class Producer(threading.Thread):
def __init__(self, antibody_url_queue, *args, **kwargs):
super(Producer, self).__init__(*args, **kwargs)
self.antibody_url_queue = antibody_url_queue
self.mysql = MYSQL('new_antibodies_info')
def run(self):
while True:
if self.antibody_url_queue.empty():
break
url = self.antibody_url_queue.get()
self.parse_page(url)
time.sleep(random.uniform(1.5, 2.5))
def parse_page(self, url):
global count
try:
r = requests.get(url, headers=get_request_headers(), timeout=10)
r.raise_for_status()
except Exception as e:
self.antibody_url_queue.put(url)
print('访问抗体列表页失败，将url放回队列')
print(e)
else:
html = r.text
try:
catanum_list = re.findall('"ProductCode":"(.*?)"', html, re.S)
catanum = get_first_item(catanum_list, 40)
size_price_list = re.findall(
'"Size":"(.*?)".*?"Price":"(.*?)"', html, re.S)
for size_price in size_price_list:
size = size_price[0]
price = size_price[1]
price_sql = 'insert into Abcam_Antibody_price(Catalog_Number,Size,Price) values("{}","{}","{}");'.format(
catanum, size, price)
self.mysql.insert_into_table(price_sql)
# data = json.loads(html)
# for i in data:
# title = i['Title']
# pmid = i['PubmedID']
# application = i['ApplicationsShortName']
# species = i['Species']
# citation_sql = 'insert into Abcam_Antibody_citations (Catalog_Number, PMID , Application, Species, Article_title) values ("{}","{}","{}","{}","{}");'.format(
# catanum, pmid, application, species, pymysql.escape_string(title))
# self.mysql.insert_into_table(citation_sql)
except Exception as es:
print(es)
print(url)
else:
update_status_sql = 'update Abcam_Antibody_detail set Price_Status = "1" where Price_url = "%s";' % url
self.mysql.insert_into_table(update_status_sql)
count += 1
print("\r获得抗体详情页进度: %d" % count, end="")
class Producer (threading.Thread):
def __init__(self, antibody_url_queue, *args, **kwargs):
super(Producer, self).__init__(*args, **kwargs)
self.antibody_url_queue = antibody_url_queue
self.mysql = MYSQL('new_antibodies_info')
def run(self):
while True:
if self.antibody_url_queue.empty():
break
url = self.antibody_url_queue.get()
self.parse_page(url)
time.sleep(random.uniform(1.5, 2.5))
def parse_page(self, url):
global count
try:
r = requests.get(url, headers=get_request_headers(), timeout=10)
r.raise_for_status()
except Exception as e:
self.antibody_url_queue.put(url)
print('访问抗体列表页失败，将url放回队列')
print(e)
else:
html = r.text
element = etree.HTML(html)
try:
catanum = url.split('=')[1]
data = json.loads(html)
for i in data:
title = i['Title']
pmid = i['PubmedID']
application = i['ApplicationsShortName']
species = i['Species']
citation_sql = 'insert into Abcam_Antibody_citations (Catalog_Number, PMID , Application, Species, Article_title) values ("{}","{}","{}","{}","{}");'.format(
catanum, pmid, application, species, pymysql.escape_string(title))
self.mysql.insert_into_table(citation_sql)
except Exception as es:
print(es)
print(url)
else:
update_status_sql = 'update Abcam_Antibody_detail set Citations_Status = "1" where Citations_url = "%s";' % url
self.mysql.insert_into_table(update_status_sql)
count += 1
print("\r获得抗体详情页进度: %d" % count, end="")
import requests
from utils.Random_UserAgent import get_request_headers
import re
from lxml import etree
from Mysql_helper import MYSQL
mysql = MYSQL('new_antibodies_info')
for x in range(1, 3061):
url = 'https://www.abcam.cn/products/loadmore?selected.productType=Primary+antibodies&pagenumber=%d' % x
sql = 'insert into Abcam_Antibody_list_url (Antibody_list_URL) values("{}");'.format(
url)
mysql.insert_into_table(sql)
class Producer(threading.Thread):
def __init__(self, pmid_queue, *args, **kwargs):
super(Producer, self).__init__(*args, **kwargs)
self.pmid_queue = pmid_queue
self.mysql = MYSQL('antibodies_info')
def run(self):
while True:
if self.pmid_queue.empty():
break
pmid = self.pmid_queue.get()
self.parse_page(pmid)
time.sleep(random.uniform(0.5, 2))
def parse_page(self, pmid):
global count
try:
url = 'https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db=pubmed&id={}&mode=xml&_=1572314980717'.format(
pmid)
r = requests.get(url, headers=get_request_headers(), timeout=10)
r.raise_for_status()
except Exception as e:
self.pmid_queue.put(pmid)
print('访问抗体列表页失败，将{}放回队列'.format(pmid))
print(e)
else:
html = r.text
#pmid_list = re.findall('<PMID Version="1">(.*?)</PMID>', html, re.S)
authors = re.findall(
'<LastName>(.*?)</LastName>.*?<ForeName>(.*?)</ForeName>',
html, re.S)
tab = []
if not authors:
authors = [('', '')]
for i in range(len(authors)):
a = authors[i][0] + ' ' + authors[i][1]
tab.append(a)
author = ', '.join(tab)
pubdate = re.findall(
'<PubDate>.*?<Year>(.*?)</Year>.*?<Month>(.*?)</Month>.*?<Day>(.*?)</Day>',
html, re.S)
if not pubdate:
pubdate = [('', '', '')]
for l in range(len(pubdate)):
pubdatetime = pubdate[l][0] + '-' + pubdate[l][
1] + '-' + pubdate[l][2]
institution = re.findall('<Affiliation>(.*?)</Affiliation>', html,
re.S)
if not institution:
institution = ['']
journal_list = re.findall('<Title>(.*?)</Title>', html, re.S)
journal = get_first_item(journal_list, 100)
try:
insert_sql = 'insert into abcam_citations_details (pmid, journal, pub_date, institution, author) values ("{}","{}","{}","{}","{}");'.format(
pmid, journal, pubdatetime, institution[0], author)
self.mysql.insert_into_table(insert_sql)
except Exception as es:
print(es)
print(url)
else:
update_sql = 'update abcam_pmid set pmid_Status = "1" where pmid = {};'.format(
pmid)
self.mysql.insert_into_table(update_sql)
count += 1
print("\r获得citation详情页进度: %d" % count, end="")
class Producer(threading.Thread):
def __init__(self, antibody_url_queue, *args, **kwargs):
super(Producer, self).__init__(*args, **kwargs)
self.antibody_url_queue = antibody_url_queue
self.mysql = MYSQL('new_antibodies_info')
def run(self):
while True:
if self.antibody_url_queue.empty():
break
url = self.antibody_url_queue.get()
self.parse_page(url)
time.sleep(random.uniform(2.5, 4.5))
def parse_page(self, url):
global count
try:
r = requests.get(url, headers=get_request_headers(), timeout=10)
r.raise_for_status()
except Exception as e:
self.antibody_url_queue.put(url)
print('访问抗体列表页失败，将url放回队列')
print(e)
else:
html = r.text
element = etree.HTML(html)
try:
antiname_list = re.findall(
'产品名称</h3>.*?<div class="value">(.*?)<', html, re.S)
antiname = antiname_list[0]
cataNo_list = re.findall('data-product-code="(.*?)">', html,
re.S)
cataNo = cataNo_list[0]
antibody_type_list = re.findall(
'克隆</h3>.*?<div class="value">(.*?)</div>', html, re.S)
antibody_type = get_first_item(antibody_type_list, 30)
lis = element.xpath('.//li[@class="attribute list"]')
if lis:
li = lis[-1]
synonyms_list = li.xpath('.//li/text()')
synonyms = ','.join(synonyms_list)
synonyms = get_string(synonyms, 3000)
else:
synonyms = ''
# 取指定文本标签的同级标签
divs = element.xpath('.//h3[.="经测试应用"]/following-sibling::div')
if divs:
div = divs[0]
application_lists = div.xpath('./abbr/text()')
application = ','.join(application_lists)
else:
application = ''
conjugation_list = re.findall('<li>Conjugation: (.*?)</li>',
html, re.S)
conjugation = get_first_item(conjugation_list, 200)
clone_number_list = re.findall(
'克隆编号</h3>.*?div class="value">(.*?)</div>', html, re.S)
clone_number = get_first_item(clone_number_list, 40)
recombinant_list = re.findall(
'product-label product-label--recombinant">(.*?)</div>',
html, re.S)
if recombinant_list: # 判断是否有敲除验证
recombinant = "yes"
else:
recombinant = ''
modify_list = re.findall('(描述</h3>.*?</div>)', html, re.S)
if modify_list:
modify_list = re.findall('描述</h3>.*?\((.*?)\)',
modify_list[0], re.S)
modify = get_first_item(modify_list, 200)
else:
modify = ''
host_list = re.findall(
'宿主</h3>.*?<div class="value">(.*?)</div>', html, re.S)
host = get_first_item(host_list, 200)
species_reactivity_list = re.findall(
'种属反应性</h3>.*?</strong>(.*?)<', html, re.S)
species_reactivity = get_first_item(species_reactivity_list,
1000)
abid = re.findall('data-track-value="(.*?)"', html, re.S)
if abid:
price_url = 'https://www.abcam.cn/datasheetproperties/availability?abId=' + abid[
0]
sellable = 'yes'
else:
price_url = ''
sellable = 'no'
geneid_list = re.findall('Entrez Gene:(.*?)</li>', html, re.S)
if geneid_list:
geneid_list = list(
map(lambda geneid: geneid.strip(), geneid_list))
geneid = ','.join(geneid_list)
if len(geneid) > 499:
geneid = geneid[0:480]
else:
geneid = ''
siRNA_list = re.findall('alt="使用(.*?)细胞株进行验证', html, re.S)
if siRNA_list: # 判断是否有敲除验证
siRNA = "yes"
else:
siRNA = ''
swisprot_list = re.findall('SwissProt:(.*?)</li>', html, re.S)
if swisprot_list:
swisprot_list = list(
map(lambda swisprot: swisprot.strip(), swisprot_list))
swisprot = ','.join(swisprot_list)
if len(swisprot) > 499:
swisprot = swisprot[0:480]
else:
swisprot = ''
predicted_mw_list = re.findall(
'Predicted band size:</b>(.*?)<br>', html, re.S)
predicted_mw = get_first_item(predicted_mw_list, 200)
observed_mw_list = re.findall('Observed band size:</b> (.*?)<',
html, re.S)
observed_mw = get_first_item(observed_mw_list, 200)
isotype_list = re.findall(
'同种型</h3>.*?div class="value">(.*?)</div>', html, re.S)
isotype = get_first_item(isotype_list, 100)
citations_list = re.findall('被引用在 (.*?)文献中', html, re.S)
citations = get_first_item(citations_list, 100)
if citations_list:
reference_url = 'https://www.abcam.cn/DatasheetProperties/References?productcode=' + cataNo_list[
0]
else:
reference_url = ''
pdf_url_list = re.findall(
'class="pdf-links">.*?<li><a target="_blank" href="(.*?)"',
html, re.S)
if pdf_url_list:
pdf_url = 'https://www.abcam.cn' + get_first_item(
pdf_url_list, 300)
else:
pdf_url = ''
review_list = re.findall('"reviewCount": "(.*?)"', html, re.S)
review = get_first_item(review_list, 100)
lis = element.xpath(
'//*[@id="description_images"]/div[2]/ul/li')
image_qty = len(lis)
# 在此处写入检测图片
if lis:
for li in lis:
image_url_list = li.xpath('./div/a/@href')
image_url = get_first_item(image_url_list, 500)
description_list = li.xpath('./div[1]/div/div//text()')
description = get_first_item(description_list, 1000)
image_sql = 'insert into Abcam_Antibody_images (Catalog_Number, Image_url, Image_description) values ("{}","{}","{}");'.format(
cataNo, image_url, description)
self.mysql.insert_into_table(image_sql)
# 在此处写入应用信息
trs = element.xpath(
'//*[@id="description_applications"]/div[2]/table/tbody/tr'
)
if trs:
for tr in trs:
application_list = tr.xpath('./td[1]//text()')
application2 = get_first_item(application_list, 200)
dillution_list = tr.xpath('./td[3]//text()')
dillution = get_first_item(dillution_list, 1000)
application_sql = 'insert into Abcam_Antibody_application (Catalog_Number, Application, Dilution) values ("{}","{}","{}");'.format(
cataNo, application2, dillution)
self.mysql.insert_into_table(application_sql)
detail_sql = 'insert into Abcam_Antibody_detail(Sellable,Catalog_Number, Product_Name, Antibody_Type, Synonyms, Application, Conjugated, Clone_Number, Recombinant_Antibody, Modified, Host_Species, Antibody_detail_URL, GeneId, KO_Validation, Species_Reactivity, SwissProt,Predicted_MW,Observed_MW,Isotype,Citations,Citations_url,DataSheet_URL,Review,Price_url,Image_qty) values ("{}", "{}", "{}","{}", ' \
'"{}","{}","{}","{}","{}", "{}", "{}","{}", "{}", "{}","{}", "{}","{}","{}", "{}", "{}","{}", "{}", "{}","{}", "{}");'.format(sellable,cataNo, antiname,antibody_type,synonyms,application,conjugation,clone_number,recombinant,modify,host,url,pymysql.escape_string(geneid),siRNA,species_reactivity,pymysql.escape_string(swisprot),predicted_mw,observed_mw,isotype,citations,reference_url,pdf_url,review,price_url,image_qty)
self.mysql.insert_into_table(detail_sql)
except Exception as es:
print(es)
print(url)
else:
update_status_sql = 'update Abcam_Antibody_list set Antibody_Status = "1" where Antibody_detail_URL = "%s";' % url
self.mysql.insert_into_table(update_status_sql)
count += 1
print("\r获得抗体详情页进度: %d" % count, end="")
class Producer(threading.Thread):
headers = {
'Cookies':
'PP=1; _ga=GA1.2.1635461879.1565096809; _gid=GA1.2.133744421.1565496241; Hm_lvt_30fac56dd55db0f4c94ac3995'
'5a1d1f1=1565268961,1565389179,1565496240,1565510325; Qs_lvt_186141=1565096808%2C1565268960%2C1565389178%2C'
'1565496240%2C1565510324; _sp_ses.4591=*; mediav=%7B%22eid%22%3A%2295155%22%2C%22ep%22%3A%22%22%2C%22vid%22%'
'3A%22-XCl%25T1HEC%3A4I9xGrX(9%22%2C%22ctn%22%3A%22%22%7D; _gat_UA-367099-9=1; _dc_gtm_UA-367099-9=1; C2LC=CN'
'; JSESSIONID=C88C68C292A8E0EF6D45F465F0D12E1C.Pub1; Hm_lpvt_30fac56dd55db0f4c94ac39955a1d1f1=1565510331; Qs_p'
'v_186141=3753158417549899000%2C4277747906829928000%2C349668107189188000%2C3100574197771999000%2C23251166996415'
'81000; _sp_id.4591=0c85e63041a8e8b7.1565096808.6.1565510332.1565501036.a1a460db-b738-431c-9eb1-7f0dc0ed348b',
'DPR':
'1',
'Host':
'www.abcam.cn',
'Referer':
'https://www.abcam.cn/products?selected.productType=Primary+antibodies',
'User-Agent':
'Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 '
'Safari/537.36',
'X-Requested-With':
'XMLHttpRequest',
'Connection':
'close'
}
def __init__(self, pageurl_queue, *args, **kwargs):
super(Producer, self).__init__(*args, **kwargs)
self.pageurl_queue = pageurl_queue
self.mysql = MYSQL('new_antibodies_info')
def run(self):
while True:
if self.pageurl_queue.empty():
break
url = self.pageurl_queue.get()
self.parse_page(url)
time.sleep(random.uniform(1, 3))
def parse_page(self, url):
global count
try:
r = requests.get(url, headers=self.headers)
#r = gethtml(url)
except Exception as e:
self.pageurl_queue.put(url)
print('访问抗体列表页失败，尝试其他代理')
print(e)
else:
html = r.text
element = etree.HTML(html)
# print(html)
divs = element.xpath('.//div[@class="pws-item-info"]')
try:
for div in divs:
anti_name = div.xpath('.//h3/a/text()')[0]
anti_catanum = div.xpath('.//h3/a/span/text()')[0]
href_list = div.xpath('.//h3/a/@href')
href = 'https://www.abcam.cn/' + href_list[0]
# print(anti_name, anti_catanum, href)
sql = 'insert into Abcam_Antibody_list (Catalog_Number, Product_Name, Antibody_detail_URL)' \
'values("{}","{}","{}");'.format(anti_catanum, anti_name, href)
self.mysql.insert_into_table(sql)
except Exception as es:
print(url)
print(es)
else:
update_status_sql = 'update Abcam_Antibody_list_url set Antibody_Status = "1" where Antibody_list_URL = "%s";' % url
self.mysql.insert_into_table(update_status_sql)
count += 1
print("\r获得抗体详情页进度: %d" % count, end="")