "https://www.gov.cn/zhengce/zuixin/home.htm"
else:
CATEGORY_URL = f"https://www.gov.cn/zhengce/zuixin/home_{i}.htm"
i = i + 1
req = urllib.request.urlopen(CATEGORY_URL)
text = req.read()
html_text = text.decode("utf-8")
page = etree.HTML(html_text)
articlelist = page.xpath("//div[contains(@class, 'news_box')]//h4")
for article in articlelist:
if isinstance(article, etree._Element):
subelement = etree.tostring(article).decode()
subpage = etree.HTML(subelement)
date = subpage.xpath("//span/text()")[0]
parsed_datetime = datetime.strptime(time.strftime("%Y-%m-%d", time.strptime(date,"%Y-%m-%d")), "%Y-%m-%d")
if parsed_datetime < (datetime.today() - timedelta(days=DELTA)):
i = -1
else:
urls = subpage.xpath("//a[contains(@target, '_blank')]/@href")
for url in urls:
try:
article = {}
url = url.replace('../', 'https://www.gov.cn/zhengce/')
if "https://www.gov.cn" in url:
article['site'] = "State Council of China"
crawl(url, article)
except Exception as error:
print(error)
print("mof.gov.cn")
i = 0
while i > -1:
if i == 0:
CATEGORY_URL = "https://www.mof.gov.cn/zhengwuxinxi/caizhengxinwen/"
else:
CATEGORY_URL = f"https://www.mof.gov.cn/zhengwuxinxi/caizhengxinwen/index_{i}.htm"
i = i + 1
req = urllib.request.urlopen(CATEGORY_URL)
text = req.read()
html_text = text.decode("utf-8")
page = etree.HTML(html_text)
articlelist = page.xpath("//div[contains(@class, 'xwfb_listerji')]/ul/li[not(@class = 'clear')]")
for article in articlelist:
if isinstance(article, etree._Element):
subelement = etree.tostring(article).decode()
subpage = etree.HTML(subelement)
date = subpage.xpath("//span/text()")[0]
parsed_datetime = datetime.strptime(time.strftime("%Y-%m-%d", time.strptime(date,"%Y-%m-%d")), "%Y-%m-%d")
if parsed_datetime < (datetime.today() - timedelta(days=DELTA)):
i = -1
else:
urls = subpage.xpath("//a[contains(@target, '_blank')]/@href")
for url in urls:
try:
article = {}
url = url.replace("../", "https://www.mof.gov.cn/zhengwuxinxi/")
url = url.replace("./", "https://www.mof.gov.cn/zhengwuxinxi/caizhengxinwen/")
article['category']= "Financial News"
crawl(url, article)
except Exception as error:
print(error)
i = 0
while i > -1:
if i == 0:
CATEGORY_URL = "https://www.mof.gov.cn/zhengwuxinxi/zhengcejiedu/"
else:
CATEGORY_URL = f"https://www.mof.gov.cn/zhengwuxinxi/zhengcejiedu/index_{i}.htm"
i = i + 1
req = urllib.request.urlopen(CATEGORY_URL)
text = req.read()
html_text = text.decode("utf-8")
page = etree.HTML(html_text)
articlelist = page.xpath("//div[contains(@class, 'xwfb_listerji')]/ul/li[not(@class = 'clear')]")
for article in articlelist:
if isinstance(article, etree._Element):
subelement = etree.tostring(article).decode()
subpage = etree.HTML(subelement)
date = subpage.xpath("//span/text()")[0]
parsed_datetime = datetime.strptime(time.strftime("%Y-%m-%d", time.strptime(date,"%Y-%m-%d")), "%Y-%m-%d")
if parsed_datetime < (datetime.today() - timedelta(days=DELTA)):
i = -1
else:
urls = subpage.xpath("//a[contains(@target, '_blank')]/@href")
for url in urls:
try:
article = {}
url = url.replace("./", CATEGORY_URL)
article['category']= "Policy Interpretation"
print(url)
crawl(url, article)
except Exception as error:
print(error)
print("mofcom.gov.cn")
categories = ['jdzhsw','jdgnmy','jddwmy','jdtzhz']
for category in categories:
i = 1
while i > -1:
if i == 1:
URL = f"http://www.mofcom.gov.cn/article/zcjd/{category}/"
else:
URL = f"http://www.mofcom.gov.cn/article/zcjd/{category}/?{i}"
i = i + 1
req = urllib.request.urlopen(URL)
text = req.read()
html_text = text.decode("utf-8")
page = etree.HTML(html_text)
articlelist = page.xpath("//section[contains(@class, 'listCon iListCon f-mt30')]/ul/li")
for article in articlelist:
if isinstance(article, etree._Element):
subelement = etree.tostring(article).decode()
subpage = etree.HTML(subelement)
date = subpage.xpath("//span/text()")[0]
parsed_datetime = datetime.strptime(time.strftime("%Y-%m-%d", time.strptime(date,"%Y-%m-%d %H:%M:%S")), "%Y-%m-%d")
if parsed_datetime < (datetime.today() - timedelta(days=DELTA)):
i = -1
else:
urls = subpage.xpath("//a/@href")
for url in urls:
try:
article = {}
if '/article/zcjd' in url:
url = "http://www.mofcom.gov.cn" + url
article['category']= "Policy Interpretation"
else:
article['category']= "Policy Release"
crawl(url, article)
except Exception as error:
print(error)
print("ndrc.gov.cn")
i = 0
while i > -1:
if i == 0:
CATEGORY_URL = "https://www.ndrc.gov.cn/xxgk/jd/jd/index.html"
else:
CATEGORY_URL = f"https://www.ndrc.gov.cn/xxgk/jd/jd/index_{i}.html"
i = i + 1
req = urllib.request.urlopen(CATEGORY_URL)
text = req.read()
html_text = text.decode("utf-8")
page = etree.HTML(html_text)
articlelist = page.xpath("//div[contains(@class, 'list')]/ul/li[not(@class = 'empty')]")
for article in articlelist:
if isinstance(article, etree._Element):
subelement = etree.tostring(article).decode()
subpage = etree.HTML(subelement)
date = subpage.xpath("//span/text()")[0]
parsed_datetime = datetime.strptime(time.strftime("%Y-%m-%d", time.strptime(date,"%Y/%m/%d")), "%Y-%m-%d")
if parsed_datetime < (datetime.today() - timedelta(days=DELTA)):
i = -1
else:
urls = subpage.xpath("//a[contains(@target, '_blank')]/@href")
for url in urls:
try:
article = {}
if "www.gov.cn" in url:
article['category']= "Policy Release"
elif "../../zcfb/" in url:
url = url.replace("../../zcfb/", "https://www.ndrc.gov.cn/xxgk/zcfb/")
article['category']= "Policy Release"
else:
url = url.replace("../../", "https://www.ndrc.gov.cn/xxgk/jd/jd/")
url = url.replace("./", "https://www.ndrc.gov.cn/xxgk/jd/jd/")
article['category']= "Policy Interpretation"
crawl(url, article)
except Exception as error:
print(error)
print("safe.gov.cn")
i = 1
while i > -1:
if i == 1:
CATEGORY_URL = "https://www.safe.gov.cn/safe/zcfgjd/index.html"
else:
CATEGORY_URL = f"https://www.safe.gov.cn/safe/zcfgjd/index_{i}.html"
i = i + 1
req = urllib.request.urlopen(CATEGORY_URL)
text = req.read()
html_text = text.decode("utf-8")
page = etree.HTML(html_text)
articlelist = page.xpath("//div[contains(@class, 'list_conr')]/ul/li")
for article in articlelist:
if isinstance(article, etree._Element):
subelement = etree.tostring(article).decode()
subpage = etree.HTML(subelement)
date = subpage.xpath("//dd/text()")[0]
parsed_datetime = datetime.strptime(time.strftime("%Y-%m-%d", time.strptime(date,"%Y-%m-%d")), "%Y-%m-%d")
if parsed_datetime < (datetime.today() - timedelta(days=DELTA)):
i = -1
else:
urls = subpage.xpath("//a/@href")
for url in urls:
try:
article = {}
url = "https://www.safe.gov.cn" + url
article['category']= "Policy Interpretation"
crawl(url, article)
except Exception as error:
print(error)
i = 1
while i > -1:
if i == 1:
CATEGORY_URL = "https://www.safe.gov.cn/safe/sjjd/index.html"
else:
CATEGORY_URL = f"https://www.safe.gov.cn/safe/sjjd/index_{i}.html"
i = i + 1
req = urllib.request.urlopen(CATEGORY_URL)
text = req.read()
html_text = text.decode("utf-8")
page = etree.HTML(html_text)
articlelist = page.xpath("//div[contains(@class, 'list_conr')]/ul/li")
for article in articlelist:
if isinstance(article, etree._Element):
subelement = etree.tostring(article).decode()
subpage = etree.HTML(subelement)
date = subpage.xpath("//dd/text()")[0]
parsed_datetime = datetime.strptime(time.strftime("%Y-%m-%d", time.strptime(date,"%Y-%m-%d")), "%Y-%m-%d")
if parsed_datetime < (datetime.today() - timedelta(days=DELTA)):
i = -1
else:
urls = subpage.xpath("//a/@href")
for url in urls:
try:
article = {}
url = "https://www.safe.gov.cn" + url
article['category']= "Data Interpretation"
crawl(url, article)
except Exception as error:
print(error)
print("stats.gov.hk")
i = 0
while i > -1:
if i == 0:
CATEGORY_URL = "https://www.stats.gov.cn/sj/sjjd/"
else:
CATEGORY_URL = f"https://www.stats.gov.cn/sj/sjjd/index_{i}.html"
i = i + 1
req = urllib.request.urlopen(CATEGORY_URL)
text = req.read()
html_text = text.decode("utf-8")
page = etree.HTML(html_text)
articlelist = page.xpath("//div[contains(@class, 'list-content')]/ul/li")
for article in articlelist:
if isinstance(article, etree._Element):
subelement = etree.tostring(article).decode()
subpage = etree.HTML(subelement)
date = encode(subpage.xpath("//span"))
parsed_datetime = datetime.strptime(time.strftime("%Y-%m-%d", time.strptime(date,"%Y-%m-%d")), "%Y-%m-%d")
if parsed_datetime < (datetime.today() - timedelta(days=DELTA)):
i = -1
else:
urls = subpage.xpath("//a[@class='fl pc_1600']/@href")
for url in urls:
try:
article = {}
url = url.replace('./', "https://www.stats.gov.cn/sj/sjjd/")
article['category']= "Data Interpretation"
crawl(url, article)
except Exception as error:
print(error)
|